<div class="trix-content">
  <div>This guided project shows you how to build an intelligent AI agent that autonomously handles an entire machine learning pipeline, from messy data cleanup to probability predictions. You won't just train a model manually. You'll create an agent powered by LangGraph and the ReAct pattern that reasons about which tools to use and when, transforming a single natural language instruction into a complete end to end ML workflow. From speed dating datasets to match probability scores, you'll learn to build agents that think through complex tasks and execute them without micromanagement.</div><div><br /></div><h1><strong>What You'll Learn</strong></h1><div>By the end of this project, you will be able to:</div><ul><li>Build autonomous AI agents with the ReAct pattern: Understand how to create agents that alternate between reasoning about what needs to happen next and taking action with tools, eliminating manual function chaining.</li><li>Design LangGraph workflows for machine learning pipelines: Use StateGraph to orchestrate sequential ML operations with conditional routing, tool nodes, and state management that scales beyond simple scripts.</li><li>Create custom tools for data cleaning, feature selection, and model training: Learn to wrap ML operations in LangChain tools that language models can intelligently invoke, including handling data leakage, categorical encoding, and missing values.</li><li>Implement probability based classification with XGBoost: Go beyond simple yes/no predictions to generate match probability scores, and evaluate model quality using ROC AUC metrics that measure ranking performance.</li><li>Handle real world data challenges in speed dating datasets: Clean byte string encodings, remove data leakage from decision variables, impute missing values, and use Recursive Feature Elimination to identify what actually predicts romantic chemistry.</li></ul><div><br /></div><h1><strong>Who Should Enroll</strong></h1><ul><li>Data scientists and ML engineers who want to automate repetitive pipeline steps and understand how agentic AI can orchestrate complex workflows without constant manual intervention.</li><li>Python developers interested in AI agents who want practical, production relevant experience with LangGraph and the ReAct pattern beyond simple chatbot demos.</li><li>Students and professionals exploring machine learning automation who need to understand how modern AI systems can reason about multistep tasks and make intelligent decisions about tool usage.</li></ul><div><br /></div><h1><strong>Why Enroll</strong></h1><div>Agentic AI isn't just hype. It's becoming the standard for building intelligent systems that can handle complex, multistep workflows. This project gives you hands on experience with the architecture patterns that power real world AI agents: state management, tool binding, conditional routing, and the ReAct reasoning loop. You'll finish with a working match prediction system you can adapt to other ML domains, plus the foundational understanding to know when agents add value versus when traditional scripts suffice. And as a bonus, you'll have built something genuinely fun for Valentine's Day.<br /><br /></div><h1><strong>What You'll Need</strong></h1><div>You should be comfortable with Python and have basic familiarity with pandas and introductory machine learning concepts like train/test splits and classification. Some exposure to scikit learn is helpful but not required. All dependencies (LangChain, LangGraph, XGBoost) are pre configured in the environment, and the project runs best on current versions of Chrome, Edge, Firefox, or Safari.</div>
</div>


Build a Dating Match Prediction Agent w/ ReAct and LangGraph

Learn how to build an AI agent that predicts romantic compatibility using LangGraph and machine learning. In this Valentine's Day themed guided project, you'll create an autonomous workflow that cleans speed dating data, selects optimal features, and trains an XGBoost probability model, all from a single natural language instruction. Perfect for beginners in AI agents, machine learning pipelines, or data science automation looking to combine intelligent reasoning with end to end ML workflows.

<div class="trix-content">
  <div>Have you ever wondered how families across Asia turn Lunar New Year celebrations into playful competitions for lucky money? Red pocket scrambles are a beloved tradition where relatives race to answer trivia questions to claim their share of digital hongbao. In this project, you'll build an AI-powered Lunar New Year game that combines cultural education with authentic holiday traditions. By orchestrating multiple GPT-4o-mini agents through CrewAI, you'll create a system where a Family Matriarch generates questions, a Cultural Historian ensures accuracy, and a Family Chat Simulator brings the experience to life with realistic reactions. Along the way, you'll gain hands-on experience with multi-agent AI architecture, Gradio web interface design, and implementing game mechanics that mirror real-world cultural practices.<br /><br /></div><h1><strong>What You'll Learn</strong></h1><div>By the end of this project, you will be able to:</div><ul><li>Build multi-agent AI systems with CrewAI: Orchestrate specialized GPT-4o-mini agents that collaborate to generate, verify, and enhance content quality.</li><li>Design culturally authentic game mechanics: Implement the traditional red pocket money distribution algorithm that randomly divides winnings among players.</li><li>Create festive web interfaces with Gradio: Develop an interactive app featuring custom CSS styling, state management, and dynamic UI updates.</li><li>Apply AI to cultural education: Learn how specialized agents can deliver region-specific content about Mainland China, Vietnam, Korea, and North American Lunar New Year traditions.</li></ul><div><br /></div><h1><strong>Who Should Enroll</strong></h1><ul><li>Python developers interested in building AI-powered educational games and cultural applications.</li><li>Educators and language instructors looking to create interactive tools for teaching Asian traditions and customs.</li><li>Students and researchers exploring multi-agent systems and practical LLM applications beyond chatbots.</li></ul><div><br /></div><h1><strong>Why Enroll</strong></h1><div>This project demonstrates how multi-agent AI architecture creates more robust and engaging applications than single-model approaches. Instead of relying on one AI to generate questions, verify accuracy, and simulate conversations, you'll see how specialized agents working together produce higher-quality, culturally authentic content. By the end, you'll have a shareable Lunar New Year celebration app, practical experience with CrewAI and GPT-4o-mini, and a deeper understanding of how to build AI systems that respect and celebrate cultural diversity.<br /><br /><br /></div><h1><strong>What You'll Need</strong></h1><div>To get the most out of this project, you should have:</div><ul><li>Basic Python programming knowledge.</li><li>Interest in cultural education or game development.</li></ul><div>All dependencies are pre-configured in the environment, and the project runs best on current versions of Chrome, Edge, Firefox, or Safari.</div>
</div>


Build a Lunar New Year Game with CrewAI Multi-Agent System

Build an interactive Gradio web app powered by CrewAI and GPT-4o-mini multi-agent AI to create a Lunar New Year red pocket game testing cultural knowledge across China, Korea, North America etc. Use CrewAI to orchestrate three agents, Family Matriarch, Cultural Historian, and Family Chat Simulator, delivering accurate trivia with family interactions. Implement traditional red pocket money distribution, design festive red-and-gold UI, and build a game engine tracking player progress. Create a shareable celebration app combining AI-powered cultural education with authentic holiday traditions.

<div class="trix-content">
  <div>This capstone course provides a comprehensive, project-based experience that brings together the data science skills and techniques developed throughout the <strong>IBM Data Analytics with Excel and R Professional Certificate</strong>. You will assume the role of a newly hired Data Scientist and work through a realistic business challenge requiring end-to-end data analysis on real-world datasets.<br /><br />After completing this capstone project, you will be able to:<br /><br /></div><ul><li>Collect data from multiple sources, including writing web scraping programs to extract HTML data and convert it into structured data frames</li><li>Prepare datasets for modeling by handling missing values, normalizing and formatting data, binning variables, and encoding categorical features</li><li>Perform exploratory data analysis using SQL, Tidyverse, and ggplot2 to generate descriptive statistics, correlations, and visual insights</li><li>Apply linear regression models to analyze relationships in real-world datasets and interpret analytical results</li><li>Create effective visualizations and build an interactive Shiny dashboard with Leaflet maps to communicate findings</li><li>Present complete data analysis reports, including an executive summary, tailored to technical and non-technical stakeholders</li></ul><div> </div><div>The course begins by having you collect and understand data from multiple sources. This includes writing a web scraping program to extract data from HTML pages. Using Tidyverse, you will perform data wrangling and preparation tasks such as handling missing values, formatting and normalizing data, binning variables, and converting categorical values into numeric form. </div><div> </div><div>Exploratory data analysis will be conducted using SQL, Tidyverse, and ggplot2, enabling you to generate descriptive statistics, correlations, and visual insights.</div><div> </div><div>As part of the modeling phase, you will apply linear regression to analyze relationships within the data and create charts and plots to communicate findings effectively. You will also design and build an interactive dashboard and R Shiny application incorporating a Leaflet map to support stakeholder exploration of results.</div><div> </div><div>The course culminates in a formal data analysis presentation, including an executive summary tailored to organizational stakeholders. Successful completion demonstrates your readiness to perform applied data science tasks, from data acquisition and preparation through modeling, visualization, and professional communication.<br /><br />The following skills are required to be successful with this course: </div><ul><li>We recommend completing all previous courses in the <strong>IBM Data Analytics with Excel and R Professional Certificate</strong> before starting this capstone.</li></ul><div><br /></div><h1>Course Syllabus</h1><div><br /><strong>Module 1 - Capstone Overview and Data Collection</strong></div><div><br /></div><ul><li>Capstone Overview</li><li>Data Collection Overview</li><li>Hands-on Lab: Complete the Data Collection with Web Scraping Notebook</li><li>Hands-on Lab: Complete the Data Collection with OpenWeather API Notebook</li><li>Graded Checkpoints</li></ul><div><br /><strong>Module 2 - Data Wrangling </strong></div><div><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Data Wrangling Overview</li><li>Hands-on Lab: Complete Data Wrangling with Regular Expressions Notebook</li><li>Hands-on Lab: Complete Data wrangling with dplyr Notebook</li><li>Graded Checkpoints</li></ul><div><br /></div><div><strong>Module 3 - Performing Exploratory Data Analysis with SQL, Tidyverse &amp; ggplot2 </strong></div><div><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Hands-on Lab: Load Data into Db2 on IBM Cloud</li><li>Hands-on Lab: Complete the EDA with SQL Lab</li><li>Hands-on Lab: Complete the EDA with Data Visualization Lab</li><li>Graded Checkpoints</li></ul><div><br /></div><div><strong>Module 4 - Building a Shiny Dashboard </strong></div><div><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Predict Bike-Sharing Demand Using Regression Models</li><li>Hands-on Lab: Complete the Building a Baseline Regression Model Lab</li><li>Hands-on Lab: Complete the Improving the Linear Model lab</li><li>Graded Checkpoints</li></ul><div><br /><strong>Module 5 - Building a R Shiny Dashboard App </strong></div><div><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Create a R Shiny Dashboard</li><li>Hands-on Lab: Build a Bike-Sharing Demand Prediction App with R Shiny and Leaflet</li><li>Hands-on Lab: Enhance the Bike-Sharing Demand Prediction App with City Details Plots</li><li>Graded Checkpoints</li></ul><div><br /></div><div><strong>Module 6 - Present Your Data-Driven Insights</strong></div><div><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Elements Of A Successful Data Findings Report</li><li>Structure Of A Report</li><li>Best Practices For Presenting Your Findings</li><li>(Optional) Hands-on Lab: Getting Started With PowerPoint For The Web</li><li>(Optional) Hands-on Lab: Basics of PowerPoint</li><li>(Optional) Hands-on Lab: Save your PowerPoint Presentation as PDF</li><li>Final Submission Overview and Instructions</li><li>Exercise: Preparing Your Presentation (with provided slide template)</li><li>Peer Review: Submit your Work and Review your Peers</li></ul>
</div>


Capstone Project: Data Science with R

This capstone course applies core data science skills to real-world datasets through hands-on analysis and modeling with tools like R, SQL, Tidyverse, and visualization tools, culminating in an interactive dashboard and executive presentation.

<div class="trix-content">
  <div>This course introduces R as a powerful language purpose-built for data analysis and predictive modeling, guiding you through a structured, end-to-end analytical workflow. You will begin with a business question and learn how to transform raw data into actionable insights through data preparation, exploratory analysis, and model development.<br /><br />After completing this course, you will be able to:<br /><br /></div><ul><li>Prepare data for analysis by handling missing values, normalizing and formatting variables, binning data, and encoding categorical features</li><li>Examine datasets using descriptive statistics, data grouping, correlation analysis, and analysis of variance (ANOVA)</li><li>Build and compare predictive models using simple linear, multiple linear, and polynomial regression techniques</li><li>Evaluate model performance by identifying overfitting and underfitting conditions</li><li>Tune models using regularization and grid search to improve predictive accuracy and robustness</li><li>Apply end-to-end R-based workflows to analyze real-world datasets and generate actionable insights</li></ul><div><br />The course starts with a focus on data wrangling techniques, including handling missing values, formatting and normalizing data, binning variables, and converting categorical values into numeric form. You will perform exploratory data analysis using descriptive statistics, grouping techniques, correlation analysis, and analysis of variance (ANOVA) to better understand patterns and relationships within your data.</div><div> </div><div>Once your data is prepared, you will develop predictive models using simple linear, multiple linear, and polynomial regression. You will evaluate model performance, diagnose overfitting and underfitting, and apply tuning techniques such as regularization and grid search to improve results and ensure analytical rigor.</div><div> </div><div>Through a hands-on case study analyzing airline departure and arrival data, you will assume the role of a data analyst tasked with predicting flight delays. Using the Airline Reporting Carrier On-Time Performance Dataset, you will practice reading and preprocessing data, building and refining models, and selecting the best-performing solution. </div><div> </div><div>By the end of the course, you will have practical experience delivering reliable, data-driven insights using R.<br /><br />The following skills are required to be successful with this course:  </div><ul><li>Basic R programming skills </li><li>It is recommended that you complete the <strong>R for Data Science</strong> course prior to starting this course. </li></ul><div><br /></div><h1>Course Syllabus</h1><div><br />Module 1 - Introduction to Data Analysis with R</div><div><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>The Problem</li><li>Understanding the Data</li><li>R Packages for Data Science</li><li>Importing and Exporting Data in R</li><li>Getting Started analyzing Data in R</li><li>Hands-on Lab 1: Introduction to Data Analysis</li><li>Summary &amp; Highlights</li><li>Practice Quiz</li><li>Graded Quiz</li></ul><div><br />Module 2 - Data Wrangling</div><div><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Pre-Processing Data in R</li><li>Dealing with Missing Values in R</li><li>Data Formatting in R</li><li>Data Normalization in R</li><li>Binning in R</li><li>Turning Categorical Values to a Numeric Variable in R</li><li>Hands-on Lab 2: Data Wrangling</li><li>Summary &amp; Highlights</li><li>Practice Quiz</li><li>Graded Quiz</li></ul><div><br /></div><div>Module 3 - Exploratory Data Analysis</div><div><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Descriptive Statistics</li><li>Grouping Data in R</li><li>Analysis of Variance (ANOVA) in R</li><li>Correlation in R</li><li>Correlation - Statistics</li><li>Hands-on Lab 3: Exploratory Data Analysis</li><li>Summary &amp; Highlights</li><li>Practice Quiz</li><li>Graded Quiz</li></ul><div><br />Module 4 - Model Development in R</div><div><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Introduction to Model Development</li><li>Simple Linear Regression</li><li>Multiple Linear Regression</li><li>Assessing Models Visually</li><li>Polynomial Regression</li><li>Assessing the Model</li><li>Prediction and Decision Making</li><li>Hands-on Lab 4: Model Development</li><li>Summary &amp; Highlights</li><li>Practice Quiz</li><li>Graded Quiz</li></ul><div><br /><br /></div><div>Module 5 - Model Evaluation</div><div><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Model Evaluation</li><li>Overfitting and Underfitting</li><li>Regularization</li><li>Grid Search</li><li>Model Evaluation</li><li>Summary &amp; Highlights  </li><li>Practice Quiz</li><li>Graded Quiz</li><li>Final Project</li></ul><div><br /><br /></div><div>Syntax Cheat Sheet (Course Overview)<br /><br /></div><ul><li>Overview and Scenario</li><li>IBM Watson Setup</li><li>Download and Complete the Tasks in a Notebook</li><li>Add the Completed Notebook to Watson Studio</li><li>Share Your Notebook with a Public URL</li><li>Peer Review: Submit your Work and Review your Peers</li><li>Final Exam</li></ul>
</div>


R for Data Analysis

Learn R for data analysis and predictive modeling by preparing data, exploring relationships, and building regression models. You will analyze airline performance data to evaluate, tune, and compare models using real-world datasets.

<div class="trix-content">
  <div>This course introduces relational databases and SQL as essential tools for data science, guiding you through practical techniques for accessing, querying, and analyzing data using SQL and R. You will build foundational knowledge of database concepts while developing hands-on skills for working with real-world datasets in a data science environment.<br /><br />After completing this course, you will be able to: <br /><br /></div><ul><li>Create and access a cloud-based database instance for data analysis</li><li>Compose and execute basic SQL statements, including SELECT, INSERT, UPDATE, DELETE, CREATE, and DROP</li><li>Construct SQL queries to filter, sort, and group data, use built-in functions, write nested queries, and access multiple tables</li><li>Analyze real-world datasets from Jupyter notebooks by combining SQL querying with R-based analysis</li><li>Apply relational database concepts to organize, retrieve, and manage structured data</li><li>Use integrated SQL and R workflows to support practical data science tasks</li></ul><div><br />You will begin by creating and accessing a database instance in the cloud and learning how SQL is used to communicate with databases. Through a series of hands-on labs, you will compose and execute core SQL statements such as SELECT, INSERT, UPDATE, DELETE, CREATE, and DROP. You will also construct more advanced queries to filter, sort, and group results, apply built-in functions, write nested queries, and access data across multiple tables.</div><div> </div><div>In addition, you will learn how to integrate SQL with R inside Jupyter notebooks, enabling you to analyze data by combining SQL queries with R-based analysis workflows. Throughout the course, you will work with real databases, real data science tools, and authentic datasets to reinforce practical learning.</div><div> </div><div>By the end of the course, you will be able to confidently query databases, manage data using SQL, and perform exploratory analysis in Jupyter using both SQL and R—demonstrating readiness to apply these core skills in real-world data science and data analysis projects.<br /><br />The following skills are required to be successful with this course: </div><ul><li>No prior knowledge of databases, SQL, or R Programming is required.</li></ul><div><br /></div><h1>Course Syllabus</h1><div><strong>Module 1: Basic SQL<br /></strong><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Video: SELECT Statement</li><li>Video: SELECT statement examples</li><li>Lab: Simple SELECT Statements</li><li>Video: COUNT, DISTINCT, LIMIT</li><li>Lab: COUNT, DISTINCT, LIMIT</li><li>Video: INSERT Statement</li><li>Video: UPDATE and DELETE Statements</li><li>Lab: INSERT, UPDATE, and DELETE</li><li>Reading: Summary and Highlights</li><li>Practice Quiz: Basic SQL</li><li>Reading: SQL Cheat Sheet: Basics - SELECT, INSERT, UPDATE, DELETE, COUNT, DISTINCT, LIMIT</li><li>Graded Quiz: Basic SQL</li></ul><div><br /></div><div><strong><br />Module 2: Introduction to Relational Databases and Tables<br /></strong><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Video: Introduction to Databases</li><li>Video: Relational Database Concepts</li><li>Video: Types of SQL statements (DDL vs. DML)</li><li>Video: CREATE TABLE Statement</li><li>Video: ALTER, DROP, and Truncate Tables</li><li>Reading: Examples to CREATE and DROP Tables</li><li>Lab: CREATE, ALTER, TRUNCATE, DROP</li><li>Lab: Create and Load Tables using SQL Scripts</li><li>Module Summary: Introduction to Relational Databases and Tables</li><li>Practice Quiz:  Introduction to Relational Databases and Tables</li><li>SQL Cheat Sheet: CREATE TABLE, ALTER, DROP, TRUNCATE</li><li>Graded Quiz: Introduction to Relational Databases and Tables</li><li>Video: How to Create a Database Instance on Cloud</li><li>Lab: Obtain IBM Cloud Feature Code and Activate Trial Account</li><li>[Optional] Lab: Using IBM Db2</li></ul><div><br /></div><div><strong><br />Module 3: Intermediate SQL<br /></strong><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Video: Using String Patterns, Ranges</li><li>Video: Sorting Result Sets</li><li>Video: Grouping Result Sets</li><li>Lab: String Patterns, Sorting, and Grouping</li><li>Reading: Summary &amp; Highlights</li><li>Video: Built-in Database Functions</li><li>Video: Date and Time Built-in Functions</li><li>Lab: Built-in Functions</li><li>Video: Sub-Queries and Nested Selects</li><li>Lab: Sub-Queries and Nested SELECTs</li><li>Video: Working with Multiple Tables</li><li>Lab: Working with Multiple Tables</li><li>Summary: Intermediate SQL</li><li>Practice Quiz: Intermediate SQL</li><li>SQL Cheat Sheet: Intermediate - LIKE, ORDER BY, GROUP BY</li><li>Graded Quiz: Intermediate SQL</li><li>[Optional] Lab: Using IBM Db2</li></ul><div><br /></div><div><strong><br />Module 4: Getting Started with Databases using R<br /></strong><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Video: Why Use R with Databases</li><li>Video: R Persistence Options</li><li>Video: Terminology Comparison</li><li>Video: Mapping Data between R and RDBMS</li><li>Video: Database Design Considerations</li><li>Lab: Review using Jupyter and R Dataframes</li><li>Cheat Sheet: R Basics</li><li>Video: Connectivity Options</li><li>Video: Connecting with RJDBC</li><li>Video: Connectivity Using ODBC</li><li>Video: RODBC in Detail</li><li>Video: Metadata Discovery</li><li>Lab: Accessing Your Database using RJDBC</li><li>(Optional) Lab: Accessing Your Database using RJDBC</li><li>Lab: Accessing Your Database with RSQLIte</li><li>Summary &amp; Highlights: Getting Started with Databases using R</li><li>Practice Quiz: Connecting to Databases from R </li><li>Quiz: Practice Quiz : R and Relational Databases</li><li>Cheat Sheet: Getting Started with Databases using R</li><li>Graded Quiz: Getting Started with Databases using R</li></ul><div><br /></div><div><strong><br />Module 5: Working with Database Objects using R<br /></strong><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Video: Working with Data</li><li>Video: Database Design and Data Preparation</li><li>Video: Creating Physical Database Objects</li><li>Video: Loading the Data</li><li>Video: Querying Data (SQL SELECT)</li><li>Video: Analyzing the Data</li><li>Lab: Creating and Querying Database Objects from R using RSQLite with SQLite</li><li>Summary and Highlights: Working with Database Objects using R</li><li>Practice Quiz: Working with Database Objects using R</li><li>CheatSheet: Creating Database Objects &amp; Querying Data from R</li><li>Graded Quiz: Working with Database Objects using R</li></ul><div><br /><br /></div><div><strong>Module 6: Course Project</strong></div><div><br /></div><ul><li>Module Introduction and Learning Objectives</li><li>Lab: Practice Querying Real World Datasets</li><li>[Optional] Practice Lab: Practice Querying Real World Datasets</li><li>Final Project Overview</li><li>Reading: Final Project Submission Guidelines and Deliverables</li><li>Lab for Final Project - Data Analytics for Canadian Crop Production Data Set</li><li>(Optional) Jupyter Notebook with Problems for Peer Reviewed Assignment</li><li>Option 1: AI Graded - Final Project Submission and Evaluation</li><li>Option 2: Peer Graded - Final Project Submission and Evaluation</li></ul><div><br /></div><div><strong><br />Final Exam<br /></strong><br /></div><ul><li>Final Exam Instructions</li><li>Practice Final Exam</li><li>Final Exam - Timed Exam</li></ul><div><br /></div><div><strong><br />Course Wrap-Up<br /></strong><br /></div><ul><li>Reading: Congratulations &amp; Next Steps</li><li>Thanks from the Course Team</li><li>Copyrights and Trademarks</li></ul><div><br /></div><div><strong>Course Rating and Feedback<br /></strong><br /></div><ul><li>Course Rating and Feedback</li></ul><div><br /></div>
</div>


SQL for Data Science with R

Learn SQL and R for data science by working with cloud databases and real-world datasets. Create database instances, write SQL queries, and analyze data from Jupyter notebooks using integrated SQL and R workflows.

<div class="trix-content">
  <h1>About this course</h1><div>In this intermediate course, you’ll learn the essentials of PyTorch for machine learning techniques. Starting with tensors, you’ll understand their role in machine learning and how to perform basic operations with them. You’ll also explore differentiation in PyTorch, which is key for optimizing models. With hands-on labs, you’ll apply these concepts to work with simple and Torch Vision datasets, gaining experience in handling data for model training.</div><div> </div><div>You’ll then move into regression techniques, beginning with linear regression, where you’ll learn how to predict outcomes and optimize models using gradient descent. You’ll understand key concepts like loss functions and the steps involved in model training, which will prepare you for more complex machine learning tasks.</div><div> </div><div>The course will also cover more advanced regression techniques, including multiple input-output linear regression. You’ll learn how to handle multi-dimensional data, make predictions with multiple features and outputs, and train more sophisticated models.</div><div> </div><div>Classification is another key area of focus, where you’ll dive into logistic regression and learn how to apply it to solve classification problems. Through exercises, you’ll explore how to use linear classifiers, apply loss functions like Cross Entropy Loss, and implement effective models for binary classification.</div><div> </div><div>Finally, you’ll apply your learning to real-world problems. The practice project will involve building a neural network to classify breast cancer data, while the final project will challenge you to develop a League of Legends match predictor. You’ll work through data preparation, model building, and optimization, while receiving peer feedback to refine your skills.</div><div> </div><div>By the end of the course, you’ll be equipped to build and optimize machine learning models with PyTorch, solving regression and classification problems efficiently and effectively. You’ll gain the experience necessary to tackle machine learning challenges and develop your skills further in this rapidly growing field.<br /><br /></div><h1>What you will learn: </h1><div>After completing this course, you will be able to: </div><ul><li>Define tensors and understand their applications in PyTorch.</li><li>Explain linear regression and how to apply it using PyTorch.</li><li>Implement stochastic and mini-batch gradient descent algorithms.</li><li>Compare different methods of regression (linear, multiple) in terms of predictions and loss functions.</li><li>Assess the performance of a model using training, validation, and test splits.</li><li>Develop a final project that applies learned techniques to classify or predict outcomes in a dataset.</li></ul><div><br /></div><h1>Course Syllabus</h1><div><strong>Module 1: Tensors 1D<br /></strong><br /></div><div><strong>Welcome</strong></div><ul><li>Video: Course Introduction</li><li>Reading: Course Overview</li><li>General Information</li><li>Learning Objectives and Syllabus</li><li>Grading Scheme</li><li>Helpful Tips for Course Completion</li><li>Video: Overview of Tensors </li></ul><div><strong>Tensors 1D</strong></div><ul><li>Errata:Tensors ID</li><li>Video: Tensors 1D </li><li>Reading: Tensors 1D </li><li>Lab2: Tensors 1D </li></ul><div><strong>Two-Dimensional Tensors</strong></div><ul><li>Errata:Two-Dimensional Tensors </li><li>Video: Two-Dimensional Tensors </li><li>Lab: Two-Dimensional Tensors </li></ul><div><strong>Derivatives in PyTorch</strong></div><ul><li>Video: Differentiation in PyTorch </li><li>Lab: Differentiation in PyTorch </li></ul><div><strong>Simple Dataset</strong></div><ul><li>Video: Simple Dataset </li><li>Lab: Simple Dataset</li></ul><div><strong>Dataset</strong></div><ul><li>Video: Dataset </li><li>Lab: Dataset </li><li>Lab: Torch Vision Datasets </li><li>Module-level Graded Quiz: Tensor and Dataset</li></ul><div><br /><strong>Module 2: Linear Regression<br /></strong><br /></div><div><strong>Linear Regression Prediction</strong></div><ul><li>Video: Linear Regression Prediction </li><li>Lab: Linear Regression 1D: Prediction  </li></ul><div><strong>Linear Regression Training</strong></div><ul><li>Errata: Linear Regression Training  </li><li>Video: Linear Regression Training  </li><li>Video: Loss  </li></ul><div><strong>Gradient Descent and Cost</strong></div><ul><li>Video: Gradient Descent and Cost </li><li>Video: Cost  </li></ul><div><strong>PyTorch Slope</strong></div><ul><li>Video: Linear Regression PyTorch </li><li>Lab: Linear Regression ID: Training one Parameter</li></ul><div><strong>Linear Regression Training</strong></div><ul><li>Errata: PyTorch Linear Regression Training Slope and Bias  </li><li>Video: PyTorch Linear Regression Training Slope and Bias  </li><li>Lab: Linear Regression: Prediction </li><li>Module-level Graded Quiz: Linear Regression</li></ul><div><br /><strong>Module 3: Linear Regression PyTorch Way<br /></strong><br /></div><div><strong>Stochastic Gradient Descent and Data Loader</strong></div><ul><li>Video: Stochastic Gradient Descent  </li><li>Lab: Stochastic Gradient Descent and Data Loader   </li></ul><div><strong>Mini-Batch Gradient Descent</strong></div><ul><li>Video: Mini-Batch Gradient Descent  </li><li>Lab: Mini-Batch Gradient Descent  </li></ul><div><strong>Optimization in PyTorch</strong></div><ul><li>Video: Optimization in PyTorch </li><li>Lab: Optimization in PyTorch </li></ul><div><strong>Training, Validation, and Test Split</strong></div><ul><li>Video: Training, Validation, and Test Split </li><li>Errata: Training, Validation, and Test Split PyTorch</li><li>Video: Training, Validation, and Test Split PyTorch </li><li>Lab: Training, Validation, and Test Split in PyTorch </li><li>Module-level Graded Quiz: Linear Regression PyTorch Way</li></ul><div><br /><strong>Module 4: Multiple Input Output Linear Regression<br /></strong><br /></div><div><strong>Multiple Linear Regression Prediction</strong></div><ul><li>Video: Multiple Linear Regression Prediction </li><li>Lab: Multiple Linear Regression Prediction </li><li>Video: Multiple Linear Regression Training </li><li>Lab: Multiple Linear Regression Training </li></ul><div><strong>Multiple Output Linear Regression</strong></div><ul><li>Video: Linear Regression Multiple Outputs  </li><li>Lab: Multiple Linear Regression Prediction </li><li>Video: Multiple Output Linear Regression Training </li><li>Lab: Multiple Linear Regression Training </li><li>Module-level Graded Quiz: Multiple Input Output Linear Regression </li></ul><div><br /><strong>Module 5: Logistic Regression for Classification<br /></strong><br /></div><div><strong>Linear Classier</strong></div><ul><li>Video: Linear Classifiers  </li></ul><div><strong>Logistic Regressioin Prediction</strong></div><ul><li>Video: Logistic Regression Prediction   </li><li>Lab: Logistic Regression Prediction  </li></ul><div><strong>Bernoulli Distribution and Maximum Likelihood Estimation</strong></div><ul><li>Video: Bernoulli Distribution and Maximum Likelihood Estimation </li></ul><div><strong>Logistic Regression Cross Entropy Loss</strong></div><ul><li>Video: Logistic Regression Cross Entropy Loss    </li><li>Lab: Logistic Regression Mean Square Error </li><li>Lab: Logistic Regression Cross Entropy  </li><li>Module-level Graded Quiz: Linear Classifiers</li></ul><div><br /><strong>Module 6: Practice Project and Final Project<br /></strong><br /></div><div><strong>Practice Project and Final Project</strong></div><ul><li>Practice Project: Neural Network for Breast Cancer Classification</li><li>Reading: Final Project Overview</li><li>Final Project: League of Legends Match Predictor</li><li>Reading Peer-Review: Final Project League of Legends Match Predictor</li></ul><div><strong>Course Wrap-Up</strong></div><ul><li>Congratulations and Next Steps</li><li>Thanks from the Course Team</li><li>Reading: Copyrights and Trademarks</li></ul><h1>General Information</h1><ul><li>This course is self-paced. </li><li>This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer, or Safari. </li></ul><h1>Recommended Skills Prior to Taking this Course</h1><div>The following skills are required to be successful with this course: </div><ul><li>High School level Mathematics</li><li>Working knowledge of Python.</li><li>Machine Learning with Python</li><li>Fundamentals of Deep Learning</li></ul>
</div>


PyTorch Fundamentals for Machine Learning

Learn the fundamentals of PyTorch for machine learning in this course. Topics include tensors, linear regression, logistic regression, and optimization techniques like gradient descent. Apply your skills through hands-on projects and quizzes.

<div class="trix-content">
  <div>With data privacy regulations tightening and real-world datasets often locked behind compliance walls, synthetic data generation has become a must-have skill for ML practitioners. This guided project shows you how to build a complete synthetic data pipeline using LangChain, GPT-5 mini, and proven statistical techniques. You won't just generate random noise, you'll create datasets that preserve the statistical properties and correlations of real data while containing zero actual sensitive information. From healthcare records to e-commerce transactions, you'll learn to synthesize data that's useful, realistic, and safe to share.</div><div><br /></div><h1>What You'll Learn</h1><div>By the end of this project, you will be able to:</div><ul><li><strong>Build hybrid synthetic data generators with LLMs and statistical methods:</strong> Understand when to use GPT-5 for text and structured data versus statistical sampling for numerical fields—and how to combine both for best results.          </li><li><strong>Implement correlation-preserving generation with copula methods:</strong> Use the Synthetic Data Vault (SDV) library to create multi-variate data that maintains realistic relationships between features, not just independent random values.   </li><li><strong>Validate synthetic data quality and privacy:</strong> Apply statistical tests, visualizations, and privacy checks to ensure your synthetic datasets are both useful and safe from re-identification risks. </li></ul><h1>Who Should Enroll</h1><ul><li><strong>Data scientists and ML engineers</strong> who need training data but face privacy, compliance, or data scarcity constraints—and want a practical solution they can implement immediately.   </li><li><strong>Software developers</strong> working on testing and QA who need realistic, diverse datasets without the hassle of anonymizing production data or waiting on data access requests.  </li><li><strong>Privacy and compliance professionals</strong> looking to understand synthetic data from a technical perspective so they can evaluate solutions and guide their teams effectively.                                       <br />                                                                                                                                                                                                                                          </li></ul><h1>Why Enroll</h1><div>Synthetic data isn't just a workaround, it's becoming the standard for responsible AI development. This project gives you hands-on experience with the techniques that power production-grade synthetic data systems: LLM-based generation, Gaussian copulas, conditional sampling, and privacy validation. You'll finish with a working pipeline you can adapt to your own domain, plus the understanding to know when synthetic data is the right choice and when it isn't. </div><div><br /></div><h1>What You'll Need</h1><div>You should be comfortable with Python and have basic familiarity with pandas and NumPy. Some exposure to machine learning concepts is helpful but not required. All dependencies are pre-configured in the environment, and the project runs best on current versions of Chrome, Edge, Firefox, or Safari.  </div>
</div>


Synthetic Dataset Generation with LLM Agent and Statistics

Ever wonder how companies train ML models without exposing sensitive data? Synthetic data is the answer. In this project, you'll use LangChain, OpenAI's GPT-5 mini, and statistical methods to build a pipeline that generates realistic, privacy-safe datasets from scratch. You'll learn when to use LLMs versus statistical sampling, how to validate quality, and how to check for privacy leaks. Walk away ready to create synthetic data for any domain.

<div>Advance your career in the rapidly evolving field of artificial intelligence with this Professional Certificate, an eight-course program designed to help you master advanced generative AI techniques.&nbsp;<br><br>After completing this professional certificate, you will be able to:&nbsp;<br><br></div><ul><li>Build the job-aligned GenAI skills and hands-on experience to create RAG, multimodal, and agentic AI applications employers need</li><li>Learn to design and chain AI tools with LangChain for modular, reusable gen AI workflows</li><li>Implement function calling, RAG, and vector stores to build intelligent, context-aware applications</li><li>Create autonomous AI agents using LangGraph, CrewAI, and AG2 for real-world impact</li><li>Integrate multimodal AI techniques for text, image, and audio processing</li><li>Develop a portfolio of practical AI projects demonstrating end-to-end engineering skills</li></ul><div><br>You’ll learn essential skills including prompt engineering, Retrieval-Augmented Generation (RAG), multimodal AI, and the design of autonomous multi-agent systems. With hands-on labs and guided projects, you’ll gain the technical depth needed to build sophisticated, context-aware AI applications for real-world use.</div><div>&nbsp;</div><div>Throughout the program, you will work with industry-leading tools and frameworks such as LangChain, LangGraph, CrewAI, AG2, BeeAI, and the Model Context Protocol (MCP). You’ll integrate external tools and APIs into your AI applications, orchestrate reusable workflows, apply vector databases for retrieval, and build multimodal systems capable of processing text, images, and audio.</div><div>&nbsp;</div><div>In addition to structured learning, you’ll complete a portfolio of applied projects—including RAG pipelines, prompt-engineered workflows, function-calling agents, Gradio interfaces, similarity search applications, and custom data visualization agents. The program concludes with a real-world capstone that showcases your end-to-end AI engineering capabilities.<br><br></div><div>Designed for software developers, data scientists, and ML engineers with Python experience, this certificate provides the advanced skills needed to excel as an AI engineer. Upon completion, you’ll earn a Professional Certificate from IBM, demonstrating your mastery of next-generation AI technologies.<br><br>Recommended Experience:<br><br></div><ul><li>Experience with Python programming is recommended. Familiarity with software development and AI concepts can also enhance your learning experience.</li></ul>

IBM RAG and Agentic AI Professional Certificate

Master advanced generative AI skills with RAG, multimodal processing, and agentic systems to build real-world AI applications and accelerate your AI engineering career through hands-on projects.

<div class="trix-content">
  <div>Vector databases are transforming how modern AI systems retrieve and understand information. In this course, you’ll explore the core principles of vector databases, how they compare to traditional databases, and why they are essential in recommendation systems and Retrieval-Augmented Generation (RAG). </div><div><br />After completing this course, you will be able to: <br /><br /></div><ul><li>Describe the core principles of vector databases and how they compare to traditional data systems</li><li>Perform key vector database tasks in ChromaDB, including managing collections and embeddings</li><li>Use similarity search methods to analyze and retrieve data across vector spaces</li><li>Create a functional recommendation system utilizing vector databases and embedding models</li><li>Interpret how vector storage, indexing, and retrieval mechanisms work internally</li><li>Develop a foundational understanding of how vector databases integrate into RAG pipelines</li></ul><div><br />You’ll learn foundational concepts like embeddings, vector operations, and similarity search while gaining a practical understanding of ChromaDB’s architecture and capabilities.<br /><br /></div><div>Through guided, hands-on labs, you’ll build and manage collections, load embeddings, and perform similarity searches using real datasets. You’ll gain experience executing core database operations in ChromaDB, including updating, deleting, and maintaining collections for scalable retrieval workflows.<br /><br /></div><div>Finally, you’ll apply your skills by building a functional recommendation system using ChromaDB and a Hugging Face embedding model. This real-world project reinforces how vector databases enable accurate, context-aware search in AI applications.<br /><br /></div><div>By the end of the course, you’ll understand the internal mechanisms behind RAG and vector databases, and you’ll be ready to build retrieval-powered systems that deliver intelligent, relevant results.<br /><br />The following skills are required to be successful with this course: </div><div> </div><ul><li>Python programming</li><li>Familiarity with Databases</li><li>Generative AI Application Development Fundamentals</li></ul><div><br /><br /></div><h1><strong>Course Syllabus</strong></h1><div><br /></div><div>Welcome to the Course</div><ul><li>Course Introduction</li><li>Course Overview</li><li>RAG and Agentic AI Professional Certificate Overview</li><li>Reading: Helpful Tips for Course Completion</li></ul><div><br /></div><div>Module 1: Introduction to Vector Databases and Chroma DB</div><ul><li>Module Summary and Learning Objectives</li><li>Introduction to Vector Databases and Similarity Search<ul><li>Vector Database Concepts</li><li>Reading: Vector Databases Versus Traditional Databases</li><li>Vector Database Types</li><li>Applications of Vector Databases</li><li>Reading: Similarity Search</li><li>Lab: Similarity Search by Hand</li><li>[Optional] Interactive Lesson Recap Podcast (AI-Powered)</li><li>Practice Quiz: Introduction to Vector Databases and Similarity Search</li></ul></li><li>Exploring Chroma DB<ul><li>Chroma DB Key Concepts and Architecture</li><li>Reading: Chroma DB Filtering</li><li>Reading: Similarity Search and HNSW in Chroma DB</li><li>Lab: Similarity Search on Text Using Chroma DB and Python</li><li>[Optional] Interactive Lesson Recap Podcast (AI-Powered)</li><li>Practice Quiz: Exploring Chroma DB</li></ul></li><li>Module Summary and Evaluation<ul><li>Reading: Summary and Highlights: Introduction to Vector Databases and Chroma DB</li><li>Reading: Cheat Sheet: Introduction to Vector Databases and Chroma DB</li><li>Graded Quiz: Introduction to Vector Databases and Chroma DB</li><li>[Optional] Discussion Prompt: Meet and Greet</li></ul></li></ul><div><br /></div><div>Module 2: Vector Databases for Recommendation Systems and RAG</div><ul><li>Module Summary and Learning Objectives</li><li>Chroma DB Database Operations<ul><li>Essential Database Operations in Chroma DB</li><li>Lab: Similarity Search on Employee Records using Python and Chroma DB</li><li>[Optional] Interactive Lesson Recap Podcast (AI-Powered)</li><li>Practice Quiz: Chroma DB Database Operations</li></ul></li><li>Develop a Recommendation System and Connect Learned Concepts<ul><li>How Vector Databases Power RAG</li><li>Lab: Practice Project: Food Recommendation System Using Chroma DB</li><li>[Optional] Interactive Lesson Recap Podcast (AI-Powered)</li><li>Practice Quiz: Develop a Recommendation System and Connect Learned Concepts</li></ul></li><li>Module Summary and Evaluation<ul><li>Summary and Highlights: Vector Databases for Recommendation Systems and RAG</li><li>Reading: Vector Databases for Recommendation Systems and RAG</li><li>Graded Assignment: Graded Quiz: Vector Databases for Recommendation Systems and RAG</li></ul></li></ul><div><br /></div><div>Course Wrap Up</div><ul><li>Course Wrap-Up</li><li>Congratulations and Next Steps</li><li>Team and Acknowledgments</li></ul>
</div>


RAG: Vector Databases with ChromaDB

Learn vector databases, similarity search, and ChromaDB operations to build recommendation systems, and improve AI retrieval performance in GenAI applications using embeddings.

<div class="trix-content">
  <div>Retrieval-Augmented Generation (RAG) is rapidly becoming a core skill for Data Scientists, AI Engineers, and Software Developers, with competitive salaries reflecting its demand.<br /> <strong><br /></strong><br /></div><div>After completing this course, you will be able to:<br /><br /></div><ul><li>Explain the core principles and benefits of Retrieval-Augmented Generation. </li><li>Describe how retrieval pipelines work, including chunking, embedding, and vector search.</li><li>Implement basic RAG workflows using Python and LangChain.</li><li>Design interactive user interfaces for RAG systems using Gradio.</li><li>Compare LlamaIndex and LangChain to determine their appropriate use cases. </li><li>Construct end-to-end RAG applications using LlamaIndex that answers questions from source documents.</li></ul><div><br /></div><div><br />In this course, you’ll start by learning how RAG improves information retrieval, context accuracy, and user interactions. You’ll build your first retrieval pipeline and experiment with document splitting, embedding, and retrieval workflows using Python.<br /><br /></div><div>You’ll design user-facing GenAI applications with Gradio, creating clean, interactive interfaces that connect your retrieval pipeline to real-time user queries. Through guided labs, you’ll transform project ideas into a working QA system capable of answering questions from loaded documents.<br /><br /></div><div>You’ll explore LlamaIndex as an alternative RAG framework, examining its structure, strengths, and differences compared with LangChain. By completing hands-on labs, you’ll build a full RAG application using both frameworks, gaining a practical understanding of when each tool is most effective.<br /><br /></div><div>By the end of this course, you’ll have the experience needed to design, implement, evaluate, and deploy end-to-end RAG applications that power context-aware AI solutions.<br /><br />The following skills are required to be successful with this course: <br /><br /></div><ul><li>Python programming,</li><li>Familiarity with LangChain, and its use in developing simple generative AI applications</li></ul><div><br /><br /></div><h1>Course Syllabus</h1><div><br /></div><div>Welcome to the Course</div><ul><li>Course Introduction</li><li>Course Overview</li><li>RAG and Agentic AI Professional Certificate Overview</li><li>Reading: Helpful Tips for Course Completion</li></ul><div><br /></div><div>Module 1: Introduction to RAG<br /><br /></div><ul><li>Module Summary and Learning Objectives</li><li>What Is RAG?<ul><li>Why RAG?</li><li>More RAG Details</li><li>Reading: What Is RAG?</li><li>Summarize Private Documents Using RAG, LangChain, and LLMs</li><li>Practice Quiz: What Is RAG?</li></ul></li><li>Summary and Evaluation<ul><li>Summary and Highlights: Introduction to RAG</li><li>Cheat Sheet: Introduction to RAG</li><li>Graded Quiz: Introduction to RAG</li><li>[Optional] Discussion Prompt: Meet and Greet</li></ul></li></ul><div><br /></div><div>Module 2: Build Apps with RAG</div><div><br /></div><ul><li>Module Summary and Learning Objectives</li><li>Create an Interactive RAG Application with a User-Friendly Gradio Interface</li><li>Getting Started with Gradio<ul><li>Reading: Introduction to Gradio</li><li>Lab: Set Up a Simple Gradio Interface to Interact with your Model</li><li>Lab: Construct a QA Bot that Leverages the LangChain and LLM to Answer Questions from Loaded Documents</li><li>Practice Quiz: Building Apps with RAG</li></ul></li><li>Summary and Evaluation<ul><li>Summary and Highlights: Building Apps with RAG</li><li>Cheat Sheet: Building Apps with RAG</li><li>Graded Quiz: Building Apps with RAG</li></ul></li></ul><div><br /></div><div>Module 3: Build RAG Apps with LlamaIndex<br /><br /></div><ul><li>Module Summary and Learning Objectives</li><li>Application Development with LlamaIndex<ul><li>Intro to LlamaIndex: Document Ingestion and Chunking</li><li>Intro to LlamaIndex: From Vector Stores to Query Engines</li><li>Reading: LangChain and LlamaIndex Compared</li><li>Lab: Build an AI Icebreaker Bot with IBM Granite 3.0 &amp; LlamaIndex</li><li>Practice Quiz: Application Development with LlamaIndex</li></ul></li><li>Summary and Evaluation<ul><li>Summary and Highlights: Build RAG Apps with LlamaIndex</li><li>Cheat Sheet: Build RAG Apps with LlamaIndex</li><li>Graded Quiz: Build RAG Apps with LlamaIndex</li></ul></li></ul><div><br /></div><div>Course Wrap Up</div><ul><li>Course Wrap-Up</li><li>Congratulations and Next Steps</li><li>Team and Acknowledgments</li></ul>
</div>


RAG: Build Apps with LangChain and LlamaIndex

Learn RAG development through hands-on training in retrieval pipelines, Gradio interfaces, and LlamaIndex workflows to build accurate, context-aware AI applications

<div class="trix-content">
  <div>Get ready to elevate your technical portfolio with real, job-ready GenAI development skills. In this course, you’ll break down the fundamentals of prompt engineering, explore in-context learning strategies, and design reusable prompt templates that increase consistency and accuracy across AI outputs. <br /><br /></div><div>After completing this course, you will be able to:</div><ul><li>Explain core GenAI concepts, including prompt engineering fundamentals and in-context learning.</li><li>Differentiate between prompt templates, chains, and agents within the LangChain framework.</li><li>Apply prompt engineering strategies to design structured, reusable prompts for consistent model behavior.</li><li>Develop a functional generative AI application using Python, Flask, and LangChain components.</li><li>Analyze model performance across multiple LLMs to determine their strengths and suitability for specific tasks.</li><li>Construct a complete GenAI workflow that integrates user input, backend reasoning, and structured outputs using JSON parsing. </li></ul><div><br />You’ll learn practical techniques for refining prompts, troubleshooting unpredictable model behavior, and experimenting with different LLM configurations to strengthen the quality of your responses.<br /><br /></div><div>From there, you’ll dive into LangChain’s modular ecosystem, mastering chains, tools, and agents to build context-aware applications that can reason, plan, and respond more effectively. Hands-on labs guide you through building a fully functional generative AI application in Python that accepts user input, applies your backend logic, and delivers structured results. You’ll also explore Flask and Gradio to create interactive web interfaces that showcase your GenAI system in action.</div><div> </div><div>By the end of the course, you’ll have proven experience designing, optimizing, and deploying end-to-end GenAI applications using industry-recognized tools and workflows—skills that employers now expect from modern AI developers. Enroll and start building with confidence.</div><div><br /></div><h1>Course Prerequisites</h1><div><br /></div><div>The following skills are required to be successful with this course: </div><ul><li>Working knowledge of Python</li><li>Basic understanding of AI and web development</li></ul><div><br /></div><h1>Course Syllabus</h1><div><br /></div><div>Welcome to the Course</div><ul><li>Course Introduction</li><li>RAG and Agentic AI Professional Certificate Overview</li><li>Course Overview</li><li>Reading: Helpful Tips for Course Completion</li></ul><div><br /></div><div>Module 1: Foundations of Generative AI and Prompt Engineering</div><ul><li>Module Summary and Learning Objectives</li><li>[Optional] Generative AI Essentials<ul><li>About this Optional Lesson</li><li>Introduction to Generative AI</li><li>What Are Generative AI Models?</li><li>What Is NLP (Natural Language Processing)?</li><li>Reading: Comprehensive Guide to Generative AI</li><li>Practice Quiz: Generative AI Essentials</li></ul></li><li>Working with Prompt Engineering and Prompt Templates<ul><li>Introduction to In-Context Learning</li><li>Introduction to LangChain</li><li>Advanced Methods of Prompt Engineering</li><li>LangChain LCEL Chaining Method</li><li>(Optional) Reading: What Is Prompt Engineering, and Why Do…</li><li>Lab: Master Prompt Engineering and LangChain</li><li>Practice Quiz: Working with Prompt Engineering and Prompt Templates</li></ul></li><li>Module Summary and Evaluation<ul><li>Summary and Highlights: Foundations of Generative AI and Prompt Engineering</li><li>Cheat Sheet: Foundations of Generative AI and LangChain</li><li>Graded Quiz: Foundations of Generative AI and Prompt Engineering</li><li>[Optional] Discussion Prompt: Meet and Greet</li></ul></li></ul><div><br /></div><div>Module 2: Introduction to LangChain in GenAI Applications</div><ul><li>Module Summary and Learning Objectives</li><li>LangChain Core Components and Advanced Features<ul><li>Reading: Recap: Introduction to LangChain</li><li>LangChain: Core Concepts</li><li>LangChain Chains and Agents for Building Applications</li><li>(Optional) LangChain LCEL Chaining Method</li><li>Lab: Build Smarter AI Apps: Empower LLMs with LangChain</li><li>Practice Quiz: LangChain Core Components and Advanced Features</li></ul></li><li>Module Summary and Evaluation<ul><li>Summary and Highlights: Introduction to LangChain in GenAI Applications</li><li>Cheat Sheet: Introduction to LangChain in GenAI Applications</li><li>Graded Quiz: Introduction to LangChain in GenAI Applications</li></ul></li></ul><div><br /></div><div>Module 3: Build a Generative AI Application with LangChain</div><ul><li>Module Summary and Learning Objectives</li><li>Application Development Workflow with Generative AI<ul><li>Choose the Right AI Model for Your Use Case</li><li>From Idea to AI: Building Applications with Generative AI</li><li>Introduction to Flask</li><li>(Optional) Reading: Flask: A Gateway to Web Development in…</li><li>(Optional) Reading: Python with Flask for Large Scale Projects</li><li>Cheat Sheet: Web Development Using Flask</li><li>Hands-on with GenAI: Choosing the Right Model for Your…</li><li>Practice Quiz: Application Development Workflow with Generative AI</li></ul></li><li>Module Summary and Evaluation<ul><li>Summary and Highlights: Build a Generative AI Application with LangChain</li><li>Cheat Sheet: Build GenAI Application with LangChain</li><li>Graded Quiz: Build a Generative AI Application with LangChain</li></ul></li></ul><div><br /></div><div>Course Wrap Up</div><ul><li>Course Wrap-up</li><li>Congratulations and Next Steps</li><li>Team and Acknowledgments</li></ul>
</div>


Generative AI Application Development Fundamentals

Learn GenAI development with hands-on training in prompt engineering, LangChain workflows, and model optimization to build reliable AI applications for real-world use.

<div class="trix-content">
  <div>Master cutting-edge retrieval techniques that power today’s most advanced AI systems. In this course, you’ll explore sophisticated retriever patterns, vector databases, and indexing algorithms used in Retrieval-Augmented Generation (RAG). You’ll build a strong understanding of FAISS, ChromaDB, HNSW indexing, and the mechanics behind scalable similarity search in modern AI applications.</div><div> </div><div>After completing this course, you will be able to: <br /><br /></div><ul><li>Build RAG applications using vector databases and advanced retrieval patterns</li><li>Employ the core mechanics of vector databases such as FAISS and ChromaDB and implement indexing algorithms like HNSW</li><li>Implement advanced retrievers using LlamaIndex and LangChain to improve the quality of LLM responses</li><li>Develop comprehensive RAG applications by integrating LangChain, FAISS, and interactive user interfaces built with Gradio</li><li>Differentiate retrieval strategies and assess when to apply each for improved accuracy</li><li>Use advanced similarity search techniques to optimize retrieval within RAG systems</li></ul><div><br />Through guided labs, you’ll implement advanced retrievers—including self-querying, multi-query, parent document retrievers, and vector-store-backed pipelines—using both LangChain and LlamaIndex. These exercises demonstrate how to significantly improve retrieval accuracy, reduce hallucinations, and deliver high-quality responses from large language models (LLMs).<br /><br /></div><div>You’ll bring everything together by building a complete RAG application that integrates FAISS for vector search, an advanced retriever for improved relevance, and a fully interactive Gradio interface. This end-to-end project strengthens your ability to design AI systems that understand context, surface precise information, and serve users in real time.<br /><br /></div><div>By the end of the course, you’ll have applied the latest retrieval strategies and database technologies to build production-ready RAG pipelines—skills that directly support careers in AI engineering, search systems, and applied machine learning.<br /><br />The following skills are required to be successful with this course: <br /><br /></div><ul><li>Python programming </li><li>Familiarity with vector databases</li><li>Working knowledge of RAG and Similarity Search </li></ul><div><br /><br /></div><h1>Course Syllabus</h1><div><br /><br /></div><div><strong>Welcome to the Course</strong><br /><br /></div><ul><li>Course Introduction</li><li>Course Overview</li><li>RAG and Agentic AI Professional Certificate Overview</li><li>Reading: Helpful Tips for Course Completion</li></ul><div><br /></div><div><strong>Module 1: Advanced Retrievers for RAG</strong><br /><br /></div><ul><li>Module Summary and Learning Objectives</li><li>Work with Advanced Retrievers in LangChain<ul><li>Explore Advanced Retrievers in LangChain: Part 1</li><li>Explore Advanced Retrievers in LangChain: Part 2</li><li>Lab: Build a Smarter Search with LangChain Context Retrieval</li><li>[Optional] Interactive LangChain Lesson Recap Podcast (AI-Powered)</li><li>Practice Quiz: Work with Advanced Retrievers in LangChain</li></ul></li><li>Work with Advanced Retrievers in LlamaIndex<ul><li>Advanced Retrievers in LlamaIndex</li><li>Lab: Explore Advanced Retrievers in LlamaIndex</li><li>[Optional] Interactive LlamaIndex Lesson Recap Podcast (AI-Powered)</li><li>Practice Quiz: Work with Advanced Retrievers in LlamaIndex</li></ul></li><li>Module Summary and Evaluation<ul><li>Summary and Highlights: Advanced Retrievers for RAG</li><li>Reading: Cheat Sheet: Advanced Retrievers for RAG</li><li>Graded Quiz: Advanced Retrievers for RAG</li><li>[Optional] Meet and Greet</li></ul></li></ul><div><br /></div><div><strong>Module 2: Build a Comprehensive RAG Application<br /></strong><br /></div><ul><li>Module Summary and Learning Objectives</li><li>Introduction to FAISS for RAG<ul><li>Introduction to FAISS and How It Compares to ChromaDB</li><li>Lab: Semantic Similarity with FAISS</li><li>Reading: Hierarchical Navigable Small World (HNSW)</li><li>Lab: AI-Powered YouTube Summarizer, QA Tool with RAG, LangChain, FAISS</li><li>[Optional] Interactive FAISS/HNSW Lesson Recap Podcast (AI-Powered)</li><li>Practice Quiz: Introduction to FAISS for RAG</li></ul></li><li>Module Summary and Evaluation<ul><li>Summary and Highlights: Build a Comprehensive RAG Application</li><li>Cheat Sheet: Build a Comprehensive RAG Application</li><li>Graded Quiz: Build a Comprehensive RAG Application</li></ul></li></ul><div><br /></div><div><strong>Course Wrap-Up<br /></strong><br /></div><ul><li>Course Wrap-Up</li><li>Congratulations and Next Steps</li><li>Team and Acknowledgments</li></ul>
</div>


RAG: Vector Databases and Retrievers

Master advanced RAG techniques using FAISS, ChromaDB, and modern retrievers while building high-performance search applications with LangChain and LlamaIndex, and Gradio.

<div class="trix-content">
  <div>Unlock the power of multimodal AI and learn how modern systems combine text, images, speech, and video to create intelligent applications. This course teaches the foundational concepts behind multimodal GenAI applications, the challenges of integrating diverse data types, and the techniques used to build advanced, interactive systems. You’ll develop core skills in transcription, text-to-speech, image generation, video synthesis, and multimodal reasoning.<br /><br />After completing this course, you will be able to:<br /><br /></div><ul><li>Build the job-ready skills you need to build multimodal generative AI applications in just a few hours</li><li>Understand the fundamental concepts and challenges in multimodal AI, including the integration of text, speech, images, and video</li><li>Build multimodal AI applications using state-of-the-art models and frameworks such as IBM Granite, Meta’s Llama, OpenAI Whisper, DALL·E, and Sora</li><li>Develop multimodal AI solutions, including chatbots and image/video generation models, using IBM watsonx.ai, Hugging Face, Flask, and Gradio</li><li>Apply multimodal search, retrieval, and question answering techniques to solve practical problems</li><li>Design and deploy full-stack multimodal systems that combine audio, vision, and language models</li></ul><div><br />Through hands-on labs, you’ll work with Generative AI models like IBM Granite, OpenAI Whisper, DALL·E, Sora, Meta’s Llama, Mixtral, and vision-language architectures to apply multimodal AI in practical scenarios. You’ll build tools such as captioning systems, video-from-text generators, and AI-powered assistants that can process and respond across multiple data streams.<br /><br /></div><div>The course includes full-stack projects using Python, Flask, and Gradio, where you’ll design and deploy complete multimodal AI applications. By the end, you’ll have the technical skills needed to create next-generation AI systems used in search engines, chatbots, creative tools, and enterprise applications.<br /><br />The following skills are required to be successful with this course: </div><div> </div><ul><li>Prior knowledge of Python programming, Flask, Gradio, and LangChain </li></ul><div><br /><br /></div><div><br /></div><h1>Course Syllabus</h1><div>Module 1: Foundations of Multimodal AI</div><ul><li>Module Summary and Learning Objectives</li><li>Welcome to the Course<ul><li>Video: Course Introduction</li><li>Reading: Course Overview</li><li>Plugin/Reading: Helpful Tips for Course Completion</li><li>RAG and Agentic AI Professional Certificate Overview</li></ul></li><li>Introduction to Multimodal AI: Text and Speech Processing<ul><li>Video: Introduction to Multimodal AI</li><li>Reading: What Is Multimodal Generative AI and Why Does It Matter?</li><li>Reading: What Is Computer Vision?</li><li>Video: Text-to-Speech Technologies</li><li>Video: Speech-to-Text Technologies</li><li>Reading: Text Processing, Speech Processing, and TTS</li><li>Lab: Use Mixtral and gTTS to Create Your Personal Storyteller</li><li>Reading: Challenges in Multimodal AI Integration</li><li>Lab: Build a Meeting Assistant with Whisper, LangChain, &amp; Gradio</li><li>Practice Quiz: Introduction to Multimodal AI: Text and Speech Processing</li></ul></li><li>Module Summary and Evaluation<ul><li>Reading: Summary and Highlights</li><li>Cheat Sheet: Foundations of Multimodal AI</li><li>Graded Quiz: Foundations of Multimodal AI</li></ul></li></ul><div><br /></div><div>Module 2: Integrating Visual and Video Modalities</div><ul><li>Module Summary and Learning Objectives</li><li>Image Generation and Captioning<ul><li>Video: Understanding Image Captioning with LLaMA 3.2</li><li>Reading: Introduction to Text-to-Video and Image-to-Video Technologies</li><li>Demo Video: Text-to-Video/Image-to-Video Models</li><li>Lab: DALL·E Image Generation Guide for Beginners</li><li>Reading: Strengths, Limitations, and Practical Applications of Multimodal Vision Models in Real World Scenarios</li><li>Lab: Build an Image Captioning System with watsonx and Meta’s Llama</li><li>Practice Quiz: Image Generation and Captioning</li></ul></li><li>Module Summary and Evaluation<ul><li>Reading: Summary and Highlights</li><li>Cheat Sheet: Integrating Visual and Video Modalities</li><li>Graded Quiz: Integrating Visual and Video Modalities</li></ul></li></ul><div><br /></div><div>Module 3: Advanced Multimodal Applications</div><ul><li>Module Summary and Learning Objectives</li><li>Build Advanced Multimodal Applications<ul><li>Introduction to Multimodal Retrieval-Augmented Generation</li><li>Lab: Build a Style Finder Using Multimodal Retrieval and Search</li><li>Video: Multimodal Chatbots and QA Systems</li><li>Lab: Build Your First GenAI-Powered Image-Based Web Application</li><li>Practice Quiz: Build Advanced Multimodal Applications</li></ul></li><li>Module Summary and Evaluation<ul><li>Summary and Highlights</li><li>Cheat Sheet: Advanced Multimodal Applications</li><li>Graded Quiz: Advanced Multimodal Applications</li></ul></li></ul><div><br /></div><div>Course Wrap-Up</div><ul><li>Course Wrap-Up</li><li>Reading: Congratulations and Next Steps</li><li>Thanks from the Course Team</li></ul>
</div>


Developing Multimodal Generative AI Applications

Learn multimodal AI by building applications that combine text, speech, images, and video using Whisper, DALL·E, Sora, Llama, Granite, Mixtral, Flask, and Gradio through hands-on labs and real projects.

<div class="trix-content">
  <div>Learn how to build AI agents that think, reason, and take meaningful action using LangChain’s tool calling and agent frameworks. This course introduces the foundations of AI agent design, comparing different agent architectures and showing when to use structured workflows, manual tool calling, or built-in agents. You’ll learn how to connect LLMs with external tools—calculators, APIs, data sources, and more—to extend model capabilities far beyond text generation.<br /><br />After completing this course you will be able to:<br /><br /></div><ul><li>Develop AI agents that can reason and perform tasks independently</li><li>Implement tool calling and chaining to create structured AI workflows</li><li>Utilize built-in LangChain agents to analyze data, generate visualizations, and execute database queries</li><li>Apply best practices in prompt engineering and tool calling to enhance AI agent performance</li><li>Design multi-step agent workflows using LangChain Expression Language</li><li>Build end-to-end agent applications that integrate external tools and real data sources</li></ul><div><br /><br />Hands-on labs guide you through building agents with LangChain Expression Language (LCEL), validating model outputs, orchestrating tool calls, and chaining multiple operations together. You’ll also explore pre-built DataFrame and SQL agents to perform data analysis, create visualizations, and execute natural language database queries.<br /><br /></div><div>By the end, you’ll be able to design robust, reliable agents that perform precise tasks while maintaining natural conversational flow. Whether you’re developing chatbots, assistants, or automation systems, you’ll gain the skills to engineer AI that can reason, act, and deliver results in real-world workflows.</div><div><br /></div><div>The following skills are required to be successful with this course: <br /><br /></div><ul><li>Python programming skills </li><li>Basic understanding of LangChain</li><li>Familiarity with core AI concepts </li></ul><div> </div><h1>Course Syllabus</h1><div>Welcome to the Course<br /><br /></div><ul><li>Course Introduction</li><li>Course Overview</li><li>RAG and Agentic AI Professional Certificate Overview</li><li>Helpful Tips for Course Completion</li></ul><div><br /></div><div>Module 1: Foundations of Tool Calling and Chaining<br /><br /></div><ul><li>Module Summary and Learning Objectives</li><li>Introduction to AI Agents<ul><li>What are AI Agents?</li><li>Reading: Comparing AI System Designs</li><li>Reading: When to (and not to) use AI Agents</li><li>Practice Quiz: Introduction to AI Agents</li></ul></li><li>Getting Started with Tool Calling<ul><li>Tool Calling for LLMs</li><li>Why AI Needs Tools: From Guessing to Real-World Action</li><li>Reading: Tools, Agents, and Function Calling in LangChain</li><li>Practice Quiz: Getting Started with Tool Calling</li></ul></li><li>Building and Orchestrating Tools<ul><li>Build Effective AI Tools for Advanced LLMs</li><li>Build Intelligent Agents for Dynamic LLM Tool Use</li><li>Build a Custom Math Toolkit Agent with LangChain</li><li>Lab: Build an AI Math Assistant with LangChain Tool Calling</li><li>Reading: Popular Built-in Tools in LangChain</li><li>Practice Quiz: Building and Orchestrating Tools</li></ul></li><li>Module Summary and Evaluation<ul><li>Summary and Highlights: Foundations of Tool Calling and Chaining</li><li>Cheat Sheet: Foundations of Function Calling and Chaining</li><li>Graded Quiz: Foundations of Tool Calling and Chaining</li></ul></li></ul><div><br /></div><div>Module 2: LCEL and Manual Tool Calling in LangChain<br /><br /></div><ul><li>Module Summary and Learning Objectives</li><li>Introduction to Chaining and LCEL Basics<ul><li>LangChain LCEL Chaining Method</li><li>Lab: AI-Powered Data Analysis with LCEL</li><li>Cheat Sheet: LangChain Expression Language (LCEL)</li><li>Practice Quiz: Introduction to Chaining &amp; LCEL Basics</li></ul></li><li>Manual Tool Calling Basics<ul><li>When to Call Tools Manually</li><li>Reading: Structured Outputs for Tool Calling</li><li>Practice Quiz: Manual Tool Calling Basics</li><li>Parsing and Validating Tool Calls</li><li>Build LLM Agents with Tools</li><li>Build Interactive LLM Agents</li><li>Lab: Build Interactive LLM Agents with Tools</li><li>Lab: Build a Tool Calling Agent</li><li>Practice Quiz: Parsing and Validating Tool Calls</li></ul></li><li>Module Summary and Evaluation<ul><li>Summary and Highlights: Introduction to Chaining and LCEL Basics</li><li>Cheat Sheet: Manual Tool Calling in LangChain</li><li>Graded Quiz: Manual Tool Calling in LangChain</li></ul></li></ul><div><br /></div><div>Module 3: Using Built-in Agents in LangChain<br /><br /></div><ul><li>Module Summary and Learning Objectives</li><li>Natural Language Data Visualization<ul><li>From Natural Language to Data Visualizations with LangChain</li><li>Reading: Bridging Language and Data: How AI Transforms…</li><li>Lab: Build Your Own Data Visualization Agent</li><li>Practice Quiz: Natural Language Data Visualization</li></ul></li><li>Conversational Database Access<ul><li>An Introduction to AI-Powered SQL Agents</li><li>Implementing LangChain’s AI-Powered SQL Agent</li><li>Reading: Natural Language Interfaces for Data Systems</li><li>Lab: Build a Natural Language SQL Agent</li><li>Practice Quiz: Conversational Database Access</li></ul></li><li>Module Summary and Evaluation<ul><li>Summary and Highlights: Using Built-in Agents in LangChain</li><li>Cheat Sheet: Using Built-in Agents in LangChain</li><li>Graded Quiz: Using Built-in Agents in LangChain</li></ul></li></ul><div><br /></div><div>Course Wrap-Up<br /><br /></div><ul><li>Course Wrap-Up</li><li>Congratulations and Next Steps</li><li>Team and Acknowledgement</li></ul><div><br /><br /></div>
</div>


Agentic AI: Developing AI Agents

Build intelligent AI agents using LangChain by learning tool calling, chaining, LCEL workflows, and built-in agents to create actionable, reasoning-driven applications for real-world automation.

<div class="trix-content">
  <div>Unlock the full power of agentic AI by learning to design intelligent, stateful agents that can reason, improve, and collaborate. This course teaches you how to use LangChain and LangGraph to build workflows that incorporate memory, iteration, conditional logic, and real agent decision-making. You’ll explore how nodes, edges, and shared states enable flexible graph-based control structures for advanced AI systems.<br /><br />After completing this course, you will be able to: <br /><br /></div><ul><li>Build agentic AI systems using LangChain and LangGraph to support memory, iteration, and conditional logic</li><li>Design and implement self-improving agents using Reflection, Reflexion, and ReAct architectures</li><li>Apply agent orchestration techniques to build collaborative multi-agent systems</li><li>Implement agentic RAG systems that route queries and support retrieval-enhanced reasoning</li><li>Construct workflows that incorporate dynamic state, routing, and evaluation steps</li><li>Create adaptive agents capable of refining reasoning based on feedback</li></ul><div><br />Hands-on labs guide you through implementing Reflection, Reflexion, and ReAct architectures to build self-improving agents. You’ll learn how agents evaluate their own outputs, integrate feedback, adjust reasoning steps, and refine performance over time using structured prompt engineering and reflection loops.<br /><br /></div><div>You’ll design multi-agent systems where specialized agents coordinate tasks, share information, and solve complex problems. Using agentic RAG techniques, you’ll build workflows that route queries to the right agent, retrieve relevant context, and return well-reasoned answers.<br /><br /></div><div>By the end of the course, you’ll have practical experience building adaptive, collaborative agentic systems and the skills to design scalable AI architectures for real-world applications.<br /><br />The following skills are required to be successful with this course: </div><div> </div><ul><li>Python programming skills</li><li>Basic understanding of LangChain</li><li>Familiarity with core AI concepts </li></ul><div><br /><br /></div><h1>Course Syllabus</h1><div><strong><br />Welcome<br /></strong><br /></div><ul><li>Course Introduction</li><li>Course Overview</li><li>RAG and Agentic AI Professional Certificate Overview</li><li>Reading: Helpful Tips for Course Completion</li></ul><div><br /><br /></div><div><strong>Module 1: Introduction to LangGraph</strong></div><div><br /></div><ul><li>Module Summary and Learning Objectives</li><li>Introduction to Agentic AI</li><li>Generative versus Agentic AI</li><li>Reading: Agentic AI</li><li>Practice Quiz: Introduction to Agentic AI</li><li>LangGraph versus LangChain</li><li>Core Components of LangGraph</li><li>Reading: LangGraph Architecture: Designing Effective Agentic Workflows</li><li>LangGraph versus LangChain: When to Use What</li><li>Reading: LangGraph versus LangChain: Pros, Cons, and Use Cases</li><li>Practice Quiz: LangGraph versus LangChain</li><li>Build a LangGraph Workflow</li><li>Getting Started with LangGraph 101</li><li>Lab: LangGraph 101: Building Stateful AI Workflows</li><li>Practice Quiz: Build a LangGraph Workflow</li><li>Summary and Highlights</li><li>Cheat Sheet: Introduction to LangGraph</li><li>Graded Quiz: Introduction to LangGraph</li></ul><div><br /></div><div><strong>Module 2: Build Self-Improving Agents with LangGraph</strong></div><div><br /></div><ul><li>Module Summary and Learning Objectives</li><li>Build Reflection Agents</li><li>Overview: Types of AI Agents</li><li>The Art of AI Self-Improvement: Building Reflection Agents</li><li>Lab: Building a Reflection Agent with LangGraph</li><li>Practice Quiz: Build Reflection Agents</li><li>Advanced Self-Improvement with Reflexion Agents</li><li>Reading: Structuring LLM Tool Calls with Pydantic and JSON</li><li>Understanding Reflexion Agents</li><li>Building Reflexion Agents</li><li>Lab: Building a Reflexion Agent with External Knowledge</li><li>Practice Quiz: Advanced Self-Improvement with Reflexion Agents</li><li>ReAct: Integrating Reasoning and Action</li><li>ReAct: Building Agents that Reason Before Acting</li><li>Lab: ReAct: Build Reasoning and Acting AI Agents</li><li>Practice Quiz: ReAct: Integrating Reasoning and Action</li><li>Summary and Highlights</li><li>Cheat Sheet: Build Self-Improving Agents with LangGraph</li><li>Graded Quiz: Build Self-Improving Agents with LangGraph</li></ul><div><br /></div><div><strong>Module 3: Multi-Agent Systems and Agentic RAG with LangGraph</strong></div><div><br /></div><ul><li>Module Summary and Learning Objectives</li><li>The Evolution from Single to Multi-Agent Systems</li><li>Introduction to Multi-Agent Systems</li><li>Reading: Multi-Agent LLM System Fundamentals</li><li>Risks of Agentic AI: What You Need to Know</li><li>Practice Quiz: The Evolution from Single to Multi-Agent Systems</li><li>Build Multi-Agent Applications</li><li>Agentic RAG: Enhance Retrieval with Multi-Agent Systems</li><li>Reading: Building Multi-Agent Systems with LangGraph</li><li>Lab: DocChat: Build a Multi-Agent RAG System</li><li>Practice Quiz: Build Multi-Agent Applications</li><li>Summary and Highlights</li><li>Cheat Sheet: Multi-Agent Systems and Agentic RAG with LangGraph</li><li>Graded Quiz: Multi-Agent Systems and Agentic RAG with LangGraph</li></ul>
</div>


Agentic AI: LangChain and LangGraph

Build intelligent agentic AI systems with LangChain and LangGraph using memory, iteration, reflection, and multi-agent orchestration to solve complex tasks through retrieval-enhanced reasoning.

<div class="trix-content">
  <div>Learn how to develop intelligent, autonomous multi-agent systems using today’s leading agentic AI frameworks. This course teaches you how to apply agentic design principles, workflow patterns, and orchestration strategies to build scalable AI systems that plan, reason, and collaborate. You’ll explore foundational concepts behind agentic architectures and learn how to choose the right framework based on use case, complexity, and required system behaviors.<br /><br />After completing this course, you will be able to:</div><div><br /></div><ul><li>Design optimized AI systems by selecting and combining appropriate agentic frameworks and architectural patterns</li><li>Implement AI workflow patterns using agentic design principles and LangGraph</li><li>Build structured multi-agent workflows using CrewAI, including agents, tasks, and custom tools</li><li>Develop AI applications with BeeAI and design conversation-driven interactions using AG2</li><li>Combine orchestration strategies with modular workflows to create scalable multi-agent systems</li><li>Evaluate the strengths and use cases of LangGraph, CrewAI, BeeAI, and AG2 to choose the best tool for a given application</li></ul><div><br />You’ll begin with LangGraph, implementing workflow patterns such as sequential execution, routing, conditional flows, and parallelization. Hands-on labs teach you how to use these patterns to structure dynamic agent interactions and maintain clean, maintainable system designs.<br /><br /></div><div>You’ll learn CrewAI, working with agents, tasks, and crews to build structured multi-agent applications. You’ll generate structured outputs with YAML and Pydantic, integrate custom tools, and orchestrate collaborative operations across multiple agents.<br /><br /></div><div>The course then introduces BeeAI and AG2, where you’ll build agents that manage workflows, coordinate reasoning steps, and engage in role-based conversations. You’ll design multi-agent dialogues, extend capabilities with plugins, and implement applied use cases such as healthcare assistants or enterprise automations.<br /><br /></div><div>By the end of the course, you’ll have hands-on experience building multi-agent workflows across multiple frameworks and selecting the right patterns to optimize real-world AI systems.<br /><br />The following skills are required to be successful with this course: </div><div> </div><ul><li>Working knowledge of Python programming, LangChain, and LangGraph, along with an understanding of how agentic AI systems work.</li></ul><div><br /><br /></div><h1>Course Syllabus</h1><div><br /><strong>Welcome<br /></strong><br /></div><ul><li>Course Introduction</li><li>Course Overview</li><li>RAG and Agentic AI Professional Certificate Overview</li><li>Helpful Tips for Course Completion</li></ul><div><br /><br /></div><div><strong>Module 1: Agentic Frameworks and LangGraph Design Patterns for Effective AI Systems<br /></strong><br /></div><ul><li>Module Summary and Learning Objectives</li><li>Introduction to Agentic Frameworks</li><li>Understanding Agentic AI and Open Source Frameworks</li><li>Building AI Agents with Open Source Frameworks</li><li>Practice Quiz: Introduction to Agentic Frameworks</li><li>Understand AI System Design Patterns</li><li>Essential Design Patterns for AI Systems</li><li>Orchestrator Design Pattern</li><li>Evaluator-Optimizer Design Pattern</li><li>Lab: Implement Workflow Patterns with LangGraph</li><li>Practice Quiz: Understand AI System Design Patterns</li><li>Cheat Sheet: Agentic Frameworks and Design Patterns for Effective AI Systems</li><li>Graded Quiz: Agentic Frameworks and Design Patterns for Effective AI Systems</li></ul><div><br /><br /></div><div><strong>Module 2: CrewAI Fundamentals and Advanced Applications<br /></strong><br /></div><ul><li>Module Summary and Learning Objectives</li><li>Introduction to CrewAI</li><li>Design AI Agent Workflows with CrewAI</li><li>Lab: CrewAI 101: Building Multi-Agent AI Systems</li><li>Practice Quiz: Introduction to CrewAI</li><li>Structured Outputs in CrewAI</li><li>CrewAI with Structured Outputs, YAML, and CrewBase</li><li>Lab: Create a Structured Meal &amp; Grocery Planner with CrewAI</li><li>Reading: Structured Outputs in CrewAI</li><li>Practice Quiz: Structured Outputs in CrewAI</li><li>Functions and CrewAI</li><li>Extending CrewAI with Custom Functions</li><li>Lab: Agents with Tools vs. Tasks with Tools in CrewAI</li><li>Practice Quiz: Functions and CrewAI</li><li>Lab: Building Your Own AI Nutrition Coach Using a Multi-Agent System</li><li>Summary and Highlights</li><li>Cheat Sheet: CrewAI Fundamentals and Advanced Applications</li><li>Graded Quiz: CrewAI Fundamentals and Advanced Applications</li></ul><div><br /><br /></div><div><strong>Module 3: Alternative Agentic Frameworks: BeeAI and AG2 (AutoGen)<br /></strong><br /></div><ul><li>Module Summary and Learning Objectives</li><li>BeeAI Core Concepts and Architecture</li><li>BeeAI: Introduction and Core Components</li><li>Building Agents with the BeeAI Framework</li><li>Lab: Building Agentic AI Systems with the BeeAI Framework</li><li>Practice Quiz: BeeAI Core Concepts and Architecture</li><li>AG2 (AutoGen) Core Concepts, Architecture, and Conversations</li><li>Introduction to AG2 (AutoGen) and Its Key Elements</li><li>Extending AG2 with Tools and Structured Outputs</li><li>Reading: Agent Orchestration and Design Patterns in AG2</li><li>Lab: AG2 101 (AutoGen): Complete Tutorial</li><li>Lab: Build Multi-Agent Chatbot with AG2 (AutoGen)</li></ul>
</div>


Agentic AI: LangGraph, CrewAI, AutoGen, and BeeAI

Build multi-agent AI systems using LangGraph, CrewAI, BeeAI, and AG2 by mastering agentic design patterns, orchestration workflows, and collaborative agent behaviors for scalable AI applications.

<div class="trix-content">
  <div>As speech recognition technology becomes more accessible, developers now have the tools to build applications that feel natural and effortless—speaking instead of typing, listening instead of reading. This guided project shows you how to use OpenAI's Whisper model to create a voice-powered journaling application that converts spoken thoughts into searchable, organized text entries. Instead of simple dictation, you'll build an intelligent system that handles audio processing, transcription, metadata management, and persistent storage—giving you hands-on experience with the entire pipeline of speech-to-text AI applications.</div><div><br /></div><h1>What You'll Learn</h1><div>By the end of this project, you will be able to:</div><ul><li> <strong>Build a complete voice-to-text application with Whisper:</strong> Learn how to load and configure OpenAI's Whisper model, process audio input, and generate accurate transcriptions from speech.</li><li><strong>Design structured data systems for managing transcriptions:</strong> Create a journal class that organizes entries with timestamps, metadata, and audio files, giving you a foundation for building any content management system.</li><li> <strong>Implement audio processing pipelines with librosa:</strong> Understand how to load, resample, and prepare audio data for machine learning models, including handling different file formats and sample rates.</li><li><strong>Add search and export functionality to text-based applications:</strong> Extend your journal with keyword search and file export features, making your data useful and accessible.</li></ul><div><br /></div><h1>Who Should Enroll</h1><ul><li> Early-career ML engineers who want practical experience applying speech recognition models to real-world use cases beyond simple demos or tutorials.</li><li>Python developers interested in building AI-powered applications but unsure how to integrate models like Whisper into complete, functional systems.</li><li>Product builders exploring voice interfaces and conversational AI who need to understand the technical foundations of speech-to-text pipelines.</li></ul><div><br /></div><h1>Why Enroll</h1><div>This project bridges the gap between running a model once and building something you'd actually use. You'll learn how to integrate Whisper into a complete application, handle real audio data, design persistent storage systems, and build user-facing features—skills that translate directly to building voice assistants, transcription services, or any speech-enabled application. By the end, you won't just understand speech recognition in theory—you'll have a working voice journal you built yourself, plus the knowledge to adapt it into meeting transcribers, voice note apps, or accessibility tools.</div><div><br /></div><h1>What You'll Need</h1><div>To get the most out of this project, you should have basic Python programming skills and some familiarity with NumPy or data structures. No prior experience with machine learning or audio processing is required—everything is explained step by step. All dependencies are pre-configured in the cloud environment, and the project runs entirely in your browser using Jupyter notebooks. The Whisper tiny model runs efficiently on CPU, so no GPU is needed.</div>
</div>


Build an AI-Powered Voice Journal with Whisper

Journaling is hard when you have to type everything. What if you could just talk? Using OpenAI's Whisper model, you'll build an AI-powered voice journal that automatically transcribes your spoken thoughts into organized text entries. This project walks you through speech recognition and audio processing, taking you from raw audio to a working journal app. By the end, you'll have built a complete transcription system and learned how to apply speech-to-text AI to real-world problems.

<div class="trix-content">
  <div>In this project, you will learn how modern AI agents can work with graph-structured data to retrieve, rank, and summarize information. You will build a lightweight Graph-RAG workflow where an agent explores a social-network graph, identifies influential nodes, and generates clear insights using an LLM. By following the step-by-step process, you will see how graph structure, ranking logic, and agent reasoning come together in a practical, end-to-end retrieval pipeline.<br /><br /></div><h1>Who Is It For</h1><div>This project is designed for learners with foundational Python skills, such as software engineers, data scientists, or AI practitioners, who want to deepen their understanding of how modern AI systems retrieve, rank, and summarize information using lightweight agent workflows. This project is designed for individuals who want to move beyond basic retrieval-augmented generation (RAG) methods and gain practical, hands-on experience with graph-based reasoning and structured AI retrieval pipelines.</div><div><br /></div><h1>What You’ll Learn</h1><div>By the end of this project, you will understand how AI agents navigate connected data, how Graph-RAG differs from traditional RAG, and how simple graph features can significantly improve the quality of retrieved information. You will be able to:</div><ul><li>Learn how to construct and analyze a social-network graph and extract meaningful subgraphs for retrieval.</li><li>Build an AI agent that retrieves graph data, applies ranking logic, and produces structured explanations with the help of an LLM.</li></ul><div><br /></div><h1>What You'll Need</h1><div>You should be comfortable writing basic Python code and working with common data structures. No prior experience with AI agents or Graph-RAG is required. The libraries used in this project can be installed directly within the IBM Skills Network Labs environment, allowing you to set up and run the workflow without any external configuration. The project works best on modern browsers such as Chrome, Edge, Firefox, or Safari.</div>
</div>


Agentic Graph-RAG Over Social-Network Knowledge Graphs

Learn how to build an AI agent that retrieves, ranks, and summarizes information from a social-network graph. This guided project introduces a lightweight Graph-RAG workflow and demonstrates how an agent can combine graph structure, ranking logic, and AI reasoning to generate clear, data-driven insights. By working through each step, you will gain practical experience with graph-based retrieval and understand how modern AI systems navigate and interpret connected data. You will also learn how each component works together in an end-to-end agentic pipeline, giving you stronger foundation.

<div class="trix-content">
  <div>In this project, you’ll learn how explainability techniques reveal the internal reasoning of graph-based models. You will examine how GNNExplainer highlights influential nodes, edges, and functional motifs, and how faithfulness metrics help validate whether explanations reflect true model behavior. These methods are then applied to the MUTAG molecular graph dataset, where you will investigate which atomic interactions and functional groups most strongly drive mutagenicity predictions, connecting explainability methods to real scientific use cases.<br /><br /></div><h1>Who Is It For</h1><div>This project is designed for learners who have basic familiarity with graph machine learning and want a practical, hands-on introduction to explaining Graph Neural Networks (GNNs). It is suitable for developers, data scientists, and machine learning enthusiasts who are interested in understanding how GNNs make decisions, especially in molecular prediction tasks. The project is particularly valuable for learners who want to move beyond treating GNNs as black boxes and gain insight into how graph-based models reason over nodes, edges, and substructures.</div><div><br /></div><h1>What You’ll Learn</h1><div>By the end, you’ll be able to interpret GNN decisions in a principled and scientifically informed way.</div><ul><li>Understand the core principles behind explaining Graph Neural Networks.</li><li>Use GNNExplainer to identify influential substructures and graph components.</li><li>Evaluate explanation quality using faithfulness-based tests.</li></ul><div><br /></div><h1>What You'll Need</h1><div>This project requires basic familiarity with Python, graph-structured data, and machine learning concepts. An understanding of molecules as graphs (atoms as nodes, bonds as edges) will be helpful. The libraries used in this project can be installed directly within the IBM Skills Network Labs environment, allowing you to set up and run the workflow without any external configuration. The project works best on modern browsers such as Chrome, Edge, Firefox, or Safari.</div>
</div>


Explainability in Graph Neural Networks: Molecular Insights

Explaining how Graph Neural Networks reason is essential for validating their structural understanding. This project examines GNNExplainer for revealing which graph components drive model behavior, analyzing influential nodes, edges, and functional motifs, and evaluating explanation faithfulness through principled sparsification and substructure tests. The explainability method is applied to molecular graphs in the MUTAG dataset to uncover which atomic interactions and functional groups most strongly drive mutagenicity predictions, linking model reasoning to meaningful chemical insights.

<div class="trix-content">
  <div>In this project, you’ll walk through each stage of building a modern graph-based recommender system, from preparing the interaction data to implementing message passing and training the LightGCN model. You’ll gain both conceptual understanding and hands-on experience with real datasets and a complete end-to-end recommendation pipeline..<br /><br /></div><h1>Who Is It For</h1><div>This project is designed for software developers, data scientists, or AI practitioners interested in Graph Neural Networks (GNNs) and their applications in recommender systems. It is ideal for learners who want to understand how Graph Convolutional Networks (GCNs) model relational data such as user–item interactions, explore how LightGCN streamlines traditional GCN architectures to better handle large-scale recommendation scenarios, and gain practical experience by implementing a real graph-based recommendation pipeline that connects theoretical concepts directly to hands-on practice.<br /><br /></div><h1>What You’ll Learn</h1><div>By the end of this project, you will be able to:</div><ul><li>Understand the theoretical foundations of Graph Convolutional Networks (GCNs) and how LightGCN simplifies them.</li><li>Build and train a LightGCN recommender system in PyTorch using the MovieLens dataset.</li><li>Evaluate the model using Recall@K and NDCG@K metrics, and generate Top-K recommendations.</li></ul><div><br /></div><h1>What You'll Need</h1><div>Learners should have proficiency in Python and prior experience with interactive coding environments. A working knowledge of machine learning fundamentals, including embeddings, loss functions, and evaluation metrics, is recommended. All required libraries can be installed directly within the IBM Skills Network Labs environment, allowing you to set up and run the workflow without external configuration. The project works best on modern browsers such as Chrome, Edge, Firefox, or Safari.</div>
</div>


Light Graph Convolutional Network for Recommender Systems

Learn how to build a recommender system using Graph Convolutional Networks (GCN) with the LightGCN model. In this guided project, you’ll construct a user–item interaction graph, implement LightGCN in PyTorch, and evaluate it using Recall@K and NDCG@K. By the end, you’ll understand the theoretical foundations of LightGCN and apply it effectively to real recommendation tasks. You will also explore how message passing captures multi-hop collaborative signals, gaining a complete practical workflow for modern graph-based recommendation while learning to analyze embedding behavior in depth.

<div class="trix-content">
  <h1>Why This Project Matters</h1><div>Hyperparameter tuning plays a critical role in determining how well machine learning models perform, yet it is often handled manually through trial and error. As models increase in complexity, this approach becomes inefficient, time-consuming, and difficult to scale. <strong>Optuna</strong> addresses this challenge by providing an automated, intelligent framework for hyperparameter optimization that adapts based on past results.<br /><br /></div><div>In this guided project, you’ll learn how to move beyond default model settings and manual tuning. By working with both <strong>scikit-learn</strong> and <strong>PyTorch</strong>, you’ll gain hands-on experience optimizing machine learning models and neural networks using the industry-relevant tool, Optuna. Completing this project will help you build practical optimization skills that are directly applicable to real-world machine learning workflows.</div><div><br /></div><h1>A Look at the Project Ahead</h1><div>After completing this project, you will be able to:</div><ul><li><strong>Apply Optuna to optimize machine learning models</strong> by defining search spaces.</li><li><strong>Run and evaluate</strong> optimization trials to identify optimal model configurations.</li><li><strong>Tune and evaluate models built with scikit-learn and PyTorch.</strong></li><li><strong>Use automated optimization and pruning</strong> to improve performance and efficiency.</li><li><strong>Analyze optimization results </strong>using Optuna's built-in visualization tools.</li></ul><div><br /></div><h1>What You'll Need</h1><div>To get started with this guided project, you should have:</div><ul><li>Proficiency with <strong>Python</strong></li><li>Familiarity with <strong>PyTorch and scikit-learn</strong> libraries</li><li>Introductory knowledge of <strong>machine learning concepts</strong> (model training and evaluation)</li><li>A modern web browser (Chrome, Edge, Firefox)</li></ul><div>No local installation or setup is required. The <strong>IBM Skills Network Labs environment</strong> is fully hosted online and comes with all necessary tools and libraries, allowing you to focus entirely on learning and experimentation without configuration hassles.</div>
</div>


Optimize Models with Optuna: Adaptive Hyperparameter Tuning

Learn adaptive hyperparameter tuning with Optuna using PyTorch and scikit-learn to optimize machine learning models for better performance. In this guided project, you’ll explore how automated hyperparameter optimization improves a wide range of machine learning workflows. You’ll work hands-on with the Optuna framework to define search spaces, evaluate trials, and apply pruning to cut training time and computational costs. This project breaks down complex concepts into clear tasks, allowing you to focus on learning in a fully online environment without setup or configuration hassles.

<div class="trix-content">
  <div>Have you ever wanted to bring a little extra magic to your holiday gatherings? While trivia games are a staple of festive parties, creating one that is both historically accurate and entertaining can be a challenge. In this project, you will build an <strong>AI-powered Christmas Trivia Host</strong> that brings global traditions to life. By orchestrating a team of specialized <strong>CrewAI agents</strong> and integrating <strong>IBM watsonx.ai foundation models</strong>, you will create an interactive game that doesn't just recycle common facts, but also uncovers obscure folklore, generates witty multiple-choice challenges, and even simulates a judgment from Santa Claus himself. This system demonstrates the power of <strong>agentic workflows</strong>, where distinct AI personalities collaborate to research, format, and present information in a dynamic, user-friendly web application.<br /><br /><br /><br /></div><h1>What You'll Learn</h1><div>By the end of this project, you will be able to:</div><ul><li><strong>Orchestrate Multi-Agent Systems with CrewAI:</strong> Define and manage specialized agents, a <strong>Folklore Historian</strong>, an <strong>Entertainment Elf</strong>, and a <strong>Santa Judge, </strong>to handle distinct parts of a complex workflow.</li><li><strong>Integrate Enterprise-Grade LLMs:</strong> Connect your application to <strong>IBM watsonx.ai</strong> to leverage the <strong>Granite</strong> model series for high-quality, context-aware text generation.</li><li><strong>Implement Secure Configuration Patterns:</strong> Master the use of os.environ to safely manage API keys and project credentials, a critical skill for deploying secure AI applications.</li><li><strong>Design Interactive Web UIs with Gradio:</strong> Build a polished frontend featuring custom <strong>HTML/CSS styling</strong> and <strong>JavaScript animations</strong> (like falling snow) to create an immersive user experience.</li><li><strong>Manage Application State Logic:</strong> Learn how to use state machines within a web app to handle multi-turn conversations, ensuring smooth transitions between question generation and answer evaluation.</li><li><strong>Deploy and Share:</strong> Package your Python code into a shareable web demo that can be accessed by friends, family, or potential employers.</li></ul><div><br /><br /></div><h1>Who Should Enroll</h1><ul><li><strong>Python Developers</strong> looking to expand their skills into Generative AI and agent orchestration.</li><li><strong>AI Enthusiasts</strong> curious about how frameworks like CrewAI can simplify the creation of complex, multi-step AI behaviors.</li><li><strong>Educators and Gamification Designers</strong> interested in using AI to create dynamic, educational content on the fly.</li><li><strong>Creative Coders</strong> who want to learn how to blend backend logic with frontend aesthetics for thematic applications.</li></ul><div><br /><br /></div><h1>Why Enroll</h1><div>This project bridges the gap between <strong>backend AI engineering</strong> and <strong>frontend user experience design</strong>. Instead of a simple text-in/text-out chatbot, you will build a system with personality and structure. You will move beyond basic prompting to designing a <strong>collaborative AI team</strong> that follows strict formatting rules and persona guidelines. By the end, you will have a working <strong>holiday trivia game</strong>, practical experience with <strong>state-of-the-art agent frameworks</strong>, and a template for building any kind of interactive, educational AI assistant.<br /><br /><br /></div><h1>What You'll Need</h1><div>To get the most out of this project, you should have:</div><ul><li>Basic <strong>Python programming knowledge</strong>.</li><li>Familiarity with the concept of <strong>APIs</strong> (helpful but not required).</li><li>Interest in <strong>Generative AI</strong>, <strong>Game Design</strong>, and <strong>Web Development</strong>.</li></ul><div>All dependencies are pre-configured in the environment, and the project runs best on current versions of Chrome, Edge, Firefox, or Safari.</div>
</div>


Build Multi-Agent Santa Quiz Game w/ Granite, CrewAI, Gradio

Build your own multi-agent Santa Quiz Game with IBM Granite, CrewAI, and Gradio. Learn to orchestrate specialized agents with CrewAI agents and tasks to collaboratively research global traditions and generate interactive challenges. Use IBM Granite models to power high-quality text generation and secure environment variables for reliable system configuration. Integrate custom JavaScript snow effects and festive CSS styling to deliver a polished, immersive web interface. Explore how CrewAI enables agent collaboration and state-based logic to create a fully automated holiday experience.

<div class="trix-content">
  <div>Poor management practices cost the global economy $8.8 trillion, or about 9% of world GDP! (Gallup) This course builds job-ready skills in business process modeling, analysis, and improvement that businesses desperately need; no prior experience required. </div><div> </div><div>Designed for professionals and aspiring managers, this course builds your practical knowledge of how Lean, Six Sigma, and systems thinking, can analyze and enhance how work gets done. </div><div> </div><div>Through activities such as podcasts and AI-enabled role-plays, you will model and map processes, identify inefficiencies, and apply proven methods to improve performance, communication, and collaboration across teams. Plus, through real-world scenarios and a final project, you’ll design and document a complete business process model and narrative.  </div><div> </div><div>By the end, you’ll be ready to contribute to process improvement initiatives and pursue certifications such as CompTIA Project+, ASQ CQIA, or AIGPE Process Mapping Specialist. </div><div> </div><div>Enroll today to strengthen your analytical skills and accelerate your career in business analysis and operations management. </div><h1>Course Syllabus</h1><div>This course comprises five modules, which are outlined below. You are encouraged to set aside 2–3 hours each week to complete all modules over the suggested five-week period. Maintaining a consistent study schedule will help you achieve your learning goals. <br /><br /><strong>Module 1: Process Modeling Fundamentals </strong></div><div><strong>Module 2: Business Process Mapping Techniques </strong></div><div><strong>Module 3: Business Process Improvement and AI <br />Module 4: Systems Thinking, Lean, and Six Sigma <br />Module 5: Final Project, Final Quiz and Course Wrap-Up </strong></div><div><br /></div><h1>Learning Objectives</h1><ul><li>Build job-ready skills in business process modeling, Lean, Six Sigma, and systems thinking to excel in business analysis and process management roles  </li><li>Develop and interpret process models and maps that represent current and desired states, enabling better communication and decision making  </li><li>Analyze processes to identify inefficiencies, bottlenecks, and improvement opportunities using mapping, narratives, and analytical frameworks  </li><li>Integrate systems thinking, Lean, and Six Sigma to design, implement, and sustain optimized processes with measurable impact </li></ul><h1>Recommended Skills Prior to Taking this Course</h1><div>This course is for people interested in business process modeling and  improvement, systems thinking, and applications of Lean, and Six Sigma</div>
</div>


Business Process Modeling, Analysis, and Improvement

In this course, you will learn how to think and work like a business analyst or project manager, regardless of your current role or title. You will build practical skills in business process modeling, mapping, and improvement to help teams operate more efficiently and effectively. You will explore Lean, Six Sigma, systems thinking, and AI-supported analysis to identify inefficiencies, optimize workflows, and design sustainable improvements. 

<div class="trix-content">
  <div>66% of Agile businesses use the Scrum framework (The Tech Report). Project-oriented professionals with strong Scrum Master skills are highly sought after! This course deepens your understanding of the essential aspects of being a Scrum Master and builds the skills employers are looking for. <br /><br /></div><div>What does a Scrum Master do? A Scrum Master facilitates and supports the Scrum team by ensuring adherence to Agile principles, removing obstacles, and fostering collaboration to help the team deliver value efficiently.  <br /><br /></div><div>During this course, you’ll be immersed in the world of Scrum. You’ll explore how Scrum compares with traditional project management methods, and you’ll gain a deeper appreciation of why Scrum is a game-changer in today’s dynamic business landscape.  <br /><br /></div><div>You’ll apply your Scrum Master skills to real-world scenarios through hands-on labs and projects, where you’ll navigate challenges, foster collaboration, and drive successful project outcomes. In addition, you’ll complete a final assessment that will develop your understanding of the criteria for certification as an Advanced Certified Scrum Master (A-CSM).  <br /><br /></div><div>If you’re looking to take your Scrum Master skills to a deeper level and stand out to employers, ENROLL TODAY and power up your resume with competencies that will catch their eye! <br /><br /></div><div> </div><div><strong>You will learn:</strong> </div><ul><li>Job-ready Scrum Master skills employers need in less than a month. </li><li>The Scrum Process flow and the various artifacts required at different phases of the process, as well as how to create Scrum personas.      </li><li>How to develop a working agreement to foster a collaborative environment among team members.   </li><li>How to run a retrospective for a given scenario and apply useful coaching techniques to resolve issues within a dysfunctional team.   </li><li>How to develop a product vision and goals while collaborating with the product owner to refine a backlog.   </li></ul><div> </div><div><br /><br /></div><h1>Course Syllabus</h1><div><strong>Welcome</strong> <br />• Video: Course Introduction <br />• Reading: General Information <br />• Reading: Learning Objectives and Syllabus <br />• Reading: Grading Scheme <br />• Reading: How to make the most of this course <br /> <br /><strong>Module 1: Scrum and Scrum Master Basics</strong> <br />• Reading: Module 1 Introduction and Learning Objectives <br />• Video: Scrum Process and Artifacts  <br />• Video: The Role of the Scrum Master <br />• Reading: Detailed Review of Scrum Artifacts <br />• Video: The Job Description of a Scrum Master <br />• Video: Expert Viewpoints: What Does a Scrum Master Do? <br />• Video: Comparing Scrum Values to Project Management Methodologies <br />• Reading: Key Players in the Scrum Process <br />• Video: Keys to Success: Skills, Attributes, and Personality Traits Essential to Scrum Master Success <br />• Video: Scrum Master Defined <br />• Reading: Key Leadership Traits Essential to Scrum Master Success <br />• Video: Introduction to Personas <br />• Lab: Defining the Scrum Process and Scrum Personas: Task 1 <br />• Lab: Defining the Scrum Process and Scrum Personas: Task 2 <br />• Reading: Module 1 Summary: Scrum and Scrum Master Basics <br />• Reading: Module 1 Glossary: Scrum and Scrum Master Basics <br />• Practice Quiz: Module 1: Scrum and Scrum Master Basics <br />• Graded Quiz: Module 1 Scrum and Scrum Master Basics <br />  <br /><strong>Module 2: Scrum Master as a Facilitator and Coach</strong> <br />• Reading: Module 2 Introduction and Learning Objectives <br />• Video: Managing Stakeholders <br />• Video: Engaging Stakeholders <br />• Reading: Analyzing Situational Facilitation Techniques to Maximize Collaboration and Various Coaching Techniques <br />• Video: Expert Viewpoints: Scrum Master as a Leader <br />• Video: Working Agreement  <br />• Lab: Develop a Working Agreement <br />• Reading: Acceptance Criteria and the Concept of “Done” <br />• Video: Managing the Daily Stand-up Meeting <br />• Video: Focusing the Team <br />• Video: Scrum Master as a Coach  <br />• Video: Expert Viewpoints: The Scrum Master as a Facilitator <br />• Video: The Sprint Retrospective <br />• Lab: Analyze a Scenario: Developing a Retrospective <br />• Reading: Module 2 Summary: Scrum Master as a Facilitator and a Coach <br />• Reading: Module 2 Glossary: Scrum Master as a Facilitator and a Coach <br />• Practice Quiz: Module 2: Scrum Master as a Facilitator and a Coach <br />• Graded Quiz: Module 2 Scrum Master as a Facilitator and a Coach <br />  <br /><strong>Module 3: Leadership: Scrum Master as a Servant Leader</strong> <br />• Reading: Module 3 Introduction and Learning Objectives <br />• Video: Servant Leadership <br />• Video: Define Qualities of a Self-Organized Team and Techniques to Achieve Team Maturity <br />• Video: Expert Viewpoints: Scrum Master as a Coach <br />• Video: Development Models to Improve Team Effectiveness and Continuous Improvement <br />• Lab: Getting a Dysfunctional Team Back on Track <br />• Video: Scrum Master and the Product Owner Collaboration <br />• Video: Expert Viewpoints: Servant Leadership <br />• Video: Develop a Product Vision and Determine Product Goals <br />• Lab: Review a Scenario. Create a Product Vision <br />• Video: Collaborating with the Product Owner to Refine the Backlog <br />• Video: Refining the Backlog <br />• Reading: Reading: Module 3 Summary: Leadership: Scrum Master as a Servant Leader <br />• Reading: Module 3 Glossary: Leadership: Scrum Master as a Servant Leader <br />• Practice Quiz: Module 3: Leadership: Scrum Master as a Servant Leader <br />• Graded Quiz: Module 3 Leadership: Scrum Master as a Servant Leader <br />  <br /><strong>Module 4: Navigating Complexity and Change</strong> <br />• Reading: Module 4 Introduction and Learning Objectives <br />• Video: Identifying Organizational Impediments <br />• Video: Dealing with Difficult Stakeholders <br />• Video: Expert Viewpoints: Product Owner Collaboration <br />• Video: Using the Force Field Analysis Tool <br />• Lab: Read a Scenario. Develop a Force Field Analysis <br />• Video: Conflict and the Team <br />• Video: Expert Viewpoints: Managing Complexity and Change <br />• Video: Recognizing Dependencies <br />• Reading: Evaluating and Responding to Team Interactions <br />• Video: Navigating Change <br />• Lab: Review a Scenario. Apply Change Models to Address the Change Factors <br />• Reading: Module 4 Summary: Navigating Complexity and Change <br />• Reading: Module 4 Glossary: Navigating Complexity and Change <br />• Practice Quiz: Module 4: Navigating Complexity and Change <br />• Graded Quiz: Module 4: Navigating Complexity and Change  <br />  <br /><strong>Module 5: Course Summary and Final Assessment</strong> <br />• Reading: Module 5 Introduction and Learning Objectives <br />• Reading: Review of Previous Modules and the Scrum Process <br />• Reading: The Path to Certification: PMI-ACP, DASM, and A-CSM Certification Exam <br />• Video: The Path to Certification <br />• Reading: Glossary of Terms <br />• Graded Quiz: Final Graded Exam <br />• Retake Exam <br />• Final Project: The Big Picture: Putting it All Together <br />• Reading: Final Project Scenario <br />• Lab: Health of the Project <br />• Lab: Recommendations <br />• Lab: Retrospective <br />• Final Project: Submission and Peer Review </div><div><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>To get the most out of this course, you should possess some basic project management skills and experience.  </div><div> </div>
</div>


Scrum Master: The Path to Success

Get job-ready Scrum Master skills and valuable hands-on experience employers value in less than a month.  

<div class="trix-content">
  <div>This Machine Learning Capstone is designed to showcase and solidify your expertise in Python-based machine learning. In this hands-on course, you’ll bring together everything you’ve learned in previous courses in the program and apply it to real-world problems using libraries such as Pandas, Scikit-learn, and TensorFlow/Keras. <br /><br /></div><div>Your main project will focus on building a course recommender system. You’ll work with course-related datasets, calculate cosine similarity, create similarity matrices, and experiment with multiple algorithms. By applying K-Nearest Neighbors (KNN), Principal Component Analysis (PCA), and non-negative matrix collaborative filtering, you will compare and contrast the performance of different machine learning approaches to recommendation systems. <br /><br /></div><div>Beyond recommendation systems, you'll also train a neural network to predict course ratings and build regression and classification models to enhance your predictive analytics skills. This project gives you the opportunity to demonstrate not just technical proficiency, but also critical thinking in evaluating and selecting the most effective models. </div><div><br />By the end of the course, you’ll have a portfolio-worthy project, practical experience with advanced machine learning techniques, and the confidence to apply your skills to real-world challenges. <br /><br /></div><h1>Learning Objectives</h1><div>• Apply advanced machine learning techniques using Python libraries such as Pandas, Scikit-learn, and TensorFlow/Keras </div><div>• Design and implement a real-world course recommender system using cosine similarity, KNN, PCA, and collaborative filtering methods </div><div>• Demonstrate proficiency in predictive analytics by building and evaluating regression, classification, and neural network models </div><div>• Showcase critical thinking and professional skills by comparing algorithms, selecting effective models, and delivering a portfolio-ready project <br /><br /></div><h1>Course Syllabus</h1><div>Welcome  </div><ul><li>Video: Introduction to Machine Learning Capstone </li><li>Ungraded Plugin: Capstone Overview </li></ul><div>Module 1: Machine Learning Capstone Overview </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction to Recommender Systems </li><li>Reading: Text Analysis </li><li>Reading: Stopwords and WordCloud </li><li>App Item: Exploratory Data Analysis on Online Course Enrollment Data </li><li>App Item: Extract Bag of Words (BoW) Features from Course Textual Content </li><li>Reading: Sparse and Dense Bag of Words (BOW) Vectors </li><li>Reading: Similarity Measures in Recommender Systems </li><li>App Item: Calculate Course Similarity using BoW Features </li><li>Practice Assignment: Checkpoints: Exploratory Data Analysis on Online Course Enrollment Data </li><li>Graded Assignment: Exploratory Data Analysis and Feature Engineering </li></ul><div>Module 2:  Unsupervised-Learning Based Recommender System </div><ul><li>Reading: Learning Objectives </li><li>Video: Content-based Recommender Systems </li><li>Reading: Evaluation Metrics of Recommender Systems </li><li>App Item: Content-based Course Recommender System using User Profile and Course Genres </li><li>Reading: Heatmaps </li><li>App Item: Content-based Course Recommender System using Course Similarities </li><li>App Item: Clustering-based Course Recommender System </li><li>Practice Assignment: Checkpoints:  Unsupervised-Learning Based Recommender System </li><li>Graded Assignment: Unsupervised-Learning Based Recommendation Systems </li></ul><div>Module 3: Supervised-Learning Based Recommender Systems </div><ul><li>Reading: Learning Objectives </li><li>Video: Collaborative Filtering-Based Recommender Systems </li><li>Reading: Exploring Surprise Library and KNN Model </li><li>App Item: Collaborative Filtering-based Recommender System using K Nearest Neighbor </li><li>App Item: Collaborative Filtering-based Recommender System using Non-negative Matrix Factorization </li><li>App Item: Course Rating Prediction using Neural Networks </li><li>App Item: Regression-based Rating Score Prediction Using Embedding Features <br />App Item: Classification-based Rating Mode Prediction using Embedding Features </li><li>Practice Assignment: Checkpoints: Supervised-Learning Based Recommender Systems </li><li>Graded Assignment: Supervised-Learning Based Recommendation Methods </li></ul><div>Module 4: Share and Present Your Recommender Systems </div><ul><li>Reading: Learning Objectives </li><li>Video: Elements Of A Successful Data Findings Report </li><li>Reading: Structure Of A Report </li><li>Video: Best Practices For Presenting Your Findings </li><li>(Optional) Hands-on Lab: Getting Started With PowerPoint For The Web </li><li>(Optional) Hands-on Lab: Basics of PowerPoint </li><li>(Optional) Hands-on Lab: Save your PowerPoint Presentation as PDF </li></ul><div>Module 5: Final Submission </div><ul><li>Reading: Learning Objectives </li><li>Final Submission Overview and Instructions </li><li>Exercise: Preparing Your Presentation (with provided slide template) </li><li>Peer Review: Submit Your Work and Review Your Peers </li><li>Reading: An Overview of the Streamlit Module </li><li>Ungraded Plugin: Introduction to Streamlit </li><li>Ungraded Plugin: Build a Course Recommender App with Streamlit </li><li>Reading: Congratulations and Next Steps </li><li>Reading: Thanks from the Course Team </li></ul><h1>General Information</h1><div>This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer or Safari. <br /><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>Before taking this course, please ensure you have completed all of the other 5 courses in the edx Machine Learning Professional Certificate. </div><div>To make the most out of this course, you should have familiarity with programming on a Python development environment, as well as fundamental understanding of Calculus, Linear Algebra, Probability, and Statistics.</div>
</div>


Machine Learning: Capstone Project

Demonstrate your machine learning expertise in this IBM Capstone course. Apply Pandas, Scikit-learn, TensorFlow/Keras, and build a real-world course recommender system. Showcase your ML skills through this comprehensive hands-on project.

<div class="trix-content">
  <div>Discover how generative AI can help you create engaging, personalized learning content and improve your productivity so you can enhance student outcomes. <br /><br /></div><div>During this course, you’ll explore gen AI methodologies and best practices for implementing AI in education. You’ll look at how it can be used to create content, enhance personalized learning, special education, and adaptive learning. You’ll get hands-on with popular gen AI tools, including IBM watsonx, ChatGPT, Claude, and Khanmigo in education. Plus, you’ll investigate the ethical implementation of gen AI, considering privacy protection, bias mitigation, and the creation of inclusive learning environments.   <br /><br /></div><div>Throughout, you’ll hear from industry experts, who share insights on the future of gen AI in education. You’ll build your gen AI expertise in hands-on labs and interactive activities. Plus, you’ll complete a final project where you’ll apply all that you’ve learned to a practical, real-world scenario.  <br /><br /></div><div>Whether you’re an educator looking to revolutionize your classroom practices or simply want to streamline ad<br />ministrative tasks, this course will give you the gen AI skills you need to excel. Enroll today!<br /><br /><strong>Prerequisites</strong> </div><div> </div><div>This course is designed for educators who already have an educational or teaching background and want to enhance their teaching capabilities using gen AI. You should have a fundamental understanding of gen AI and instructional design. The following courses in the <strong>Generative AI for Educators</strong> specialization can help you become familiar with gen AI basics and prompt engineering techniques: </div><div> </div><ul><li><a href="https://www.coursera.org/learn/generative-ai-introduction-and-applications?specialization=generative-ai-for-everyone">Course 1: Generative AI: Introduction and Applications</a> </li><li><a href="https://www.coursera.org/learn/generative-ai-prompt-engineering-for-everyone?specialization=generative-ai-for-everyone">Course 2: Generative AI: Prompt Engineering Basics</a> </li></ul><div> </div><div><strong>Objectives</strong> </div><div>After completing this course, you will be able to: </div><div> </div><ul><li>Identify appropriate gen AI tools for education, considering pedagogy, integration ease, and cost, to address specific teaching needs </li><li>Align the content with learners’ abilities, preferences, and engagement goals to create personalized learning content </li><li>Leverage gen AI tools to design lesson plans and assessments to encourage dynamic and interactive learning </li><li>Apply ethical AI practices by safeguarding data privacy, mitigating bias, and promoting an inclusive learning environment </li></ul><div> </div><div> </div><div><strong>Course Outline</strong> </div><div> </div><div>This course is divided into three modules. You can complete each module at your own pace, but it’s recommended to set a goal of completing at least one module per week.   </div><div> </div><div><strong>Module 1: Gen AI Tools and Personalized Learning </strong> <br /> </div><div>In this module, you will explore the landscape of educational gen AI tools and select them based on pedagogical needs, integration capabilities, and cost considerations. You will also learn to evaluate the effectiveness of AI tools for different teaching requirements and identify principles for AI-enhanced personalized learning and advanced content customization techniques. Finally, you will be able to leverage AI-powered tools for content creation and implement strategies for differentiating instruction using AI-powered resources.  </div><div> </div><div> </div><div> </div><div><strong>Module 2: AI Integration and Performance Assessment</strong> <br /> </div><div>This module introduces you to how to integrate AI tools seamlessly into teaching practices and leverage them for learners’ evaluation. You will gain insight into designing AI-enhanced lesson planning aligning them with learning objectives. Additionally, you will learn to create assessment strategies using gen AI tools to gauge learners’ mastery of concepts and analyze AI-generated performance data. Finally, you will be able to leverage AI-powered feedback mechanisms to provide timely, data-driven insights that support learners’ growth and continuous improvement.  </div><div> </div><div> <br /><strong>Module 3: Ethical Implementation and Applied Project</strong> </div><div> </div><div>This module helps address ethical considerations while implementing gen AI in education, recognize bias, and develop its mitigation strategies. You will also learn to design data privacy protection strategies for AI integration. </div><div> </div><div>This module includes storyline interactivity based on the ethical guidelines while implementing gen AI in education.  </div><div> </div><div>The module includes a final project based on the concepts covered in the course. In this module, you will attempt a graded quiz to test and reinforce your understanding of concepts. The module also includes a glossary to enhance comprehension of generative AI-related terms.   <br /> <br /> </div><div> </div><div><strong>Tools/Software</strong> </div><div>In this course, you will explore no-cost versions of various gen AI tools and platforms, including: </div><div> </div><ul><li>Microsoft’s Copilot </li><li>OpenAI’s ChatGPT – A versatile AI language model for creating lesson plans, answering learners’ queries, and personalized tutoring  </li><li>Anthropic Claude – An advanced conversational AI model for generating insightful educational content and assisting in curriculum design </li><li>Khanmigo Tools for Teachers – A suite of AI-powered tools designed to assist teachers in lesson planning, curriculum alignment, and classroom management </li><li>TeachFlow – A tool for streamlining teaching workflows, providing AI-driven assistance for lesson planning and classroom management </li><li>Synthesia – A tool for creating engaging animated videos  </li></ul><div> </div><div>These tools are accessible via modern web browsers such as Chrome, Firefox, and Edge. Learners are not required to install these tools on their devices. </div><div> </div><div><strong>Tips for Success</strong> </div><ul><li>Stay organized and keep track of teaching strategies and learning requirements </li><li>Consistently practice using the gen AI tools and technologies covered in the course </li><li>Experiment with the examples provided to enhance your understanding and application of AI in education </li></ul><div> </div><div>Congratulations on taking this step to elevate your teaching career with gen AI! Enjoy your learning journey. </div>
</div>


Generative AI: Skills & Tools for Educators

This course is for education professionals, including teachers, professors, instructional designers, education administrators, EdTech professionals, corporate trainers, education policymakers, online course creators, and consultants who want to advance their careers by leveraging the power of generative AI. 

<div class="trix-content">
  <div>This course explores two of the most dynamic and in-demand areas of machine learning: Deep Learning and Reinforcement Learning. You’ll begin by diving into Deep Learning, a subset of machine learning that powers many modern AI systems—from image and speech recognition to natural language processing.  </div><div><br />The course introduces the foundational theory behind neural networks, explaining how they are structured, how they learn, and why they are effective for handling complex, high-dimensional data. You’ll gain hands-on experience building and training neural networks and explore modern deep learning architectures that are widely used in industry. <br /><br /></div><div>You’ll then move on to Reinforcement Learning (RL), a rapidly growing field in AI that focuses on decision-making and learning through interaction with an environment. Reinforcement Learning has practical applications in research, across robotics, autonomous systems, game-playing AI, and beyond. You’ll learn the key concepts of RL, including agents, environments, actions, rewards, and policies, and how these elements work together in the learning process. </div><div><br />By the end of this course, you will have developed a strong understanding of how Deep Learning and Reinforcement Learning differ from traditional supervised and unsupervised learning approaches. You’ll also be able to design, build, and interpret basic deep learning models, as well as grasp the foundational principles that drive reinforcement learning strategies. <br /><br /></div><h1>Learning Objectives</h1><div>• Demonstrate understanding of deep learning by explaining how neural networks are structured, trained, and applied to complex data </div><div>• Apply technical skills to design, build, and train basic deep learning models using modern architectures </div><div>• Show working knowledge of reinforcement learning by identifying agents, environments, actions, rewards, and policies in AI systems </div><div>• Differentiate between supervised, unsupervised, deep, and reinforcement learning approaches to highlight their unique applications <br /><br /></div><h1>Course Syllabus</h1><div>Course Introduction </div><ul><li>Video: Course Introduction </li></ul><div>Module 1: Introduction to Neural Networks </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction to Neural Networks </li><li>Video: Basics of Neurons </li><li>Video: Neural Networks with Sigmoid Function </li><li>Video: Neuron in Action </li><li>Video: Neural Networks with SKlearn </li><li>App Item: Neural Networks with Sklearn </li><li>Video: Forward Propagation </li><li>Video: Matrix Representation of Forward Propagation </li><li>Video: Main Types of Deep Neural Network </li><li>App Item: Introduction to Neural Networks Demo (Activity) </li><li>Video: (Optional) Introduction to Neural Networks Notebook - Part 1 </li><li>Video: (Optional) Introduction to Neural Networks Notebook - Part 2 </li><li>Practice Assignment: Introduction to Neural Networks </li><li>Video: Gradient Descent Basics </li><li>Video: Compare Different Gradient Descent Methods </li><li>App Item: Gradient Descent Demo (Activity) </li><li>Video: (Optional) Gradient Descent Notebook - Part 1 </li><li>Video: (Optional) Gradient Descent Notebook - Part 2 </li><li>Video: (Optional) Gradient Descent Notebook - Part 3 </li><li>Practice Assignment: Optimization and Gradient Descent </li><li>Reading: Summary/Review </li><li>Module 1 Graded Quiz </li></ul><div>Module 2: Back Propagation Training and Keras </div><ul><li>Reading: Learning Objectives </li><li>Video: How to Train a Neural Network </li><li>Video: Backpropagation </li><li>App Item: Backpropagation Demo (Activity) </li><li>Video: (Optional) Backpropagation Notebook - Part 1 </li><li>Video: (Optional) Backpropagation Notebook - Part 2 </li><li>Video: The Sigmoid Activation Function </li><li>Video: Other Popular Activation Functions </li><li>Video: (Optional) Backpropagation Notebook - Part 3 </li><li>Practice Assignment: Practice: Back Propagation, Activation Functions </li><li>Video: Popular Deep Learning Library </li><li>Video: A Typical Keras Workflow </li><li>Video: Implementing an Example Neural Network in Keras </li><li>App Item: Keras Demo (Activity) </li><li>Video: (Optional) Keras Notebook - Part 1 </li><li>Video: (Optional) Keras Notebook - Part 2 </li><li>Video: (Optional) Keras Notebook - Part 3  </li><li>App Item: Regression with Keras </li><li>App Item: (Optional) Loading Images with Keras </li><li>Practice Assignment: Keras Library </li><li>Reading: Summary/Review </li><li>Module 2 Graded Quiz </li></ul><div>Module 3: Neural Network Optimizers </div><ul><li>Reading: Learning Objectives </li><li>Video: Optimizers and Momentum </li><li>Video: Regularization Techniques for Deep Learning </li><li>Video: Popular Optimizers </li><li>Video: Details of Training Neural Networks </li><li>Reading: Learning Rate Scheduler Reading </li><li>Video: Data Shuffling  </li><li>App Item: Optimizers </li><li>App Item: Grid Search with Keras </li><li>Video: Transforms </li><li>Practice Assignment: Optimizers and Data Shuffling </li><li>Reading: Summary/Review </li><li>Module 3 Graded Quiz </li></ul><div>Module 4: Convolutional Neural Networks </div><ul><li>Reading: Learning Objectives </li><li>Video: Categorical Cross Entropy </li><li>App Item: Categorical Cross Entropy </li><li>Video: Introduction to Convolutional Neural Networks (CNN) </li><li>Video: Images Dataset </li><li>Video: Kernels </li><li>Video: Convolution for Color Images </li><li>App Item: Images Convolution </li><li>Video: Convolutional Settings - Padding and Stride </li><li>App Item: Padding, Pooling, and Stride </li><li>Video: Convolutional Settings - Depth and Pooling </li><li>App Item: Channels and Flattening </li><li>App Item: Training the Network </li><li>App Item: Convolutional Neural Networks Demo (Activity) </li><li>Video: (Optional) Demo CNN Notebook - Part 1 </li><li>Video: (Optional) Demo CNN Notebook - Part 2 </li><li>Practice Assignment: Convolutional Neural Networks </li><li>Reading: Summary/Review </li><li>Module 4 Graded Quiz  </li></ul><div>Module 5: Transfer Learning </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction to Transfer Learning </li><li>Video: Transfer Learning and Fine Tuning </li><li>App Item: Transfer Learning Demo (Activity) </li><li>Video: (Optional) Transfer Learning Notebook </li><li>Practice Assignment: Transfer Learning </li><li>Video: Convolutional Neural Network Architectures – LeNet </li><li>Video: Convolutional Neural Network Architectures – AlexNet </li><li>Video: VGG </li><li>Video: Convolutional Neural Network Architectures – Inception </li><li>Video: Convolutional Neural Network Architectures – ResNet </li><li>App Item: Types of Model APIs in Keras </li><li>App Item: Transfer Learning Examples with Existing Architectures </li><li>Practice Assignment: Convolutional Neural Network Architectures </li><li>Reading: Regularization </li><li>App Item: Regularization Techniques </li><li>Practice Assignment: Regularization </li><li>Reading: Summary/Review </li><li>Module 5 Graded Quiz </li></ul><div>Module 6: Recurrent Neural Networks and Long-Short Term Memory Networks </div><ul><li>Reading: Learning Objectives </li><li>Video: Recurrent Neural Networks (RNNs) </li><li>Video: State and  Recurrent Neural Networks </li><li>App Item: (Optional) Introduction to Sequential Data </li><li>App Item: Existing Recurrent Neural Networks </li><li>Video: Details Recurrent Neural Networks </li><li>App Item: Word Embeddings </li><li>App Item: Recurrent Neural Networks Demo (Activity) </li><li>Video: (Optional) Recurrent Neural Networks Notebook - Part 1 </li><li>Video: (Optional) Recurrent Neural Networks Notebook - Part 2 </li><li>Practice Assignment: Recurrent Neural Networks </li><li>Video: Long-Short Term Memory (LSTM) Networks </li><li>Video: LSTM Explanation </li><li>Video: Gated Recurrent Unit </li><li>Video: Gated Recurrent Unit Details </li><li>App Item: LSTM and GRU Demo (Activity) </li><li>Practice Assignment: LSTM and GRU </li><li>Reading: Summary/Review </li><li>Module 6: Graded Quiz </li></ul><div>Module 7: Autoencoders </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction to Autoencoders </li><li>Video: Autoencoders </li><li>Ungraded Plugin: Transposed Convolution Reading </li><li>App Item: Autoencoders </li><li>Practice Assignment: Autoencoders </li><li>Autoencoders Demo (Activity) </li><li>Video: (Optional) Autoencoders Notebook - Part 1 </li><li>Video: (Optional) Autoencoders Notebook - Part 2 </li><li>Video: (Optional) Autoencoders Notebook - Part 3 </li><li>Video: (Optional) Autoencoders Notebook - Part 4 </li><li>Video: (Optional) Autoencoders Notebook - Part 5 </li><li>Reading: Summary/Review </li><li>Module 7 Graded Quiz  </li></ul><div>Module 8: Generative Models and Applications of Deep Learning </div><ul><li>Reading: Learning Objectives </li><li>Video: What is a Variational Autoencoder </li><li>Video: How Variational Autoencoders Work </li><li>App Item: Variational Autoencoder </li><li>Practice Assignment: Variational Autoencoders </li><li>Video: Introduction to GANs </li><li>Video: How GANS Work </li><li>Video: Issues with Training GANS </li><li>App Item: GANS Lab 1 </li><li>App Item: GANS Lab 2 </li><li>Video: Additional Topics in Deep Learning </li><li>App Item: GPU with Keras </li><li>Video: Model Agnostic Explainable AI </li><li>Practice Assignment: Generative Adversarial Networks </li><li>Reading: Summary/Review </li><li>Module 8 Graded Quiz </li></ul><div>Module 9: Reinforcement Learning </div><ul><li>Reading: Learning Objectives </li><li>Video: Reinforcement Learning (RL) </li><li>App Item: Reinforcement Learning Demo (Activity) </li><li>Video: (Optional) Reinforcement Learning Notebook - Part 1 </li><li>Video: (Optional) Reinforcement Learning Notebook - Part 2 </li><li>Video: (Optional) Reinforcement Learning Notebook - Part 3 </li><li>Video: (Optional) Reinforcement Learning Notebook - Part 4 </li><li>Practice Assignment: Reinforcement Learning </li><li>Reading: Summary/Review </li><li>Module 9 Graded Quiz </li><li>Peer Review: Final Project </li><li>Reading: Thanks from the Course Team </li></ul><div><br /></div><h1>General Information</h1><div>This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer or Safari. <br /><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>To make the most out of this course, you should have familiarity with programming on a Python development environment, as well as fundamental understanding of Calculus, Linear Algebra, Probability, and Statistics. </div>
</div>


Machine Learning: Deep & Reinforcement Learning

Get started in Reinforcement and Deep Learning! Explore the theory and practice behind neural networks, build deep learning models, and study modern architectures used in today’s AI applications.

<div class="trix-content">
  <div>Gain a detailed introduction to unsupervised learning, one of the core branches of machine learning focused on uncovering patterns and insights in data without labeled outcomes. Learn how to work with datasets that lack a target variable by applying powerful techniques such as clustering and dimensionality reduction. These methods are essential for identifying structure within the data, discovering hidden groupings, and simplifying complex datasets while retaining meaningful information. <br /><br /></div><div>Throughout the course, you’ll explore commonly used algorithms like k-means, hierarchical clustering, DBSCAN, and principal component analysis (PCA), as well as learn how to choose the most appropriate method based on the nature of your data. You’ll gain an understanding of the curse of dimensionality and how it affects the performance of clustering algorithms when working with high-dimensional data.</div><div><br />The hands-on component emphasizes real-world problem solving using best practices in unsupervised learning. You’ll gain practical experience implementing clustering and dimensionality reduction techniques, interpreting the results, and applying appropriate metrics to evaluate the quality of your clusters. </div><div><br />By the end of the course, you’ll be equipped to identify when unsupervised learning is appropriate, apply different algorithms effectively, and extract meaningful insights from unlabeled datasets. </div><div><br /></div><h1>Learning Objectives</h1><div>• Define the core concepts of unsupervised learning and identify when to apply clustering and dimensionality reduction to unlabeled datasets. </div><div>• Implement algorithms such as k-means, hierarchical clustering, DBSCAN, and PCA using tools like NumPy to uncover hidden patterns and simplify complex data. </div><div>• Analyze clustering results, interpret dimensionality reduction outputs, and evaluate model performance while addressing challenges such as the curse of dimensionality. </div><div>• Select and justify the most appropriate unsupervised learning technique for real-world problems to extract meaningful insights from data. <br /><br /></div><h1>Course Syllabus</h1><div>Course Introduction </div><ul><li>Video: Course Introduction </li></ul><div>Module 1: Introduction to Unsupervised Learning and K Means </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction to Unsupervised Learning: Overview </li><li>Video: Introduction to Unsupervised Learning: Use Cases of Clustering </li><li>Video: Introduction to Clustering </li><li>Ungraded Practice Assignment: Introduction to Unsupervised Learning </li><li>Video: K-Means </li><li>Video: K-Means Initialization </li><li>Video: Selecting the Right Number of Clusters in K-Means </li><li>Video: Elbow method and Applying K-means </li><li>K Means Demo (Activity) </li><li>Video: (Optional) K Means Notebook - Part 1 </li><li>Video: (Optional) K Means Notebook - Part 2 </li><li>Video: (Optional) K Means Notebook - Part 3 </li><li>Practice Lab: K Means Clustering Lab </li><li>Reading: Mixture of Gaussians </li><li>Practice Lab: Mixture of Gaussians Lab </li><li>Ungraded Practice Assignment: K Means Clustering </li><li>Reading: Summary </li><li>Graded: Module 1 Quiz </li></ul><div>Module 2: Distance Metrics &amp; Computational Hurdles </div><ul><li>Reading: Learning Objectives </li><li>Video: Distance Metrics: Euclidean and Manhattan Distance </li><li>Video: Distance Metrics: Cosine and Jaccard Distance </li><li>Demo lab: Curse of Dimensionality </li><li>Video: (Optional) Curse of Dimensionality Notebook - Part 1 </li><li>Video: (Optional) Curse of Dimensionality Notebook - Part 2 </li><li>Video: (Optional) Curse of Dimensionality Notebook - Part 3 </li><li>Video: (Optional) Curse of Dimensionality Notebook - Part 4 </li><li>Practice Lab: Distance Metrics Lab </li><li>Ungraded Practice Assignment: Distance Metrics </li><li>Reading: Summary </li><li>Graded: Module 2 Quiz </li></ul><div>Module 3: Selecting a Clustering Algorithm </div><ul><li>Reading: Learning Objectives </li><li>Video: Hierarchical Agglomerative Clustering </li><li>Video: Hierarchical Agglomerative Clustering: Hierarchical Linkage Types </li><li>Video: Applying Hierarchical Agglomerative Clustering </li><li>Video: DBSCAN </li><li>Video: Visualizing DBSCAN </li><li>Practice lab: DBSCAN Clustering </li><li>Video: Mean Shift </li><li>Practice lab: Mean Shift Clustering </li><li>Ungraded Practice Assignment: Clustering Algorithms </li><li>Video: Comparing Algorithms </li><li>Clustering Demo (Activity) </li><li>Video: Clustering Notebook - Part 1 </li><li>Video: Clustering Notebook - Part 2 </li><li>Video: (Optional) Clustering Notebook - Part 3 </li><li>Video: (Optional) Clustering Notebook - Part 4 </li><li>Ungraded Practice Assignment: Comparing Clustering Algorithms </li><li>Reading: Summary </li><li>Graded: Module 3 Quiz </li></ul><div>Module 4: Dimensionality Reduction </div><ul><li>Reading: Learning Objectives </li><li>Video: Dimensionality Reduction:  Overview </li><li>Video: Dimensionality Reduction: Principal Component Analysis </li><li>App Item: (Optional) Matrix Review </li><li>Demo lab: Dimensionality Reduction (Part 1) </li><li>Video: (Optional) Dimensionality Reduction Notebook - Part 1 </li><li>Video: (Optional) Dimensionality Reduction Notebook - Part 2 </li><li>Practice lab: Principal Component Analysis </li><li>App Item: Singular Value Decomposition </li><li>Video: Dimensionality Reduction Imaging Example </li><li>Ungraded Practice Assignment: Dimensionality Reduction  </li><li>Reading: Summary </li><li>Graded: Module 4 Quiz </li></ul><div>Module 5: Nonlinear and Distance-Based Dimensionality Reduction </div><ul><li>Reading: Learning Objectives </li><li>Video: Kernel  Principal Component Analysis and Multidimensional Scaling </li><li>Demo lab: Dimensionality Reduction (Part 2) </li><li>Video: (Optional) Dimensionality Reduction Notebook - Part 3 </li><li>Practice lab: Kernel PCA </li><li>Practice lab: Multidimensional Scaling </li><li>Ungraded Practice Assignment: Kernel PCA and MDS </li><li>Reading: Summary </li><li>Graded: Module 5 Quiz  </li></ul><div>Module 6: Matrix Factorization </div><ul><li>Reading: Learning Objectives </li><li>Video: Non Negative Matrix Factorization </li><li>Demo lab: Non-Negative Matrix Factorization </li><li>App Item: (Optional) TF-IDF Supplemental. </li><li>Video: (Optional) Non Negative Matrix Factorization Notebook - Part 1 </li><li>Video: (Optional) Non Negative Matrix Factorization Notebook - Part 2 </li><li>Practice lab: Non-Negative Matrix Factorization </li><li>Ungraded Practice Assignment: Non Negative Matrix Factorization </li><li>Reading: Summary </li><li>Graded: Module 6 Quiz </li></ul><div>Module 7: Final Project </div><ul><li>Peer Review: Course Final Project </li><li>Reading: Thanks from the Course Team </li></ul><h1>General Information</h1><div>This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer or Safari. <br /><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>To make the most out of this course, you should have familiarity with programming on a Python development environment, as well as fundamental understanding of Calculus, Linear Algebra, Probability, and Statistics. </div>
</div>


Machine Learning: Unsupervised Models

This course introduces key unsupervised machine learning techniques and explains how to choose the best algorithm for your data. Learn clustering and dimensionality reduction to find insights in unlabeled data sets. 

<div class="trix-content">
  <div>This course provides an introduction to classification, a fundamental technique in supervised machine learning used to predict categorical outcomes. Learn how to build, train, and evaluate predictive models using methods such as logistic regression, decision trees, and powerful ensemble techniques like random forests and gradient boosting.  </div><div> </div><div>You’ll gain hands-on experience with essential machine learning practices, including properly splitting data into training and testing sets to avoid overfitting and using techniques like oversampling and undersampling to handle unbalanced datasets. This ensures your models are both accurate and robust when applied to real-world data. </div><div> </div><div>A key focus of the course is on model evaluation using a range of error metrics, helping you compare performance and choose the best model for your data. By the end of the course, you will understand when to use classification versus other supervised learning methods, how to implement and interpret different classification algorithms, and how to use best practices to ensure your models are effective and generalizable. </div><div> </div><div>This course is ideal for aspiring machine learning engineers and data scientists looking to apply classification techniques in practical business scenarios. Whether you’re aiming to predict customer churn, detect fraud, or categorize products, this course will equip you with the skills needed to solve real-world classification problems. </div><div><br /></div><div>To succeed in the course, you should be comfortable with Python programming and have a foundational understanding of data cleaning, exploratory data analysis, calculus, linear algebra, probability, and statistics. </div><div><br /></div><h1>Learning Objectives</h1><div>• Build and evaluate classification models using logistic regression, decision trees, random forests, and gradient boosting. </div><div>• Apply best practices in model training and testing to improve generalization and prevent overfitting. </div><div>• Handle unbalanced datasets with techniques such as oversampling and undersampling. </div><div>• Compare classification models using performance metrics to select the most effective solution for real-world problems. <br /><br /></div><h1>Course Syllabus</h1><div>Course Introduction </div><ul><li>Reading: About this course </li><li>Video: Welcome </li><li>Reading: Optional: Download data assets </li></ul><div>Module 1: Logistic Regression </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction: What is Classification? </li><li>Video: Introduction to Logistic Regression </li><li>Video: Classification with Logistic Regression </li><li>Video: Logistic Regression with Multi-Classes </li><li>Video: Implementing Logistic Regression Models </li><li>Video: Confusion Matrix, Accuracy, Specificity, Precision, and Recall </li><li>Video: Classification Error Metrics: ROC and Precision-Recall Curves </li><li>Video: Implementing the Calculation of ROC and Precision-Recall Curves </li><li>Practice Assignment: Logistic Regression </li><li>Demo Lab: Logistic Regression </li><li>Reading: [Optional] Download Assets for Demo Lab: Logistic Regression </li><li>Video: [Optional] Logistic Regression Lab - Part 1 </li><li>Video: [Optional] Logistic Regression Lab - Part 2 </li><li>Video: [Optional] Logistic Regression Lab - Part 3 </li><li>Practice Lab: Logistic Regression </li><li>Practice Assignment: Logistic Regression Labs </li><li>Reading: Summary/Review </li><li>Module 1 Graded Quiz Logisitic Regression </li></ul><div>Module 2: K Nearest Neighbors </div><ul><li>Reading: Learning Objectives </li><li>Video: K Nearest Neighbors for Classification </li><li>Video: K Nearest Neighbors Decision Boundary </li><li>Video: K Nearest Neighbors Distance Measurement </li><li>Video: K Nearest Neighbors Pros and Cons </li><li>Video: K Nearest Neighbors with Feature Scaling </li><li>Practice Assignment: K Nearest Neighbors </li><li>Demo Lab: K Nearest Neighbors </li><li>Video: [Optional] K Nearest Neighbors Notebook - Part 1 </li><li>Video: [Optional] K Nearest Neighbors Notebook - Part 2 </li><li>Video: [Optional] K Nearest Neighbors Notebook - Part 3 </li><li>Practice Lab: K Nearest Neighbors </li><li>Practice Assignment: K Nearest Neighbors Labs </li><li>Reading: Summary/Review </li><li>Module 2 Graded Quiz – KNN </li></ul><div>Module 3: Support Vector Machines </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction to Support Vector Machines </li><li>Video: Classification with Support Vector Machines </li><li>Video: The Support Vector Machines Cost Function </li><li>Video: Regularization in Support Vector Machines </li><li>Practice Assignment: Support Vector Machines </li><li>Video: Introduction to Support Vector Machines Gaussian Kernels </li><li>Video: Support Vector Machines Gaussian Kernels - Part 1 </li><li>Video: Support Vector Machines Gaussian Kernels - Part 2 </li><li>Video: Support Vector Machines Workflow </li><li>Video: Implementing Support Vector Machines Kernal Models </li><li>Practice Assignment: Support Vector Machines Kernels </li><li>Demo Lab: Support Vector Machines </li><li>Video: [Optional] Support Vector Machines Notebook - Part 1 </li><li>Video: [Optional] Support Vector Machines Notebook - Part 2 </li><li>Video: [Optional] Support Vector Machines Notebook - Part 3 </li><li>Practice Lab: Support Vector Machines </li><li>Practice Assignment: Support Vector Machines Labs </li><li>Reading: Summary/Review </li><li>Module 3 Graded Quiz: Support Vector Machines  </li></ul><div>Module 4: Decision Trees </div><ul><li>Reading: Learning Objectives </li><li>Video: Overview of Classifiers </li><li>Video: Introduction to Decision Trees </li><li>Video: Building a Decision Tree </li><li>Video: Entropy-based Splitting </li><li>Video: Other Decision Tree Splitting Criteria </li><li>Video: Pros and Cons of Decision Trees </li><li>Practice Assignment: Decision Trees </li><li>Demo Lab: Decision Trees </li><li>Reading: [Optional] Download Assets for Demo Lab: Decision Trees </li><li>Video: [Optional] Decision Trees Notebook - Part 1 </li><li>Video: [Optional] Decision Trees Notebook - Part 2 </li><li>Video: [Optional] Decision Trees Notebook - Part 3 </li><li>Practice Lab: Decision Trees </li><li>Practice Assignment: Decision Trees Labs </li><li>Reading: Summary/Review </li><li>Module 4 Graded Quiz: Decision Trees </li></ul><div>Module 5: Ensemble Models </div><ul><li>Reading: Learning Objectives </li><li>Video: Ensemble Based Methods and Bagging - Part 1 </li><li>Video: Ensemble Based Methods and Bagging - Part 2 </li><li>Video: Ensemble Based Methods and Bagging - Part 3 </li><li>Practice Assignment: Bagging </li><li>Video: Random Forest </li><li>Practice Lab: Random Forest </li><li>Practice Assignment: Random Forest </li><li>Demo Lab: Bagging </li><li>Reading: [Optional] Download Assets for Demo Lab: Bagging </li><li>Video: [Optional] Bagging Notebook - Part 1 </li><li>Video: [Optional] Bagging Notebook - Part 2 </li><li>Video: [Optional] Bagging Notebook - Part 3 </li><li>Practice Lab: Bagging </li><li>Practice Assignment: Practice Lab: Bagging </li><li>Video: Review of Bagging </li><li>Video: Overview of Boosting </li><li>Video: Adaboost and Gradient Boosting Overview </li><li>Video: Adaboost and Gradient Boosting Syntax </li><li>Video: Stacking </li><li>Practice Assignment: Boosting and Stacking </li><li>Demo Lab: Boosting and Stacking </li><li>Reading: [Optional] Download Assets for Demo Lab: Boosting and Stacking </li><li>Video: [Optional] Boosting Notebook - Part 1 </li><li>Video: [Optional] Boosting Notebook - Part 2 </li><li>Video: [Optional] Boosting Notebook - Part 3 </li><li>Practice Lab: Ada Boost </li><li>Practice Lab: Stacking For Classification with Python </li><li>Practice Lab: (Optional) Gradient Boosting </li><li>Practice Assignment: Boosting and Stacking Labs </li><li>Reading: Summary/Review </li><li>Module 5 Graded Quiz </li></ul><div> </div><div>Module 6: Modeling Unbalanced Classes </div><ul><li>Reading: Learning Objectives </li><li>Video: Model Interpretability </li><li>Video: Examples of Self-Interpretable and Non-Self-Interpretable Models </li><li>Video: Model-Agnostic Explanations </li><li>Video: Surrogate Models </li><li>Practice Lab: Model Interpretability </li><li>Practice Assignment:  Model interpretability </li><li>Video: Introduction to Unbalanced Classes </li><li>Video: Upsampling and Downsampling </li><li>Video: Modeling Approaches: Weighting and Stratified Sampling </li><li>Video: Modeling Approaches: Random and Synthetic Oversampling </li><li>Video: Modeling Approaches: Nearing Neighbor Methods </li><li>Video: Modeling Approaches: Blagging </li><li>Practice Lab: Modeling Imbalanced Classes </li><li>Practice Assignment: Modeling Unbalanced Classes </li><li>Reading: Summary/Review </li><li>Module 6 Graded Quiz </li><li>Peer Assignment: Course Final Project </li><li>Reading: Thanks from the Course Team </li></ul><div><br /></div><h1>General Information</h1><div>This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer or Safari. <br /><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>To make the most out of this course, you should have familiarity with programming on a Python development environment, as well as fundamental understanding of Calculus, Linear Algebra, Probability, and Statistics. </div>
</div>


Machine Learning: Classification

This course covers key supervised machine learning (ML) and classification techniques, including logistic regression, decision trees, ensemble methods, and handling unbalanced datasets. Build and evaluate classification models using real-world data.

<div class="trix-content">
  <div>Explain to a potential learner why this course is important/interesting and what they can gain from taking your course.<br /><br /></div><h1>Course Syllabus</h1><div><strong>Module 1: Generative AI Foundations for Requirements Engineering <br /></strong><br /></div><div>Explore how generative AI supports requirement gathering, stakeholder interviews, and specification drafting. Learn to design prompts, simulate interview scenarios, and convert raw business inputs into structured requirement artifacts such as user stories, use cases, and acceptance criteria. <br /><br /></div><div><strong>Module 2: Process Modeling and Documentation with Generative AI <br /></strong><br /></div><div>Learn to auto-generate BPMN diagrams, process flows, and system architecture visuals from text inputs. Practice converting informal notes into formal documentation, critiquing workflows, and creating business rules and visual reporting assets using AI. <br /><br /></div><div><strong>Module 3: Analysis, Testing, and Compliance with Generative AI <br /></strong><br /></div><div>Enhance your analysis and communication skills using AI-assisted review, executive summaries, stakeholder mapping, and multilingual communication. Generate test cases, simulate deployment environments, and identify performance and compliance considerations using Generative AI. </div><div><strong><br />Module 4: Final Project, Final Quiz, and Course Wrap-Up <br /></strong><br /></div><div><br /></div><h1>General Information</h1><div>This is your place to add any additional information about your course. Feel free to mention the assessment style, a recommended timeline of events, or any other important information that a learner should know.<br /><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>Let your learners know what technology and skills they'll need prior to starting this guided project. Remember that the IBM Skills Network Labs environment comes with many things pre-installed (e.g. Docker) to save them the hassle of setting everything up. Also note that this platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer or Safari.</div>
</div>


Generative AI: Advancing Systems Analysis & Architecture

Are you a Systems Analyst, IT Systems Architect, Software Architect, or a Solutions Architect and keen to use generative AI (GenAI) to enhance how you analyze and design systems, define solution requirements, and share technical insights?  In this course, you’ll learn how to craft prompts and apply AI-driven requirement extraction to convert unstructured inputs, such as stakeholder interviews, emails, and process notes, into structured documentation, including user stories, use cases, system requirements, and acceptance criteria.

<div class="trix-content">
  <div><strong><br />Course outline<br /></strong><br /></div><div><strong>Module 1: Using Generative AI for SEO<br /></strong><br /></div><div>A hands-on sprint that integrates generative AI into the traditional SEO workflow. You’ll learn AI-driven keyword discovery, create topic clusters and content briefs, and optimize blog drafts for intent, readability, and internal linking. You will also generate meta titles, descriptions, multilingual variants, and JSON-LD schemas (article, FAQ, product), and validate the outputs for rich-result eligibility. Short videos explain the “why”; labs provide prompt patterns and reusable templates; quizzes reinforce guardrails so speed never sacrifices accuracy.<br /><br /></div><div><strong>Key learning activities:<br /></strong><br /></div><ul><li><br />AI-driven keyword research and clustering</li><li><br />Prompt-based content brief creation</li><li><br />AI-assisted blog editing and internal linking improvements</li><li><br />Generating and validating meta tags and JSON-LD schema</li><li><br />Practice quiz and module summary materials</li></ul><div><strong><br />Module 2: Final Project, Final Quiz, and Course Wrap-Up<br /></strong><br /></div><div><br />Apply what you’ve learned in a practical final project: Craft an SEO-friendly blog for a researched keyword and perform on-page optimization using the provided workflow and prompts. Complete a graded final quiz to demonstrate mastery, review the course glossary, and conclude with a wrap-up that consolidates practical templates and outlines next steps.<br /><br /></div><div><strong><br />Key learning activities:<br /></strong><br /></div><ul><li><br />Final project: SEO blog creation and optimization</li><li><br />Final exam and glossary review</li><li><br />Course wrap-up and suggested next learning pathways</li></ul><div><strong><br />Tools and software<br /></strong><br /></div><div><br />Work inside the <strong>Generative AI Classroom</strong> authoring environment to test prompts and models. Labs also reference free/trial versions of tools such as <strong>ChatGPT</strong> and <strong>Gemini</strong> for hands-on practice. Paid subscriptions are <strong>not required</strong>.<br /><br /></div>
</div>


Gen AI for SEO: A Hands-On Playbook

Generative AI (GenAI) is now a key power tool in an SEO professional’s toolkit. In this beginner-friendly course, you’ll learn how to leverage its power using tools like ChatGPT, Gemini, Claude, Semrush, and Keyword Insights AI to build AI-driven SEO workflows that boost speed, accuracy, and creativity. You’ll learn how to use GenAI for SEO to conduct AI-driven keyword research, create topic clusters, and build content briefs that align with your target audience’s search intent. 

<div class="trix-content">
  <div>Ready to put your ethical hacking skills to the test and power your cybersecurity career forward? <br /><br />This hands-on course is ideal for aspiring cybersecurity analysts, ethical hackers, and IT professionals who want to be able to demonstrate their real-world skills in offensive and defensive security to employers. <br /><br />During this course, you’ll start on the Red Team, using industry-standard tools such as Kali Linux, Nmap, and Metasploit to conduct reconnaissance, exploitation, privilege escalation, and persistence. Then, you’ll shift to the Blue Team, where you’ll practice log analysis, detect Indicators of Compromise, and respond to attacks using OpenVAS and the MITRE ATT&amp;CK framework.<br /><br />You’ll also explore the growing role of generative AI in cybersecurity, applying AI-assisted reconnaissance, exploit generation, and anomaly detection to strengthen your strategies.<br /><br />Each lab will challenge you to prove your mastery, culminating in a professional-grade incident response report.<br /><br />If you’re keen to showcase your ethical hacking prowess and cybersecurity skills through a portfolio-worthy capstone, enroll today!</div>
</div>


Ethical Hacking Capstone Project: Breach, Response, AI

Master advanced ethical hacking techniques by exploring cybersecurity assessment, threat modeling, and vulnerability management. Gain expertise in vulnerability scanning and the MITRE ATT&CK framework to enhance your ability to detect and prevent intrusions. Learn to navigate complex breach scenarios using AI-driven strategies for effective response. This capstone project empowers learners to safeguard systems with cutting-edge skills.

<div class="trix-content">
  <div>Leverage the power of generative AI (GenAI) to transform your UI UX design capabilities!<br /><br />This course builds the hands-on skills designers and creative professionals need to integrate AI into every stage of the user experience workflow—from ideation and research to prototyping and conversational design.<br /><br />You’ll explore leading tools such as UXPilot, Miro, Visily, Uizard and Figma and learn how you can use AI to streamline tasks such as generating personas and journey maps, creating UX microcopy, and simulating chatbot interactions—while ensuring design human-centered, inclusive, and accessible.<br /><br />In hands-on labs, you’ll build practical skills in AI-assisted wireframing, usability testing, and conversational UX design. Plus, you’ll complete a final project, where you’ll design an AI-powered experience, apply prompt engineering, and refine your solution through feedback loops.<br /><br />Within just 4 weeks, you’ll be ready to embrace AI as a collaborative design partner, and to work faster, smarter, and more innovatively.<br /><br />If you’re looking to power your UI/UX career forward and lead the next wave of AI-enhanced digital experiences, enroll today!</div>
</div>


Generative AI: The Future of UX UI Design

A basic understanding of UI, UX, and generative AI is recommended. Familiarity with design tools, prompts, and user research methods is advantageous.

<div class="trix-content">
  <div><strong>Imagine you're writing code</strong>, whether it's your first Python script or a complex application. You need AI assistance—for debugging, optimization, or architectural advice—but with so many models available, how do you choose the right one?<br /><br /><strong>AI coding assistants</strong> like <strong>Claude 3.7 Sonnet</strong> and <strong>IBM Granite 3.2 8B Instruct</strong> promise to help, but their abilities vary. <em>Does reasoning mode actually improve suggestions? Is one model better for beginners versus complex projects?</em> In this hands-on lab, you'll test these models across <strong>four practical coding tasks</strong>—from basic syntax checks to system design—to see which AI truly elevates your development process. With the <strong>Generative AI Classroom</strong>, compare models side-by-side—<strong>no setup, no fees, no guesswork</strong>. Just log in, run experiments, and discover which AI best supports your coding journey.<br /><br /></div><h1><strong>Project Overview</strong></h1><div>This lab benchmarks <strong>Claude 3.7 Sonnet vs. IBM Granite 3.2 8B Instruct</strong> across coding tasks of increasing complexity: <br />1️⃣ <strong>Basic Code Review</strong> (syntax errors, style fixes) <br />2️⃣ <strong>Algorithm Analysis</strong> (time/space complexity optimizations)<br /> 3️⃣ <strong>System Design</strong> (authentication flows, architecture patterns)<br /> 4️⃣ <strong>End-to-End Feedback</strong> (readability, maintainability, scalability)<br /><br />You’ll evaluate them on three key metrics: <br />✅ <strong>Speed</strong> – Response times for quick iterations <br />✅ <strong>Cost</strong> – Value per query at scale<br /> ✅ <strong>Accuracy</strong> – Error detection and suggestion quality<br /><br /></div><h1><strong>What You’ll Learn</strong></h1><div>By completing this lab, you will:</div><ul><li>Compare <strong>reasoning vs. standard modes</strong> for coding tasks</li><li>Identify which model excels at <strong>beginner support</strong> vs. <strong>expert-level design</strong></li><li>Learn <strong>prompting techniques</strong> to get better coding help</li><li>Gain <strong>hands-on experience</strong> with AI-assisted development</li></ul><h1><strong>Who Should Do This Lab?</strong></h1><div>Perfect for anyone who codes—no matter your level:</div><ul><li><strong>Beginners</strong> seeking AI tutoring for fundamentals</li><li><strong>Intermediate devs</strong> optimizing algorithms</li><li><strong>Senior engineers</strong> evaluating AI for architecture reviews</li><li><strong>Educators</strong> comparing AI teaching tools</li></ul><div><strong>No advanced skills needed</strong>—start with simple code and progress at your pace.</div><div><br /></div><h1><strong>What You Need</strong></h1><div>✅ <strong>A browser</strong> (Chrome/Firefox/Safari etc.) <br />✅ <strong>Basic coding awareness</strong> (any language)<br /> ✅ <strong>Curiosity</strong>—test prompts and draw conclusions!<br /><br /><strong>Zero installations</strong>—everything runs in your browser. By the end, you’ll know whether <strong>Claude’s detailed analysis</strong> or <strong>Granite’s quick feedback</strong> better matches your needs—and how to leverage both effectively.</div>
</div>


AI Code Review Showdown: Anthropic's Claude vs IBM's Granite

Compare Anthropic's Claude 3.7 Sonnet and IBM's Granite 3.2 8B Instruct models for Python code review tasks in both reasoning and non-reasoning modes. This lab evaluates how these hybrid reasoning models perform when analyzing syntax errors, algorithms, authentication systems, and architecture. Discover which model delivers better accuracy, speed, and cost-efficiency for different coding scenarios. Learn when reasoning mode provides advantages over non-reasoning mode and identify optimal use cases for each approach based on comprehensive performance metrics.

<div class="trix-content">
  <div>The Machine Learning Capstone allows you to showcase and strengthen your Python-based machine learning skills. In this hands-on course, you’ll integrate concepts from previous courses and apply them to real-world problems using Pandas, Scikit-learn, and TensorFlow/Keras. </div><div><br />Your primary project involves building a course recommender system. You’ll work with course datasets, calculate cosine similarity, generate similarity matrices, and experiment with multiple algorithms. Using K-Nearest Neighbors (KNN), Principal Component Analysis (PCA), and non-negative matrix collaborative filtering, you’ll compare and evaluate the performance of different recommendation approaches. </div><div><br />In addition, you’ll train a neural network to predict course ratings and develop regression and classification models to enhance your predictive analytics expertise. This project emphasizes both technical skills and critical thinking in model evaluation and selection. <br /><br /></div><div>By course completion, you’ll have a portfolio-ready project, hands-on experience with advanced machine learning techniques, and the confidence to apply your skills to real-world challenges. <br /><br /></div><h1>Learning Objectives</h1><div>• Apply advanced machine learning techniques using Python libraries like Pandas, Scikit-learn, and TensorFlow/Keras. </div><div>• Design and implement a real-world course recommender system using cosine similarity, KNN, PCA, and collaborative filtering. </div><div>• Build and evaluate regression, classification, and neural network models to demonstrate predictive analytics skills. </div><div>• Highlight critical thinking and professional expertise by comparing algorithms, selecting optimal models, and completing a portfolio-ready project. <br /><br /></div><h1>Course Syllabus</h1><div>Welcome  </div><ul><li>Video: Introduction to Machine Learning Capstone </li><li>Ungraded Plugin: Capstone Overview </li></ul><div> </div><div>Module 1: Machine Learning Capstone Overview </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction to Recommender Systems </li><li>Reading: Text Analysis </li><li>Reading: Stopwords and WordCloud </li><li>App Item: Exploratory Data Analysis on Online Course Enrollment Data </li><li>App Item: Extract Bag of Words (BoW) Features from Course Textual Content </li><li>Reading: Sparse and Dense Bag of Words (BOW) Vectors </li><li>Reading: Similarity Measures in Recommender Systems </li><li>App Item: Calculate Course Similarity using BoW Features </li><li>Practice Assignment: Checkpoints: Exploratory Data Analysis on Online Course Enrollment Data </li><li>Graded Assignment: Exploratory Data Analysis and Feature Engineering </li></ul><div> </div><div>Module 2:  Unsupervised-Learning Based Recommender System </div><ul><li>Reading: Learning Objectives </li><li>Video: Content-based Recommender Systems </li><li>Reading: Evaluation Metrics of Recommender Systems </li><li>App Item: Content-based Course Recommender System using User Profile and Course Genres </li><li>Reading: Heatmaps </li><li>App Item: Content-based Course Recommender System using Course Similarities </li><li>App Item: Clustering-based Course Recommender System </li><li>Practice Assignment: Checkpoints:  Unsupervised-Learning Based Recommender System </li><li>Graded Assignment: Unsupervised-Learning Based Recommendation Systems </li></ul><div> </div><div>Module 3: Supervised-Learning Based Recommender Systems </div><ul><li>Reading: Learning Objectives </li><li>Video: Collaborative Filtering-Based Recommender Systems </li><li>Reading: Exploring Surprise Library and KNN Model </li><li>App Item: Collaborative Filtering-based Recommender System using K Nearest Neighbor </li><li>App Item: Collaborative Filtering-based Recommender System using Non-negative Matrix Factorization </li><li>App Item: Course Rating Prediction using Neural Networks </li><li>App Item: Regression-based Rating Score Prediction Using Embedding Features <br />App Item: Classification-based Rating Mode Prediction using Embedding Features </li><li>Practice Assignment: Checkpoints: Supervised-Learning Based Recommender Systems </li><li>Graded Assignment: Supervised-Learning Based Recommendation Methods </li></ul><div> </div><div>Module 4: Share and Present Your Recommender Systems </div><ul><li>Reading: Learning Objectives </li><li>Video: Elements Of A Successful Data Findings Report </li><li>Reading: Structure Of A Report </li><li>Video: Best Practices For Presenting Your Findings </li><li>(Optional) Hands-on Lab: Getting Started With PowerPoint For The Web </li><li>(Optional) Hands-on Lab: Basics of PowerPoint </li><li>(Optional) Hands-on Lab: Save your PowerPoint Presentation as PDF </li></ul><div> </div><div>Module 5: Final Submission </div><ul><li>Reading: Learning Objectives </li><li>Final Submission Overview and Instructions </li><li>Exercise: Preparing Your Presentation (with provided slide template) </li><li>Peer Review: Submit Your Work and Review Your Peers </li><li>Reading: An Overview of the Streamlit Module </li><li>Ungraded Plugin: Introduction to Streamlit </li><li>Ungraded Plugin: Build a Course Recommender App with Streamlit </li><li>Reading: Congratulations and Next Steps </li><li>Reading: Thanks from the Course Team </li></ul><div><br /></div><h1>General Information</h1><div>This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer or Safari. </div><div><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>The following skills are required to be successful with this course:  </div><ul><li>We recommend completing all previous courses in the IBM Machine Learning Professional Certificate before starting this capstone. </li></ul>
</div>


Showcase your machine learning skills in this IBM Capstone course. Use Pandas, Scikit-learn, and TensorFlow/Keras to build a real-world course recommender system through a hands-on project.

<div class="trix-content">
  <div class="trix-content">
  <div>This course dives into two of the most sought-after areas of machine learning: Deep Learning and Reinforcement Learning. Start with Deep Learning, the AI backbone behind image and speech recognition, natural language processing, and other advanced applications. </div><div><br />You’ll learn the theory behind neural networks, including their structure, training methods, and why they excel at handling complex, high-dimensional data. Gain hands-on experience building and training networks and explore modern deep learning architectures widely used in industry. </div><div><br />Next, explore Reinforcement Learning (RL), an AI field focused on decision-making through interaction with environments. Learn key RL concepts: agents, environments, actions, rewards, and policies and see how they combine to enable learning in robotics, autonomous systems, game AI, and more. </div><div><br />By the end of the course, you’ll understand how Deep Learning and RL differ from traditional supervised and unsupervised learning, be able to design and implement basic deep learning models, and grasp the foundational principles of reinforcement learning strategies. <br /><br /></div><h1>Learning Objectives</h1><div>• Explain deep learning concepts, including neural network structure, training processes, and applications to complex datasets. </div><div>• Design, build, and train foundational deep learning models using modern architectures.</div><div>• Apply reinforcement learning principles by identifying agents, environments, actions, rewards, and policies in AI systems. </div><div>• Distinguish between supervised, unsupervised, deep, and reinforcement learning, highlighting their specific use cases and applications. <br /><br /></div><h1>Course Syllabus</h1><div>Course Introduction </div><ul><li>Video: Course Introduction </li></ul><div>Module 1: Introduction to Neural Networks </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction to Neural Networks </li><li>Video: Basics of Neurons </li><li>Video: Neural Networks with Sigmoid Function </li><li>Video: Neuron in Action </li><li>Video: Neural Networks with SKlearn </li><li>App Item: Neural Networks with Sklearn </li><li>Video: Forward Propagation </li><li>Video: Matrix Representation of Forward Propagation </li><li>Video: Main Types of Deep Neural Network </li><li>App Item: Introduction to Neural Networks Demo (Activity) </li><li>Video: (Optional) Introduction to Neural Networks Notebook - Part 1 </li><li>Video: (Optional) Introduction to Neural Networks Notebook - Part 2 </li><li>Practice Assignment: Introduction to Neural Networks </li><li>Video: Gradient Descent Basics </li><li>Video: Compare Different Gradient Descent Methods </li><li>App Item: Gradient Descent Demo (Activity) </li><li>Video: (Optional) Gradient Descent Notebook - Part 1 </li><li>Video: (Optional) Gradient Descent Notebook - Part 2 </li><li>Video: (Optional) Gradient Descent Notebook - Part 3 </li><li>Practice Assignment: Optimization and Gradient Descent </li><li>Reading: Summary/Review </li><li>Module 1 Graded Quiz </li></ul><div>Module 2: Back Propagation Training and Keras </div><ul><li>Reading: Learning Objectives </li><li>Video: How to Train a Neural Network </li><li>Video: Backpropagation </li><li>App Item: Backpropagation Demo (Activity) </li><li>Video: (Optional) Backpropagation Notebook - Part 1 </li><li>Video: (Optional) Backpropagation Notebook - Part 2 </li><li>Video: The Sigmoid Activation Function </li><li>Video: Other Popular Activation Functions </li><li>Video: (Optional) Backpropagation Notebook - Part 3 </li><li>Practice Assignment: Practice: Back Propagation, Activation Functions </li><li>Video: Popular Deep Learning Library </li><li>Video: A Typical Keras Workflow </li><li>Video: Implementing an Example Neural Network in Keras </li><li>App Item: Keras Demo (Activity) </li><li>Video: (Optional) Keras Notebook - Part 1 </li><li>Video: (Optional) Keras Notebook - Part 2 </li><li>Video: (Optional) Keras Notebook - Part 3  </li><li>App Item: Regression with Keras </li><li>App Item: (Optional) Loading Images with Keras </li><li>Practice Assignment: Keras Library </li><li>Reading: Summary/Review </li><li>Module 2 Graded Quiz  </li></ul><div>Module 3: Neural Network Optimizers </div><ul><li>Reading: Learning Objectives </li><li>Video: Optimizers and Momentum </li><li>Video: Regularization Techniques for Deep Learning </li><li>Video: Popular Optimizers </li><li>Video: Details of Training Neural Networks </li><li>Reading: Learning Rate Scheduler Reading </li><li>Video: Data Shuffling  </li><li>App Item: Optimizers </li><li>App Item: Grid Search with Keras </li><li>Video: Transforms </li><li>Practice Assignment: Optimizers and Data Shuffling </li><li>Reading: Summary/Review </li><li>Module 3 Graded Quiz </li></ul><div>Module 4: Convolutional Neural Networks </div><ul><li>Reading: Learning Objectives </li><li>Video: Categorical Cross Entropy </li><li>App Item: Categorical Cross Entropy </li><li>Video: Introduction to Convolutional Neural Networks (CNN) </li><li>Video: Images Dataset </li><li>Video: Kernels </li><li>Video: Convolution for Color Images </li><li>App Item: Images Convolution </li><li>Video: Convolutional Settings - Padding and Stride </li><li>App Item: Padding, Pooling, and Stride </li><li>Video: Convolutional Settings - Depth and Pooling </li><li>App Item: Channels and Flattening </li><li>App Item: Training the Network </li><li>App Item: Convolutional Neural Networks Demo (Activity) </li><li>Video: (Optional) Demo CNN Notebook - Part 1 </li><li>Video: (Optional) Demo CNN Notebook - Part 2 </li><li>Practice Assignment: Convolutional Neural Networks </li><li>Reading: Summary/Review </li><li>Module 4 Graded Quiz </li></ul><div>Module 5: Transfer Learning </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction to Transfer Learning </li><li>Video: Transfer Learning and Fine Tuning </li><li>App Item: Transfer Learning Demo (Activity) </li><li>Video: (Optional) Transfer Learning Notebook </li><li>Practice Assignment: Transfer Learning </li><li>Video: Convolutional Neural Network Architectures – LeNet </li><li>Video: Convolutional Neural Network Architectures – AlexNet </li><li>Video: VGG </li><li>Video: Convolutional Neural Network Architectures – Inception </li><li>Video: Convolutional Neural Network Architectures – ResNet </li><li>App Item: Types of Model APIs in Keras </li><li>App Item: Transfer Learning Examples with Existing Architectures </li><li>Practice Assignment: Convolutional Neural Network Architectures </li><li>Reading: Regularization </li><li>App Item: Regularization Techniques </li><li>Practice Assignment: Regularization </li><li>Reading: Summary/Review </li><li>Module 5 Graded Quiz </li></ul><div>Module 6: Recurrent Neural Networks and Long-Short Term Memory Networks </div><ul><li>Reading: Learning Objectives </li><li>Video: Recurrent Neural Networks (RNNs) </li><li>Video: State and  Recurrent Neural Networks </li><li>App Item: (Optional) Introduction to Sequential Data </li><li>App Item: Existing Recurrent Neural Networks </li><li>Video: Details Recurrent Neural Networks </li><li>App Item: Word Embeddings </li><li>App Item: Recurrent Neural Networks Demo (Activity) </li><li>Video: (Optional) Recurrent Neural Networks Notebook - Part 1 </li><li>Video: (Optional) Recurrent Neural Networks Notebook - Part 2 </li><li>Practice Assignment: Recurrent Neural Networks </li><li>Video: Long-Short Term Memory (LSTM) Networks </li><li>Video: LSTM Explanation </li><li>Video: Gated Recurrent Unit </li><li>Video: Gated Recurrent Unit Details </li><li>App Item: LSTM and GRU Demo (Activity) </li><li>Practice Assignment: LSTM and GRU </li><li>Reading: Summary/Review </li><li>Module 6: Graded Quiz </li></ul><div>Module 7: Autoencoders </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction to Autoencoders </li><li>Video: Autoencoders </li><li>Ungraded Plugin: Transposed Convolution Reading </li><li>App Item: Autoencoders </li><li>Practice Assignment: Autoencoders </li><li>Autoencoders Demo (Activity) </li><li>Video: (Optional) Autoencoders Notebook - Part 1 </li><li>Video: (Optional) Autoencoders Notebook - Part 2 </li><li>Video: (Optional) Autoencoders Notebook - Part 3 </li><li>Video: (Optional) Autoencoders Notebook - Part 4 </li><li>Video: (Optional) Autoencoders Notebook - Part 5 </li><li>Reading: Summary/Review </li><li>Module 7 Graded Quiz  </li></ul><div>Module 8: Generative Models and Applications of Deep Learning </div><ul><li>Reading: Learning Objectives </li><li>Video: What is a Variational Autoencoder </li><li>Video: How Variational Autoencoders Work </li><li>App Item: Variational Autoencoder </li><li>Practice Assignment: Variational Autoencoders </li><li>Video: Introduction to GANs </li><li>Video: How GANS Work </li><li>Video: Issues with Training GANS </li><li>App Item: GANS Lab 1 </li><li>App Item: GANS Lab 2 </li><li>Video: Additional Topics in Deep Learning </li><li>App Item: GPU with Keras </li><li>Video: Model Agnostic Explainable AI </li><li>Practice Assignment: Generative Adversarial Networks </li><li>Reading: Summary/Review </li><li>Module 8 Graded Quiz </li></ul><div>Module 9: Reinforcement Learning </div><ul><li>Reading: Learning Objectives </li><li>Video: Reinforcement Learning (RL) </li><li>App Item: Reinforcement Learning Demo (Activity) </li><li>Video: (Optional) Reinforcement Learning Notebook - Part 1 </li><li>Video: (Optional) Reinforcement Learning Notebook - Part 2 </li><li>Video: (Optional) Reinforcement Learning Notebook - Part 3 </li><li>Video: (Optional) Reinforcement Learning Notebook - Part 4 </li><li>Practice Assignment: Reinforcement Learning </li><li>Reading: Summary/Review </li><li>Module 9 Graded Quiz </li><li>Peer Review: Final Project </li><li>Reading: Thanks from the Course Team </li></ul><div><br /></div><h1>General Information</h1><div>This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer or Safari. <br /><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>To make the most out of this course, you should have familiarity with programming on a Python development environment, as well as fundamental understanding of Calculus, Linear Algebra, Probability, and Statistics. </div>
</div>
</div>


Start your journey in Reinforcement and Deep Learning! Learn neural network theory, build deep learning models, and explore modern AI architectures used in real-world applications. 

<div class="trix-content">
  <div class="trix-content">
  <div>This course introduces classification, a core technique in supervised machine learning used to predict categorical outcomes. You’ll learn to build, train, and evaluate classification models using logistic regression, decision trees, and advanced ensemble methods like random forests and gradient boosting. <br /><br /></div><div>Gain practical experience applying essential ML techniques, including splitting data for training and testing to prevent overfitting and handling unbalanced datasets through oversampling and undersampling. These practices help ensure your models perform reliably on real-world data. <br /><br /></div><div>You’ll also learn how to evaluate models using key performance metrics to compare accuracy and select the most effective approach. By the end of the course, you’ll understand how to implement and interpret various classification algorithms, distinguish classification from other supervised learning types, and apply best practices for building robust, generalizable models. <br /><br /></div><div>Designed for aspiring data scientists and machine learning engineers, this course provides the practical foundation to tackle business challenges like customer churn prediction, fraud detection, and product categorization using classification methods. <br /><br /></div><h1>Learning Objectives</h1><div>• Develop and assess classification models using logistic regression, decision trees, random forests, and gradient boosting. <br />• Apply effective training and testing strategies to enhance generalization and minimize overfitting. <br />• Manage unbalanced datasets with methods like oversampling and undersampling. <br />• Evaluate and compare models using performance metrics to identify the best solution for real-world applications. <br /><br /></div><h1>Course Syllabus</h1><div>Course Introduction </div><ul><li>Reading: About this course </li><li>Video: Welcome </li><li>Reading: Optional: Download data assets </li></ul><div>Module 1: Logistic Regression </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction: What is Classification? </li><li>Video: Introduction to Logistic Regression </li><li>Video: Classification with Logistic Regression </li><li>Video: Logistic Regression with Multi-Classes </li><li>Video: Implementing Logistic Regression Models </li><li>Video: Confusion Matrix, Accuracy, Specificity, Precision, and Recall </li><li>Video: Classification Error Metrics: ROC and Precision-Recall Curves </li><li>Video: Implementing the Calculation of ROC and Precision-Recall Curves </li><li>Practice Assignment: Logistic Regression </li><li>Demo Lab: Logistic Regression </li><li>Reading: [Optional] Download Assets for Demo Lab: Logistic Regression </li><li>Video: [Optional] Logistic Regression Lab - Part 1 </li><li>Video: [Optional] Logistic Regression Lab - Part 2 </li><li>Video: [Optional] Logistic Regression Lab - Part 3 </li><li>Practice Lab: Logistic Regression </li><li>Practice Assignment: Logistic Regression Labs </li><li>Reading: Summary/Review </li><li>Module 1 Graded Quiz Logisitic Regression </li></ul><div> </div><div>Module 2: K Nearest Neighbors </div><ul><li>Reading: Learning Objectives </li><li>Video: K Nearest Neighbors for Classification </li><li>Video: K Nearest Neighbors Decision Boundary </li><li>Video: K Nearest Neighbors Distance Measurement </li><li>Video: K Nearest Neighbors Pros and Cons </li><li>Video: K Nearest Neighbors with Feature Scaling </li><li>Practice Assignment: K Nearest Neighbors </li><li>Demo Lab: K Nearest Neighbors </li><li>Video: [Optional] K Nearest Neighbors Notebook - Part 1 </li><li>Video: [Optional] K Nearest Neighbors Notebook - Part 2 </li><li>Video: [Optional] K Nearest Neighbors Notebook - Part 3 </li><li>Practice Lab: K Nearest Neighbors </li><li>Practice Assignment: K Nearest Neighbors Labs </li><li>Reading: Summary/Review </li><li>Module 2 Graded Quiz – KNN </li></ul><div> </div><div>Module 3: Support Vector Machines </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction to Support Vector Machines </li><li>Video: Classification with Support Vector Machines </li><li>Video: The Support Vector Machines Cost Function </li><li>Video: Regularization in Support Vector Machines </li><li>Practice Assignment: Support Vector Machines </li><li>Video: Introduction to Support Vector Machines Gaussian Kernels </li><li>Video: Support Vector Machines Gaussian Kernels - Part 1 </li><li>Video: Support Vector Machines Gaussian Kernels - Part 2 </li><li>Video: Support Vector Machines Workflow </li><li>Video: Implementing Support Vector Machines Kernal Models </li><li>Practice Assignment: Support Vector Machines Kernels </li><li>Demo Lab: Support Vector Machines </li><li>Video: [Optional] Support Vector Machines Notebook - Part 1 </li><li>Video: [Optional] Support Vector Machines Notebook - Part 2 </li><li>Video: [Optional] Support Vector Machines Notebook - Part 3 </li><li>Practice Lab: Support Vector Machines </li><li>Practice Assignment: Support Vector Machines Labs </li><li>Reading: Summary/Review </li><li>Module 3 Graded Quiz: Support Vector Machines </li></ul><div> </div><div>Module 4: Decision Trees </div><ul><li>Reading: Learning Objectives </li><li>Video: Overview of Classifiers </li><li>Video: Introduction to Decision Trees </li><li>Video: Building a Decision Tree </li><li>Video: Entropy-based Splitting </li><li>Video: Other Decision Tree Splitting Criteria </li><li>Video: Pros and Cons of Decision Trees </li><li>Practice Assignment: Decision Trees </li><li>Demo Lab: Decision Trees </li><li>Reading: [Optional] Download Assets for Demo Lab: Decision Trees </li><li>Video: [Optional] Decision Trees Notebook - Part 1 </li><li>Video: [Optional] Decision Trees Notebook - Part 2 </li><li>Video: [Optional] Decision Trees Notebook - Part 3 </li><li>Practice Lab: Decision Trees </li><li>Practice Assignment: Decision Trees Labs </li><li>Reading: Summary/Review </li><li>Module 4 Graded Quiz: Decision Trees </li></ul><div> </div><div>Module 5: Ensemble Models </div><ul><li>Reading: Learning Objectives </li><li>Video: Ensemble Based Methods and Bagging - Part 1 </li><li>Video: Ensemble Based Methods and Bagging - Part 2 </li><li>Video: Ensemble Based Methods and Bagging - Part 3 </li><li>Practice Assignment: Bagging </li><li>Video: Random Forest </li><li>Practice Lab: Random Forest </li><li>Practice Assignment: Random Forest </li><li>Demo Lab: Bagging </li><li>Reading: [Optional] Download Assets for Demo Lab: Bagging </li><li>Video: [Optional] Bagging Notebook - Part 1 </li><li>Video: [Optional] Bagging Notebook - Part 2 </li><li>Video: [Optional] Bagging Notebook - Part 3 </li><li>Practice Lab: Bagging </li><li>Practice Assignment: Practice Lab: Bagging </li><li>Video: Review of Bagging </li><li>Video: Overview of Boosting </li><li>Video: Adaboost and Gradient Boosting Overview </li><li>Video: Adaboost and Gradient Boosting Syntax </li><li>Video: Stacking </li><li>Practice Assignment: Boosting and Stacking </li><li>Demo Lab: Boosting and Stacking </li><li>Reading: [Optional] Download Assets for Demo Lab: Boosting and Stacking </li><li>Video: [Optional] Boosting Notebook - Part 1 </li><li>Video: [Optional] Boosting Notebook - Part 2 </li><li>Video: [Optional] Boosting Notebook - Part 3 </li><li>Practice Lab: Ada Boost </li><li>Practice Lab: Stacking For Classification with Python </li><li>Practice Lab: (Optional) Gradient Boosting </li><li>Practice Assignment: Boosting and Stacking Labs </li><li>Reading: Summary/Review </li><li>Module 5 Graded Quiz </li></ul><div> </div><div>Module 6: Modeling Unbalanced Classes </div><ul><li>Reading: Learning Objectives </li><li>Video: Model Interpretability </li><li>Video: Examples of Self-Interpretable and Non-Self-Interpretable Models </li><li>Video: Model-Agnostic Explanations </li><li>Video: Surrogate Models </li><li>Practice Lab: Model Interpretability </li><li>Practice Assignment:  Model interpretability </li><li>Video: Introduction to Unbalanced Classes </li><li>Video: Upsampling and Downsampling </li><li>Video: Modeling Approaches: Weighting and Stratified Sampling </li><li>Video: Modeling Approaches: Random and Synthetic Oversampling </li><li>Video: Modeling Approaches: Nearing Neighbor Methods </li><li>Video: Modeling Approaches: Blagging </li><li>Practice Lab: Modeling Imbalanced Classes </li><li>Practice Assignment: Modeling Unbalanced Classes </li><li>Reading: Summary/Review </li><li>Module 6 Graded Quiz </li><li>Peer Assignment: Course Final Project </li><li>Reading: Thanks from the Course Team </li></ul><div><br /></div><h1>General Information</h1><div>This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer or Safari. <br /><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>To make the most out of this course, you should have familiarity with programming on a Python development environment, as well as fundamental understanding of Calculus, Linear Algebra, Probability, and Statistics. </div>
</div>
</div>


Learn key supervised machine learning and classification techniques, including logistic regression, decision trees, ensemble methods, and handling unbalanced data. Build and evaluate powerful classification models using real-world datasets. 

<div class="trix-content">
  <div class="trix-content">
  <div>This course offers a practical introduction to regression, a fundamental technique in supervised machine learning. You’ll explore the full workflow of building regression models from data splitting and feature selection to preventing overfitting through best practices. </div><div><br />Gain hands-on experience training models that predict continuous outcomes and evaluating performance using key metrics like MAE, MSE, and RMSE. Dive deep into linear regression and apply regularization methods such as Ridge, LASSO, and Elastic Net to enhance model accuracy and generalization. </div><div><br />By the end of the course, you’ll be able to distinguish regression from classification problems, implement and interpret linear models, use error metrics for model comparison, and choose the most effective regression approach for your data. </div><div><br />Perfect for aspiring data scientists and machine learning engineers, this course equips you with the technical and analytical skills needed to apply regression techniques to real-world problems. <br /><br /></div><h1>Learning Objectives</h1><div>• Build and test regression models to predict continuous numerical values. </div><div>• Assess model accuracy using performance metrics like MAE, MSE, and RMSE. </div><div>• Use regularization methods like Ridge, LASSO, and Elastic Net to reduce overfitting. </div><div>• Evaluate and compare models to choose the best fit for real-world tasks. <br /><br /></div><h1>Course Syllabus</h1><div>Reading: Course Prerequisites </div><div>Video: Welcome/Introduction Video <br /><br />Module 1: Introduction to Supervised Machine Learning and Linear Regression </div><ul><li>Reading: Learning Objectives </li><li>Video: Introduction to Supervised Machine Learning - Types of Machine Learning (Part 1) </li><li>Video: Introduction to Supervised Machine Learning - Types of Machine Learning (Part 2) </li><li>Video: Supervised Machine Learning (Part 1) </li><li>Video: Supervised Machine Learning (Part 2) </li><li>Video: Regression and Classification Examples </li><li>Practice Assignment: Practice Quiz: Introduction to Supervised Machine Learning </li><li>Video: Introduction to Linear Regression (Part 1) </li><li>Video: Introduction to Linear Regression (Part 2) </li><li>Video: (Optional) Linear Regression Demo – Part 1 </li><li>Video: (Optional) Linear Regression Demo – Part 2 </li><li>Video: (Optional) Linear Regression Demo – Part 3 </li><li>App Item: Demo Lab: Linear Regression </li><li>App Item: Practice Lab: Linear Regression </li><li>Practice Assignment: Practice Quiz: Linear Regression </li><li>Reading: Summary/Review </li><li>Graded Assignment: Module 1 Graded Quiz: Introduction to Supervised Machine Learning and Linear Regression </li></ul><div>Module 2: Data Splits and Polynomial Regression </div><ul><li>Reading: Learning Objectives </li><li>Video: Training and Test Splits (Part 1) </li><li>Video: Training and Test Splits (Part 2) </li><li>App Item: Demo Lab: Training and Test Splits </li><li>Video: (Optional) Training and Test Splits Lab - Part 1 </li><li>Video: (Optional) Training and Test Splits Lab - Part 2 </li><li>Video: (Optional) Training and Test Splits Lab - Part 3 </li><li>Video: (Optional) Training and Test Splits Lab - Part 4 </li><li>Practice Assignment: Practice Quiz: Training and Test Splits </li><li>Video: Polynomial Regression </li><li>App Item: Practice Lab: Polynomial Regression </li><li>Practice Assignment: Practice Quiz: Polynomial Regression </li><li>Reading: Summary/Review </li><li>Graded Assignment: Module 2 Graded Quiz: Data Splits and Polynomial Regression </li></ul><div>Module 3: Cross Validation </div><ul><li>Reading: Learning Objectives </li><li>Reading: Important Note on Labs and Videos </li><li>Video: Cross Validation - Part 1 </li><li>Ungraded Plugin: Reading: K-Fold Cross-Validation </li><li>Video: Cross Validation Demo - Part 1 </li><li>Video: Cross Validation Demo - Part 2 </li><li>Video: Cross Validation Demo - Part 3 </li><li>Video: Cross Validation Demo - Part 4 </li><li>Video: Cross Validation Demo - Part 5 </li><li>App Item: Demo Lab: Cross Validation </li><li>App Item: Practice Lab: Cross Validation </li><li>Practice Assignment: Practice Quiz: Cross Validation </li><li>Reading: Summary/Review </li><li>Graded Assignment: Graded: Module 3 Quiz:  Cross Validation </li></ul><div>Module 4:  </div><ul><li>Reading: Learning Objectives </li><li>Video: Bias Variance Trade off (Part 1) </li><li>Video: Bias Variance Trade off (Part 2) </li><li>Video: Regularization and Model Selection </li><li>Video: Ridge Regression </li><li>Video: Lasso Regression (Part 1) </li><li>Video: Lasso Regression (Part 2) </li><li>Video: Elastic Net </li><li>Practice Assignment: Practice Quiz: Regularization Techniques </li><li>App Item: Demo Lab: Polynomial Features and Regularization </li><li>Video: Polynomial Features and Regularization Demo - Part 1 </li><li>Video: Polynomial Features and Regularization Demo - Part 2 </li><li>Video: Polynomial Features and Regularization Demo - Part 3 </li><li>Practice Assignment: Practice Quiz: Polynomial Features and Regularization </li><li>Reading: Summary/Review </li><li>Graded Assignment: Module 4 Graded Quiz: Bias Variance Trade off and Regularization Techniques: Ridge, LASSO, and Elastic Net </li></ul><div>Module 5: Regularization Details </div><ul><li>Reading: Learning Objectives </li><li>Video: Further details of regularization - Part 1 </li><li>Video: Further details of regularization - Part 2 </li><li>App Item: Demo Lab: Details of Regularization </li><li>Video: (Optional) Details of Regularization - Part 1 </li><li>Video: (Optional) Details of Regularization - Part 2 </li><li>Video: (Optional) Details of Regularization - Part 3 </li><li>App Item: Practice Lab: Regularization </li><li>Practice Assignment: Practice Quiz: Details of Regularization </li><li>Reading: Summary/Review </li><li>Graded Assignment:  Module 5 Graded Quiz: Regularization Details </li></ul><div>Module 6: Final Project </div><ul><li>Reading: Project Scenario </li><li>Hands-on Lab: Final Project </li><li>Final Project Submission and Evaluation </li><li>Congratulations and Next Steps </li><li>Reading: Thanks from the Course Team </li></ul><h1>General Information</h1><div>This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer or Safari. <br /><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>To make the most out of this course, you should have familiarity with programming on a Python development environment, as well as fundamental understanding of Calculus, Linear Algebra, Probability, and Statistics. </div>
</div>
</div>


Machine Learning: Regression

Learn key supervised machine learning techniques in regression analysis. Train and test regression models to build predictive insights that are ideal for aspiring data scientists and machine learning engineers. 

<div class="trix-content">
  <div>Launch your Machine Learning journey with this introductory course, part of the IBM Machine Learning Professional Certificate. Build a solid foundation in key ML concepts and discover the importance of clean, high-quality data. Gain hands-on experience retrieving data from diverse sources like SQL and NoSQL databases, APIs, and cloud platforms. <br /><br /></div><div>Learn essential data preparation techniques, including handling missing values, encoding categorical and ordinal features, detecting and managing outliers, and applying feature engineering and selection methods. Explore feature scaling techniques and understand their impact on model performance. <br /><br /></div><div>By the end of this course, you’ll be able to prepare robust datasets for analysis and hypothesis testing that are crucial skills for real-world Machine Learning projects. Designed for aspiring data scientists, ML professionals, and AI Engineers this course offers practical, industry-relevant experience. <br /><br /></div><h1>Learning Objectives </h1><div>• Retrieve data from various sources—SQL/NoSQL databases, APIs, and cloud platforms—for machine learning tasks. </div><div>• Clean and prepare data by handling missing values, encoding categories, and managing outliers. </div><div>• Apply feature engineering, selection, and scaling to optimize model performance. </div><div>• Prepare high-quality datasets for analysis, hypothesis testing, and real-world ML projects. <br /><br /></div><h1>Course Syllabus</h1><div>Module 1: A Brief History of Modern AI and its Applications </div><ul><li>Reading: Learning Objectives </li><li>Video: Course Introduction </li><li>Reading: Course Prerequisites </li><li>Video: Introduction to Artificial Intelligence and Machine Learning </li><li>Video: Machine Learning and Deep Learning </li><li>Video: Machine Learning And Deep Learning Part 1 </li><li>Video: Machine Learning and Deep Learning - Part 2 </li><li>Video: History of AI </li><li>Video: History of Machine Learning and Deep Learning </li><li>Practice Quiz: Artificial Intelligence and Machine Learning </li><li>Video: Modern AI  </li><li>Video: Applications </li><li>Optional: Say hi or reach out for help </li><li>Video: Machine Learning Workflow </li><li>Practice Quiz: Modern AI Applications and Workflows </li><li>End of the module review &amp; evaluation </li><li>Reading: Review </li><li>Graded Quiz: Module 1 - Modern AI and its Applications </li></ul><div> </div><div>Module 2: Retrieving and Cleaning Data </div><ul><li>Module Summary and Learning Objectives </li><li>Video: Retrieving Data from CSV and JSON Files </li><li>Video: Retrieving Data from Databases, APIs, and the Cloud </li><li>Demo Lab: Reading Data in Database Files - Part A </li><li>Reading: [Optional] Download Assets for Lab: Reading Data in Database Files - Part A </li><li>Video: [Optional] Lab Solution: Reading Data Jupyter Notebook - Part A </li><li>Demo Lab: Reading Data in Jupyter Notebook - Part B </li><li>Reading: [Optional] Download Assets for Lab: Reading Data in Jupyter Notebook - Part B </li><li>Video: [Optional]Lab Solution: Reading in Database Files - Part B </li><li>Practice Quiz: Retrieving Data </li><li>Video: Data Cleaning </li><li>Video: Handling Missing Values and Outliers </li><li>Video: Handling Missing Values and Outliers using Residuals </li><li>Practice Lab: Data Cleaning </li><li>Practice Quiz: Data Cleaning </li><li>Reading: Summary/Review </li><li>Graded Quiz: Module 2 - Retrieving Data and Cleaning Data </li></ul><div> </div><div>Module 3:  </div><ul><li>Module Summary and Learning Objectives </li><li>Video: Introduction to Exploratory Data Analysis (EDA) </li><li>Video: EDA with Visualization </li><li>Video: Grouping Data for EDA </li><li>App Item: Demo Lab: Exploratory Data Analysis </li><li>Reading: [Optional] Download Assets for Lab: Exploratory Data Analysis Lab </li><li>Video: [Optional]Solution: EDA Notebook - Part 1 </li><li>Video: [Optional]Solution: EDA Notebook - Part 2 </li><li>Video: [Optional]Solution: EDA Notebook - Part 3 </li><li>Video: [Optional]Solution: EDA Notebook - Part 4 </li><li>Practice Lab:  Exploratory Data Analysis </li><li>Practice Quiz: Exploratory Data Analysis </li><li>Video: Feature Engineering and Variable Transformation – Background </li><li>Video: Variable Transformation </li><li>Video: Feature Encoding </li><li>Video: Feature Scaling </li><li>Video: Common Variable Transformations in Python </li><li>Demo Lab: Feature Engineering </li><li>Reading: [Optional] Download Assets for Lab: Feature Engineering Demo </li><li>Video: [Optional] Solution: Feature Engineering Lab - Part 1 </li><li>Video: [Optional] Solution: Feature Engineering Lab - Part 2 </li><li>Video: [Optional] Solution: Feature Engineering Lab - Part 3 </li><li>Practice Lab:  Feature Engineering </li><li>Practice Quiz: Feature Engineering and Variable Transformation </li><li>Reading: Summary/Review </li><li>Graded Quiz: Module 3 - Exploratory Data Analysis and Feature Engineering </li></ul><div>Module 4:  </div><ul><li>Video: Estimation and Inference - Introduction </li><li>Video: Estimation and Inference – Example </li><li>Video: Estimation and Inference - Parametric vs. Non-Parametric </li><li>Video: Estimation and Inference - Commonly Used Distributions </li><li>Video: Frequentist vs. Bayesian Statistics </li><li>Practice Quiz: Estimation and Inference, and Hypothesis Testing </li><li>Video: Introduction to Hypothesis </li><li>Video: Hypothesis Testing Example </li><li>Video: Bayesian Interpretation of Hypothesis Testing Example </li><li>Video: Type 1 vs Type 2 Error </li><li>Video: Type 1 vs Type 2 Error: Examples </li><li>Video: Hypothesis Testing Terminology </li><li>Video: Significance Level and P-Values </li><li>Video: Significance Level and P-Values and the F Statistic </li><li>Demo Lab: Hypothesis Testing </li><li>Reading: [Optional] Download Assets for Lab: Hypothesis Testing Demo </li><li>Video: [Optional] Hypothesis Testing Demo - Part 1 </li><li>Video: [Optional] Hypothesis Testing Demo - Part 2 </li><li>Video: Correlation vs Causation </li><li>Practice Lab:  Hypothesis Testing </li><li>Practice Quiz: Hypothesis Testing </li><li>Discussion Prompt: Optional Brainstorming </li><li>Reading: Summary/Review </li><li>Reading: Summary/Review </li><li>Graded Quiz: Module 4 - Inferential Statistics and Hypothesis Testing </li></ul><div> </div><div>Module 5:  </div><ul><li>Module Summary and Learning Objectives </li><li>Reading: Project Overview </li><li>Reading: Submission Guidelines </li><li>Final Project Submission and Evaluation </li><li>Reading: Congratulations &amp; Next Steps </li><li>Reading: Thanks from the Course Team </li></ul><h1>General Information</h1><div>This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer or Safari. <br /><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>To make the most out of this course, you should have familiarity with programming on a Python development environment, as well as fundamental understanding of Calculus, Linear Algebra, Probability, and Statistics.</div>
</div>


Machine Learning: Exploratory Data Analysis

Build essential, employer-valued skills for machine learning and AI success. Master data preparation, retrieval, and cleaning using real-world tools and techniques. 

<div class="trix-content">
  <div>Have you ever wished you could sit down for a realistic job interview, which is tailored exactly to your resume and the role you want, without scheduling with a recruiter, asking a friend for help, or feeling the pressure of a real interview?<br /><br /></div><div>Interview preparation is one of the most important steps in landing a job, but it’s often stressful and uncertain. What questions will they ask? How do your past experiences align with the role? How can you practice speaking confidently and clearly? Traditional prep tools rarely adapt to your personal background, and most mock interviews feel scripted or generic.<br /><br /></div><div>What if an AI agent could read your resume, understand the job you’re applying for, and conduct a personalized, dynamic interview? In this project, you’ll build an AI-powered interview coach that does exactly that. You’ll integrate resume parsing, job-description analysis, natural language generation, speech synthesis, and speech-to-text transcription into one seamless pipeline. Your system will read PDFs, summarize key strengths, generate tailored interview questions, convert them into natural interviewer audio, record the user’s voice responses, transcribe them, and continuously evaluate performance. Everything culminates in a polished, interactive Gradio web interface that lets anyone rehearse for a job interview anytime, anywhere.</div><div><br /></div><h1>What You’ll Learn</h1><div>By the end of this project, you will be able to:</div><ul><li><strong>Extract and understand resume content automatically:</strong> Use PyPDF2 to parse resume PDFs and generate structured summaries to inform the interview.</li><li><strong>Analyze job descriptions with LLM reasoning:</strong> Build a job description expert agent that interprets role expectations, required skills, and hiring priorities.</li><li><strong>Generate intelligent, contextual interview questions:</strong> Use a powerful LLM to ask adaptive questions based on both the resume and prior answers.</li><li><strong>Convert interviewer prompts into speech:</strong> Implement text-to-speech with gTTS to create natural-sounding, interactive audio-based interviews.</li><li><strong>Capture and transcribe user responses:</strong> Use the Faster Whisper model for high-quality speech-to-text transcription of microphone input.</li><li><strong>Deliver real-time evaluation:</strong> Build a custom evaluation agent that summarizes performance, strengths, and areas for improvement.</li><li><strong>Develop a full Gradio app:</strong> Create a smooth, shareable interface that ties all components together—upload, listen, respond, and receive feedback.</li></ul><h1>Who Should Enroll</h1><div>This project is perfect for:</div><ul><li><strong>AI enthusiasts and developers</strong> interested in combining language models, audio processing, and user-facing interfaces.</li><li><strong>Job seekers and career coaches</strong> who want to harness AI to create personalized interview training tools.</li><li><strong>Students and researchers</strong> looking to build multi-step AI systems that integrate text, speech, and interactive workflows.</li><li><strong>Educators</strong> who want a hands-on project demonstrating real-world applications of LLMs and voice interfaces.</li></ul><h1>Why Enroll</h1><div>This project brings the worlds of career development, conversational AI, and multimodal interaction together. Instead of guessing what interviewers might ask—or searching through lists of generic practice questions—you’ll learn to build a tool that understands your background and adapts to your needs. With your AI interview coach, every question, follow-up, and evaluation will be custom-made for the role you’re targeting.</div><div>By the end, you’ll have:</div><ul><li>A fully functional AI interview simulation tool.</li><li>Practical experience integrating text, audio, and LLM workflows.</li><li>A deeper understanding of how generative AI can transform professional skill-building.</li><li>A portfolio-ready project demonstrating real-world relevance and engineering depth.</li></ul><h1>What You’ll Need</h1><div>To get the most out of this project, you should have:</div><ul><li>Basic Python programming skills.</li><li>Some familiarity with AI concepts (LLMs, speech processing, etc.)—helpful but optional.</li><li>Curiosity about how generative AI can enhance professional training and personal development.</li></ul><div>All required libraries are installed in the environment, and the web app works best on the latest versions of Chrome, Firefox, Edge, or Safari.</div>
</div>


Build Your Interview Coach with Llama, OpenAI Whisper & TTS

Build an LLM-powered interview coach that analyzes resumes, reads job descriptions, and conducts personalized mock interviews with OpenAI Whisper speech tool. Extract and summarize resume content automatically, interpret job requirements, and generate tailored interview questions that adapt to the user’s responses in real time. Convert interviewer prompts into natural-sounding audio, record the user’s spoken answers, and transcribe them with Whisper for deeper evaluation. By the end, you’ll build a web app simulating a realistic interview experience, helping you ace interviews!

<div>This program equips you with the practical, job-ready skills used by successful ethical hackers — all in just 2-3 months. Ethical hacking involves authorized testing of computer systems to uncover security weaknesses before malicious actors can exploit them.&nbsp;<br><br></div><div>In this Professional Certificate, you will:&nbsp;</div><ul><li>Define key ethical and legal principles governing ethical hacking and responsible disclosure practices.</li><li>Explain the roles, responsibilities, and ethical distinctions between white hat, gray hat, and black hat hackers.</li><li>Apply Kali Linux tools to perform reconnaissance, vulnerability assessment, and exploitation within controlled environments.</li><li>Demonstrate the use of Metasploit and OpenVAS to execute controlled exploits and vulnerability scans.</li><li>Use Wireshark to evaluate system and network vulnerabilities by interpreting penetration test results and prioritizing risk mitigation strategies.</li><li>Create professional security assessment reports that document findings, ethical considerations, and recommended remediation actions.</li></ul><div>&nbsp;</div><div><strong>Program Overview</strong>&nbsp;</div><div>&nbsp;</div><div>The demand for cybersecurity professionals continues to rise, with information security jobs projected to grow 32% by 2032 (U.S. Bureau of Labor Statistics). As ethical hacking becomes an essential part of modern cybersecurity strategies, skilled ethical hackers are increasingly sought after to safeguard organizations from evolving threats.<br><br></div><div>Through structured labs and real-world projects, you’ll learn how to identify, assess, and mitigate vulnerabilities to strengthen digital defenses.</div><div>You’ll gain hands-on experience with industry-standard open-source tools such as Kali Linux, Metasploit, Wireshark and OpenVAS, while also exploring the ethical and legal foundations of cybersecurity practice. Under the guidance of IBM cybersecurity experts, you’ll learn to conduct controlled penetration tests, perform ethical exploitations, and develop effective incident response strategies.</div><div>By the end of the program, you’ll have built a professional portfolio demonstrating your ability to perform ethical hacking tasks and communicate findings clearly — preparing you for roles such as Ethical Hacker, Penetration Tester, Security Analyst, or Incident Responder.</div><div><br><strong>Applied Learning Projects:</strong></div><div>Throughout the program, you’ll complete hands-on projects simulating real-world cybersecurity scenarios. These projects help you apply theory to practice and develop a well-rounded skillset in ethical hacking.<br><br></div><div>Key projects include:</div><ul><li>Perform controlled penetration tests in virtual environments using Kali Linux&nbsp;</li><li>Capture and analyze network traffic with Wireshark to identify vulnerabilities&nbsp;</li><li>Use Metasploit to execute ethical exploits in isolated systems&nbsp;</li><li>Run vulnerability scans with OpenVAS and develop structured incident response plans&nbsp;</li><li>Practice responsible reporting by documenting discovered vulnerabilities and following ethical disclosure procedures aligned with legal and organizational guidelines.&nbsp;</li><li>Explore how AI-powered tools can enhance threat detection, vulnerability analysis, and penetration testing efficiency in modern cybersecurity practices.&nbsp;</li></ul><div>&nbsp;</div><div>Each project enhances your technical and analytical capabilities, helping you confidently identify, analyze, and resolve security vulnerabilities in professional settings.<br><br></div><div>Whether you’re looking to launch a cybersecurity career or advance into a specialist role such as Ethical Hacker, Penetration Tester, Security Analyst, or Incident Responder, this program will equip you with the job-ready experience and portfolio to stand out in a competitive field.&nbsp;<br><br></div><div>You’ll also work with advanced tools and techniques used by professionals, including Wireshark, OpenVAS, Metasploit, and Kali Linux, to perform real-world security testing and analysis.&nbsp;<br><br></div><div>Finally, through the Capstone project, you’ll explore how AI-powered tools can enhance threat detection, vulnerability assessment, and penetration testing efficiency, applying your skills in a realistic cybersecurity scenario.&nbsp;<br><br></div><div><strong>Enroll today</strong> to start building the ethical hacking skills that employers around the world are looking for.&nbsp;<br>&nbsp;</div><div><strong>Job Outlook</strong>&nbsp;</div><div>&nbsp;</div><div>There is a worldwide shortage of over 3 million skilled cybersecurity experts. (Source: ISC²).&nbsp;<br><br></div><div>With 93% of organizations experiencing two or more identity-related breaches in the past year, demand for risk management and cybersecurity skills is skyrocketing. (Source: Coursera Job Skills Report)&nbsp;<br><br></div><div>More than 50% of public organizations say a lack of resources and skills is their biggest obstacle to achieving cyber resilience. (Source: Coursera Job Skills Report)&nbsp;<br><br></div><div>Earning this certificate positions you for entry-level roles such as:&nbsp;</div><ul><li><strong>Ethical Hacker</strong>&nbsp;</li><li><strong>Penetration Tester</strong>&nbsp;</li><li><strong>Vulnerability Analyst</strong>&nbsp;</li><li><strong>Cybersecurity Analyst</strong>&nbsp;</li><li><strong>Security Operations Center (SOC) Specialist</strong>&nbsp;</li></ul><div><br></div><div>With IBM’s industry-recognized credential, you’ll demonstrate job-ready ethical hacking skills and the ability to protect systems using real-world, open-source tools. <br><br><strong>Prerequisites</strong>&nbsp;<br><br></div><div>Learners should have a basic understanding of IT and cybersecurity fundamentals before starting this course. You will also need access to a desktop or laptop computer capable of running Kali Linux and other cybersecurity tools used throughout the hands-on activities. The following are requirements for the Professional Certificate:<br><br></div><ul><li>This Professional Certificate requires fundamental knowledge of IT concepts and basic cybersecurity principles.&nbsp; The program starts with fundamentals and progressively builds more advanced skills using open-source cybersecurity tools.</li><li>To complete the hands-on exercises in this Professional Certificate, you will need your own desktop or laptop computer capable of running virtualization software and supporting the cybersecurity tools used in the course. You must install several tools, including Kali Linux (via virtualization), Wireshark, Metasploit, and OpenVAS. A reliable internet connection is also required to download these tools and access course materials. Chromebooks, tablets, or systems without virtualization capabilities will not be sufficient for completing the practical components of this program.</li></ul>

IBM Ethical Hacking with OS Tools Professional Certificate 

Master key ethical hacking tools in just 2-3 months. Explore Kali Linux, Wireshark, Metasploit, OpenVAS, and Gen AI for penetration testing, vulnerability assessment, and incident response.

<div>Get ready to launch your systems analyst career with the job-ready skills hiring managers are looking for! This IBM Professional Certificate gives you the essential skills in system analysis, design, business process modeling, stakeholder management, requirements gathering, and data visualization that you need to get your first systems analysis role.&nbsp;</div><div>&nbsp;</div><div><strong>You will learn how to:</strong>&nbsp;</div><div>&nbsp;</div><ul><li>Analyze, design, and develop scalable enterprise system architectures using modeling tools, and agile methodologies.&nbsp;</li><li>Analyze, design, and document IT systems using tools such as data flow diagrams, entity-relationship diagrams, and UML &nbsp;</li><li>Develop working knowledge of IT systems design, analysis, software testing, deployment, and maintenance strategies. &nbsp;</li><li>Gather, document, and validate business and technical needs while engaging stakeholders to ensure alignment and successful outcomes.&nbsp;</li></ul><div><strong>Program overview</strong>&nbsp;</div><div>&nbsp;</div><div>Systems analysts play a key role in evaluating, designing, and improving computer systems and business processes to boost organizational efficiency. &nbsp;</div><div>In this program, you’ll learn how to identify business needs, map workflows, and design impactful IT solutions. And you’ll get hands-on using data visualization tools, such as Excel, Cognos, and data modeling techniques—all while developing documentation and visualization skills. &nbsp;</div><div>&nbsp;</div><div>You’ll also discover how systems analysts support agile teams, drive change management initiatives, and align stakeholders through effective communication and risk management. Plus, you’ll dive into IT system design, testing, and maintenance, and then you will work on a capstone project to demonstrate your learning from this program. &nbsp;</div><div>&nbsp;</div><div>If you’re keen to launch your career in systems analysis with confidence, enroll today and power up your resume with the in-demand skills employers are looking for!&nbsp;</div><div>&nbsp;</div><div><strong>Your job outlook</strong>&nbsp;</div><div>&nbsp;</div><div>Demand for systems analysts is growing much faster than the average for all occupations (US Bureau of Labor Statistics). So, with the right skills, you have a lot to look forward to in your career.&nbsp;</div><div>&nbsp;</div><ul><li>According to the US Bureau of Labor Statistics, employment of systems analysts is projected to grow 9 percent till 2034.&nbsp;</li><li>Any organization that depends on technology to function can require the expertise of a systems analyst—including tech companies, financial institutions, healthcare organizations, government agencies, retail businesses, and manufacturing enterprises.&nbsp;</li></ul><div><br><strong>Prerequisites</strong>&nbsp;</div><div>&nbsp;</div><div>To get the most from this program, you need to have computer literacy .&nbsp;</div>

IBM Systems Analyst Professional Certificate

Build the job-ready systems analyst skills employers need in 4 months. Master process modeling, requirements gathering, stakeholder management and much more. 

<div class="trix-content">
  <div>Hello, and welcome to the Systems Analyst Capstone Project course!<br /><br /></div><div>This capstone course is designed for aspiring and current systems analysts ready to apply their knowledge and skills to solve real-world business challenges. Through this comprehensive project-based course, you will take on the role of a Systems Analyst for XYZ Health Solutions, a mid-sized healthcare provider facing operational inefficiencies and fragmented systems. You will design and implement a unified IT solution that addresses critical challenges in patient records, appointment scheduling, and billing processes.<br /><br /></div><div>This capstone brings together all the essential skills you’ve developed throughout the program, from core systems concepts to process modeling and requirements gathering, stakeholder management and project planning, data visualization and dashboards, IT fundamentals, systems design and analysis, and software testing, deployment, and maintenance.<br /><br /></div><div>Whether launching your systems analyst career or advancing your current role, this capstone provides hands-on experience with the tools, techniques, and methodologies used by professional systems analysts in today's technology-driven business environment.</div><div><br />This course is the culmination of the <a href="https://www.coursera.org/professional-certificates/ibm-systems-analyst/">IBM Systems Analyst Professional Certificate</a> program. The other courses in this certificate program include:</div><ul><li><a href="https://www.coursera.org/learn/introduction-to-systems-analysis?specialization=ibm-systems-analyst">Introduction to Systems Analysis</a></li><li><a href="https://www.coursera.org/learn/business-analysis-process-modeling-requirements-gathering?specialization=ibm-systems-analyst">Business Analysis: Process Modeling &amp; Requirements Gathering</a></li><li><a href="https://www.coursera.org/learn/business-analysis-project-and-stakeholder-management?specialization=ibm-systems-analyst">Business Analysis: Project and Stakeholder Management</a></li><li><a href="https://www.coursera.org/learn/data-visualization-dashboards-excel-cognos?specialization=ibm-systems-analyst">Data Visualization and Dashboards with Excel and Cognos</a></li><li><a href="https://www.coursera.org/learn/information-technology-it-fundamentals-for-everyone?specialization=ibm-systems-analyst">Information Technology (IT) Fundamentals for Everyone</a></li><li><a href="https://www.coursera.org/learn/it-systems-design-and-analysis?specialization=ibm-systems-analyst">IT Systems Design and Analysis</a></li><li><a href="https://www.coursera.org/learn/software-testing-deployment-and-maintenance-strategies?specialization=ibm-systems-analyst">Software Testing, Deployment, and Maintenance Strategies</a></li><li>Generative AI for Systems Analyst (Coming soon)</li><li>Practice Exam for CISA Certification (Coming soon)</li></ul><div>Follow the links above to learn more about the complete program and see how these courses can benefit you and advance your career as a systems analyst.<br /><br /></div><h1>Course Syllabus</h1><div>Module 1: Project Initiation and Requirements Gathering</div><div>Module 2: Project Planning and Process Modeling</div><div>Module 3: Data Preparation and Visualization</div><div>Module 4: System and Database Design</div><div>Module 5: System Testing and Deployment Strategies</div><div>Module 6: Final Submission and Evaluation</div><div>Bonus: Career Guidance and Next Steps</div><div><br /></div><h1>Course objectives</h1><div>After completing this course, you will be able to:</div><div>Build job-ready systems analysis skills to design IT solutions that enhance operations and data management</div><div>Create process models, Entity-Relationship Diagrams (ERDs), and interactive dashboards to visualize and optimize workflows</div><div>Implement data quality, security, and compliance measures aligned with standards and regulations</div><div>Deliver a comprehensive IT solution that addresses stakeholder needs and supports data-driven decision-making</div><div>Develop professional presentation skills to communicate technical solutions to diverse business stakeholders<br /><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>This capstone course is designed for learners who have completed all the courses in the IBM Systems Analyst Professional Certificate program. To get the most out of your learning experience, you should have some background in these topics:</div><ul><li>Stakeholder engagement techniques and requirements elicitation methods</li><li>Requirements documentation using Business Requirements Documents (BRD) and System Requirements Specifications (SRS)</li><li>Process mapping and flowcharts using tools like Lucidchart</li><li>Basic data analysis and visualization using Excel and analytics platforms</li><li>Fundamental principles of system design and database concepts</li><li>Project management methodologies and risk assessment techniques</li></ul>
</div>


Systems Analyst Capstone Project

During this project, you’ll apply systems analysis methodologies to streamline business processes, data management, and system integration. Through hands-on labs, you’ll use requirements gathering techniques, create process models using UML diagrams, design relational databases, and build interactive dashboards using Tableau or Cognos.As you work, you’ll demonstrate your end-to-end systems analysis skills in stakeholder management, data security, and meeting compliance requirements.

<div class="trix-content">
  <div>Explain to a potential learner why this course is important/interesting and what they can gain from taking your course.<br /><br /></div><h1>Course Syllabus</h1><div>Module 1 Develop a Recycling Tracker</div><div>Module 2 Build the PetCare Scheduler </div><div><br /></div><h1>Prerequisites</h1><div>To get the most out of this course, you should be comfortable with the following Java-related tools and programming techniques:</div><ul><li>Use the Java Development Kit (JDK), Java Runtime Environment (JRE), and an Integrated Development Environment (IDE).</li><li>Implement data types, variables, operators, and control flows.</li><li>Work with arrays, strings, methods, and implement robust exception handling.</li><li>Apply object-oriented programming (OOP) principles to define and implement classes and objects, using encapsulation and abstraction.</li><li>Use advanced OOP concepts such as inheritance, polymorphism, interfaces, and method overloading.</li><li>Apply the Java Collections Framework to manage data with lists, sets, queues, and maps.</li><li>Perform basic file and directory operations.</li><li>Implement commonly used techniques for handling dates and times in Java.</li></ul><div>If you need these skills, these courses offer the experience you need for success in this course<br /><br />Course 1:<br />Java for Beginners<br /><br />Course 2:<br />Object Oriented Programming in Java</div><div><br /></div><h1>Course Objectives:</h1><div>After completing this single-module course, you will be able to:</div><ul><li>Design and build modular Java applications using object-oriented programming (OOP), classes, and collections.</li><li>Develop console-based Java systems that support user interaction, data persistence, and file handling.</li><li>Implement exception handling in Java to manage input errors, enforce data integrity, and handle file operations.</li><li>Generate formatted reports from object data using Java filtering and display techniques.</li></ul><div>In this hands-on course, you'll put your Java skills into action by building two prototype console-based applications, a recycling tracker, and a pet care appointment system. You'll apply object-oriented programming to design modular code, work with ArrayLists and HashMaps to manage data, and use file I/O to store and retrieve information. You'll practice handling exceptions, validating user input, and generating clear, formatted reports. By the end, you'll have developed working console-based applications you can share with employers to showcase your growing Java expertise.</div>
</div>


Java App Development Project: Fundamentals, OOP & File I/O

Boost your Java development skills with curated projects designed to help you quickly build real-world experience.   Through online project-based labs, you'll apply critical development techniques that employers expect a good Java developer to know.  You'll gain hands-on experience coding console-based Java applications, practice your skills working with a console-based recycling tracker, and prove your capabilities building a pet appointment management system that incorporates object-oriented programming (OOP), Java collections including ArrayLists and HashMaps.

<div class="trix-content">
  <div>Ready to take your Java skills to the next level? This course bridges the gap between basic Java programming and enterprise-level software engineering. You’ll build valuable enterprise Java development skills founded on modern patterns and practices that make your resume stand out!<br /><br />During the course, you'll master design patterns using lambda expressions, implement Test-Driven Development (TDD) with JUnit 5 and Mockito, and deploy scalable applications using Docker and Kubernetes.<br /><br />In hands-on labs and real-world scenarios, you'll learn Gang of Four patterns modernized for Java 17+, comprehensive testing strategies, and cloud-native deployment approaches that top tech companies use daily. Plus, through a project-based approach, you’ll combine three critical enterprise skills: design pattern implementation, test-driven development, and containerization practices, building a complete inventory management system. A great addition to your portfolio that you can talk about in interviews! <br /><br />If you’re keen to build more advanced Java development skills employers need for Java developer roles, enroll today!<br /><br /></div><h1>Course Syllabus</h1><div><strong>Module 1: Modern Java Design Patterns</strong></div><div><strong>Module 2: Testing with Java</strong></div><div><strong>Module 3: Deployment Practices with Java</strong></div><div><strong>Module 4: Final Project and Course Wrap-Up</strong></div><div><br /></div><h1>General Information</h1><div>After completing this course, you will be able to: </div><ul><li>Design tests for extensible Java 17+ applications using factory, strategy, and observer patterns and apply them to solve real-world problems. </li><li>Implement and assess modern design patterns with Java features, including lambdas, functional interfaces, and modular architecture. </li><li>Build robust Java test suites using TDD, JUnit 5, AssertJ, and Mockito to ensure unit and integration test coverage for microservices. </li><li>Deploy secure, cloud-ready Java apps using Docker, Maven, and CI/CD pipelines with best practices in dependency management. </li></ul><div><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>This course is recommended for learners who have foundational software engineering skills, Java programming and object-oriented programming skills, working knowledge of Git and GitHub, and familiarity with cloud-native concepts. </div><div><br />If you don't yet have these skills, the following courses provide the knowledge and skills you need to successfully complete this course: <br /><br /></div><ul><li><a href="https://www.coursera.org/learn/introduction-to-software-engineering">Introduction to Software Engineering </a></li><li><a href="https://www.coursera.org/learn/java-for-programming-beginners">Java Programming for Beginners </a></li><li><a href="https://www.coursera.org/learn/getting-started-with-git-and-github">Getting Started with Git and GitHub</a></li><li><a href="https://www.coursera.org/learn/object-oriented-program-in-java">Object Oriented Programming in Java </a></li><li><a href="https://www.coursera.org/learn/cloud-native-microservices-containers-devops-agile?specialization=java-developer">Cloud Native, Microservices, Containers, DevOps, and Agile</a></li></ul><div><br /></div><div>You will need a laptop or desktop with internet access to access the course materials. </div>
</div>


Java: Design Patterns, Testing and Deployment

In this course, you'll learn how to design flexible Java applications using factory, strategy, and observer patterns to solve real-world problems. You'll discover how to apply modern Java 17+ features such as lambdas, functional interfaces, and modular architecture to write clean, maintainable code. Then learn how to build strong test suites for test-driven development (TDD) using JUnit 5, AssertJ, and Mockito to catch bugs early and help ensure reliability. Then, explore how you can deploy applications to production using Docker, Maven, and CI/CD pipelines. 

<div class="trix-content">
  <div>Build job-ready cybersecurity skills through practical experience in incident response and vulnerability assessment using OpenVAS.  <br /><br /></div><div>Designed for cybersecurity professionals and aspiring ethical hackers, this course immerses you in realistic lab environments where you’ll install and configure OpenVAS, run scans, interpret CVSS scores, and identify vulnerabilities across networked systems.  <br /><br /></div><div>As you progress, you’ll learn to detect threats by analyzing system and network logs, correlating scan results with known attack patterns, and applying proven containment strategies. You’ll go beyond just technical execution and learn to prioritize risks, recommend remediation actions, and document your findings in structured, professional reports.  <br /><br /></div><div>You’ll also integrate threat intelligence and lessons learned into actionable post-incident improvements.  <br /><br /></div><div>A final hands-on project simulates a full incident response lifecycle from detection to reporting—great for job interviews!   <br /><br /></div><div>With guided labs, quizzes, and a final assignment, this course builds real-world readiness and adds a valuable credential to your cybersecurity portfolio.  <br /><br /></div><div>Ready to dive in and defend against real-world threats? Enroll today. <br /><br /></div>
</div>


Incident Response and Defense with OpenVAS

This course provides a hands-on, structured approach to incident response and defense activities using OpenVAS. Learners will gain the skills to configure, operate, and analyze vulnerability scans, detect threats, prioritize risks, and respond effectively to cybersecurity incidents. Through interactive videos, readings, labs, and assessments, learners will develop essential operational cybersecurity skills required in real-world environments.

<div class="trix-content">
  <div>Prepare to get hands-on using tools and strategies to design, analyze, and evaluate IT systems with confidence! During this course, you’ll explore how to connect technology with business needs and dive into practical projects using techniques such as data flow diagrams, entity-relationship diagrams, and Unified Modeling Language (UML) to map and improve real-world systems. </div><div><br />As you progress, you'll investigate how system architecture, technical workflows, and enterprise tools such as ERP and CRM shape business operations. You'll sharpen your ability to spot inefficiencies, evaluate solutions, and assess feasibility and risk to support smart decision-making. Plus, by combining structured and object-oriented design methods with business process modeling, you'll strengthen your skills to turn user needs into effective, workable solutions. <br /><br />Whether you're starting a career in systems analysis or enhancing your current IT expertise, this course will help you become a key contributor in delivering scalable, user-focused technology solutions. <br /><br />Enroll today and power up your resume with the IT systems design and analysis skills businesses are actively looking for!<br /><br /></div><h1>Course Syllabus</h1><div><strong>Module 1: System Design and Modeling</strong></div><div><strong>Module 2: IT Systems Analysis and Review</strong></div><div><strong>Module 3: Solution Evaluation and Feasibility Analysis</strong></div><div><strong>Module 4: Guided Project, Final Assessment, and Course Wrap-Up</strong></div><div><br /></div><h1><strong>Objectives</strong></h1><ul><li>Create data flow diagrams, entity-relationship diagrams, and unified modeling language diagrams to visualize data movement, database structures, system architecture, and workflows </li><li>Evaluate existing IT systems by assessing system architecture, features, performance, and UI/UX to identify inefficiencies and propose enhancements for improved functionality and business alignment </li><li>Conduct cost-benefit analyses, operational feasibility studies, and risk assessments to compare IT solution alternatives and recommend optimal, financially viable, and operationally sustainable solutions </li><li>Integrate system analysis, modeling, and evaluation techniques in a comprehensive project to propose a digital transformation strategy for a real-world business </li></ul><div><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>This course is recommended for professionals looking to develop their skills as system analysts, IT professionals, or business analysts. A grounding in fundamental IT concepts, such as databases, software development, or basic programming, is recommended. <br /><br /></div><div>If you need to build your knowledge in these areas before starting this course, the following resources can help:</div><div><br /><a href="https://www.coursera.org/professional-certificates/ibm-business-analyst-professional-certificate">IBM Business Analyst Professional Certificate</a></div><div><br /><a href="https://www.coursera.org/learn/introduction-software-programming-and-databases">Introduction to Software, Programming, and Databases<br /></a><br /></div>
</div>


IT Systems Design and Analysis

This course is designed for current or aspiring systems analysts, IT managers and professionals, and business analysts looking to develop skills in implementing IT systems. This course equips you with the knowledge and skills to analyze, design, and implement IT systems and connect business needs with technical solutions. You will explore how the right tools will help you strengthen your IT experience and deliver user-centered IT solutions.

<div class="trix-content">
  <div>This course provides hands-on training in network traffic analysis using Wireshark for cybersecurity professionals. You’ll learn to capture, analyze, and interpret network traffic to detect security threats and investigate incidents. Through practical exercises, you’ll gain experience with packet sniffing, protocol analysis, and traffic flow monitoring while working with real-world network data.<br /><br /></div><div>The curriculum covers essential techniques including Deep Packet Inspection (DPI), traffic filtering, and anomaly detection. You’ll practice identifying malicious patterns like DDoS attacks, port scanning, and data exfiltration attempts. Case studies simulate actual security incidents, teaching you to correlate evidence and trace attack vectors through network traffic.<br /><br />A key focus is developing actionable reporting skills for incident response teams. You’ll learn to document findings, create visualizations of network activity, and present technical details to both security teams and non-technical stakeholders. The course culminates in a capstone project where you analyze a complex traffic capture and produce a professional security assessment report.<br /><br />Designed for aspiring cybersecurity analysts, network administrators, and IT professionals, this training bridges the gap between theoretical knowledge and practical traffic analysis skills. You’ll finish with hands-on experience using industry-standard tools and techniques that are immediately applicable in security operations centers and forensic investigations.<br /><br /></div><h1>Course Syllabus</h1><div><strong>Module 1: Network Forensics and Network Traffic Analysis</strong></div><div><strong>Module 2: Packet Capture and Filtering with Wireshark</strong></div><div><strong>Module 3: DPI and Network Protocol Analysis</strong></div><div><strong>Module 4: Advanced Traffic Analysis and Reporting</strong></div><div><strong>Module 5: Final Project and Course Wrap-Up</strong></div><div><br /></div><h1><strong>Course objectives</strong></h1><ul><li>Describe the principles, objectives, tools, and challenges of network forensics and traffic analysis</li><li>Apply packet capture and filtering techniques using tools like Wireshark</li><li>Analyze network protocols and traffic using Deep Packet Inspection (DPI) and flow data to identify potential security threats</li><li>Create detailed reports from captured data tailored for stakeholders and incident response teams</li></ul><h1>Recommended Skills Prior to Taking this Course</h1><div>To get the most out of this course, you should have:<br /><br /></div><div><strong>Basic networking knowledge</strong> (TCP/IP, OSI model fundamentals)</div><div><strong>Cybersecurity fundamentals<br />Familiarity with command-line interfaces</strong> (Linux/Windows)<br /><br /></div><div>If you need to build your knowledge in these areas before starting this course, the following resources can help:<br /><a href="https://www.coursera.org/learn/information-technology-it-fundamentals-for-everyone">Information Technology (IT) Fundamentals for Everyone</a><br /><a href="https://www.coursera.org/specializations/cybersecurity-fundamentals">Cybersecurity Fundamentals Specialization</a></div>
</div>


Network Traffic Analysis with Wireshark

This comprehensive course teaches you network traffic analysis and its critical applications in cybersecurity and ethical hacking. Using Wireshark, the industry-standard packet analysis tool, you'll develop essential skills for detecting threats, investigating security incidents, and strengthening network defenses through hands-on, real-world scenarios.You'll begin by exploring the fundamentals of network forensics and traffic analysis. You'll learn to distinguish between different investigation approaches while understanding the ethical and legal considerations involved.

<div class="trix-content">
  <div>The user interface (UI) design market is growing fast, driven by the increasing demand for digital products that prioritize user experience (UX) (Global Growth Insights).  <br /><br />This course offers an in-depth exploration of UX/UI fundamentals, design thinking, user-centered methodologies, interaction principles, and the strategic use of UX animations, enabling learners to craft seamless, visually engaging, and highly functional digital experiences. <br /><br />During the course, you’ll look at key aspects of UX/UI design, how to conduct heuristic evaluations to identify and fix usability issues and use user journey mapping to understand and optimize user flows. You’ll explore A/B testing techniques that help you make data-driven design decisions. Plus, you’ll dive into microinteraction design to create engaging user interactions and learn to build responsive user interfaces that ensures consistency across different devices.  <br /><br />Using industry-leading tools like Miro and Figma, you’ll apply your skills through hands-on labs, real-world design challenges, and usability testing frameworks. Then, you’ll complete a project designing a fully interactive UX/UI prototype for a health and fitness app, conduct usability testing, gather feedback, and refine your design to create a polished product, perfect for your portfolio!  <br /><br />If you’re keen to kickstart your UX/UI career with the core UI/UX skills employers are looking for, enroll today!</div>
</div>


UI/UX Design: Usability and Visual Principles

Learn beginner-level UI/UX design principles that enhance usability and visual appeal in digital products. Master key skills like user research, wireframing, color theory, and typography to create intuitive interfaces. Translate user needs into effective design solutions with hands-on projects and real-world examples. Elevate your design proficiency by understanding fundamental concepts that improve user interaction and satisfaction.

<div class="trix-content">
  <div>Welcome to the Practice Exam for CompTIA Tech+ Certification course. This reading will introduce the course outline and prerequisites, giving you a comprehensive overview of what to expect and the background knowledge required to navigate the course content successfully.<br /><br /></div><div><strong>Prerequisites<br /></strong><br /></div><div>This course assumes you’re familiar with the IT fundamentals that the CompTIA Tech+ exam tests on. <br /><br /></div><div><strong>Course Outline<br /></strong><br /></div><div><strong>Module 1:</strong> About the CompTIA Tech+ Certification Exam<br /><br /></div><ul><li>Lesson 1: Welcome to the Course<br />Lesson 2: CompTIA Tech+<br /><br /></li></ul><div><strong>Module 2:</strong> Practice Exam for Tech+ Certification<br /><br /></div><div><strong>Module 3:</strong> Course Wrap-Up and Cloud Basics Exam<br /><br /></div><ul><li>Lesson 1: Course Wrap-Up<br />Lesson 2: [Optional] Cloud Basics Exam<br /><br /></li></ul>
</div>


Practice Exam for CompTIA Data+ Certification

CompTIA Tech+ certification is highly regarded by employers and can open the door to entry-level roles such as help desk technician or junior system administrator. This short course helps you prepare effectively for the certification exam.  

<div class="trix-content">
  <div>Transformers have revolutionized the way machines understand and process information, not only in text but also in <strong>images</strong>. Vision Transformers (ViTs) have become a cornerstone in modern computer vision, outperforming traditional convolutional networks on many tasks. However, fine-tuning such powerful models can be <strong>computationally expensive</strong> and <strong>memory-intensive</strong>, especially on personal hardware or CPUs.<br /><br /></div><div>That’s where <strong>LoRA (Low-Rank Adaptation)</strong> comes in. LoRA makes it possible to <strong>adapt large pretrained models efficiently</strong>. This project demonstrates how you can take a <strong>pretrained Vision Transformer</strong> and fine-tune it to recognize <strong>new image classes</strong> even with <strong>limited data and no GPU</strong>. By completing this project, you’ll not only understand how modern vision models work but also how to adapt them <strong>practically and efficiently</strong> for your own use cases.<br /><br /></div><h1>A Look at the Project Ahead</h1><div><strong>In this project, you will:</strong></div><ul><li><strong>Learn the architecture of Vision Transformers (ViTs): </strong>how images are processed and interpreted.</li><li><strong>Explore the intuition behind LoRA (Low-Rank Adaptation): </strong>Why is it so effective for lightweight fine-tuning.</li><li><strong>Load and modify a pretrained DeiT (Data-efficient Image Transformer)</strong> model from Hugging Face.</li><li><strong>Extend a model’s classifier head</strong> to recognize new labels and correctly map label IDs for training.</li><li><strong>Freeze base model weights</strong> and <strong>insert LoRA adapters</strong> to adapt only selected attention layers.</li><li><strong>Preprocess image datasets</strong> using feature extractors compatible with vision transformers.</li><li><strong>Fine-tune and evaluate</strong> the adapted model on a small image dataset.</li></ul><div><strong>Skills You’ll Gain:</strong></div><ul><li>Proficient understanding of <strong>transfer learning</strong> and <strong>parameter-efficient fine-tuning (PEFT)</strong>.</li><li>Practical experience with <strong>Hugging Face Transformers</strong>, <strong>PEFT</strong>, and <strong>Datasets</strong> libraries.</li><li>Hands-on implementation of <strong>LoRA adapters</strong> in PyTorch.</li></ul><div><br /></div><h1>What You'll Need</h1><ul><li>A compatible modern browser (Chrome, Firefox, Edge, or Safari).</li><li>Basic Python and PyTorch programming</li><li>High-level understanding of transformer architecture.</li><li>Introductory  knowledge of linear algebra (specifically matrix manipulation).</li><li>Curiosity about transformers and modern computer vision methods</li></ul>
</div>


Fine Tune a Vision Model for Image Classification with LoRA

Learn to fine-tune a Vision Transformer (ViT) with LoRA (Low-Rank Adapters) for targeted image classification and adapt AI models to your own data for any use case. You might think fine-tuning a model with millions of parameters requires massive compute and memory, not with LoRA. In this guided project, you'll load a pretrained DeiT model using Hugging Face's API, extend its ability to detect new classes, and train it on a custom dataset. You'll learn how parameter-efficient fine-tuning (PEFT) makes adapting large transformer models fast, lightweight, and cost-effective for any use case.

<div class="trix-content">
  <div> Have you ever wished you could redesign your favorite outfit with just a few words: <em>"make the sleeves longer," "turn this dress into silk," or "change the color to emerald green"</em>? <br /> <br />Fashion design is a deeply creative process, but traditional editing tools demand time, precision, and technical skill. What if AI could understand your description, automatically identify the clothing item you want to change, and instantly generate your new design?  In this project, you’ll build an <strong>AI-powered fashion design assistant</strong> that combines the <strong>CLIPSeg segmentation and</strong> <strong>Segment Anything Model (SAM)</strong> with <strong>DALL·E 2</strong> to make text-guided fashion editing effortless. Together, these models form a seamless workflow: SAM figures out <em>what</em> to edit, and DALL·E 2 decides <em>how</em> to recreate it. You’ll integrate both into a user-friendly <strong>Gradio web app</strong>, where users can upload an image, select a fashion item, describe the desired transformation, and see the result generated in seconds. Along the way, you’ll learn how to bridge computer vision and generative AI to build real-world creative tools.  <br /><br /></div><h1>What You’ll Learn</h1><div>By the end of this project, you will be able to: </div><ul><li><strong>Apply the CLIPSeg and Segment Anything Model for automatic mask generation:</strong> Use SAM to detect and segment fashion elements from uploaded images, enabling precise and flexible edits without manual input.</li><li><strong>Leverage DALL·E 2 for text-guided inpainting:</strong> Use OpenAI’s generative model to redesign masked regions according to user prompts, changing textures, colors, and styles seamlessly.</li><li><strong>Build an interactive Gradio web interface:</strong> Create a shareable AI design assistant where users can visualize edits, experiment with different looks, and generate new outfit ideas from plain language.</li><li><strong>Combine vision and generative AI workflows:</strong> Understand how to connect segmentation models with diffusion-based image generators for practical, creative applications.</li></ul><div><br /></div><h1>Who Should Enroll</h1><ul><li><strong>AI enthusiasts and developers</strong> interested in combining computer vision and generative models.</li><li><strong>Designers, artists, or fashion students</strong> curious about how AI can accelerate and inspire the design process.</li><li><strong>Students and researchers</strong> who want hands-on experience building multi-model AI systems with real-world creative use cases.</li></ul><div><br /></div><h1>Why Enroll</h1><div>This project brings the worlds of <strong>fashion, creativity, and artificial intelligence</strong> together. Instead of manually editing images or spending hours rendering new designs, you’ll learn how to build a tool that understands your intent through text, transforming design into an instant, interactive experience. By the end, you’ll have a <strong>working AI fashion design assistant</strong>, a deep understanding of <strong>SAM and DALL·E 2 integration</strong>, and practical experience deploying an <strong>AI-powered web app</strong> that turns imagination into visual reality.</div><div><br /></div><h1>What You'll Need</h1><div>To get the most out of this project, you should have:</div><ul><li>Basic Python programming skills.</li><li>Some familiarity with computer vision or generative AI concepts (helpful but not required).</li><li>Curiosity about how AI can revolutionize creative design workflows.</li></ul><div>All dependencies are pre-configured in the environment, and the project runs best on the latest versions of Chrome, Edge, Firefox, or Safari.</div>
</div>


Build a Fashion Design Web App with DALL-E, Gradio and SAM

Build an AI fashion assistant with CLIPSeg, SAM, and DALL·E 2 that lets users virtually try on, restyle, and redesign clothes through text prompts. Use CLIPSeg and SAM to detect and segment clothing items or accessories in any image, then integrate DALL·E 2 to inpaint and redesign those regions from simple text prompts. Experiment with new fabrics, styles, and colors, all generated intelligently and seamlessly. By the end, you’ll have created a shareable web app that empowers anyone to visualize and prototype fashion ideas instantly through the power of computer vision and generative AI.

<div class="trix-content">
  <div class="trix-content">
  <div>Ready to put your ethical hacking skills to the test and power your cybersecurity career forward?<br /><br />After completing this capstone project, you will be able to:</div><ul><li>Demonstrate advanced ethical hacking and defensive cybersecurity skills through realistic Red Team and Blue Team exercises.</li><li>Conduct reconnaissance, exploitation, privilege escalation, and persistence techniques using professional penetration testing tools like Metasploit and Kali Linux.</li><li>Analyze system vulnerabilities, logs, and Indicators of Compromise to detect and respond to simulated attacks.</li><li>Integrate OpenVAS and the MITRE ATT&amp;CK framework to evaluate and improve security posture in defensive operations.</li><li>Apply generative AI tools to enhance reconnaissance, exploit development, and anomaly detection in cybersecurity workflows.</li><li>Produce a professional-grade incident response report, documenting findings, mitigations, and lessons learned from simulated attacks.</li></ul><div>This hands-on capstone course is designed for cybersecurity analysts, ethical hackers, and IT professionals who want to showcase their real-world expertise in offensive and defensive security operations.<br /><br /></div><div>You’ll begin on the Red Team, using industry-standard tools like Kali Linux, Nmap, and Metasploit to conduct reconnaissance, exploitation, privilege escalation, and persistence. After that, you’ll switch to the Blue Team, performing log analysis, detecting Indicators of Compromise (IOCs), and executing defensive responses using OpenVAS and the MITRE ATT&amp;CK framework.<br /><br /></div><div>You’ll also explore the transformative role of Generative AI in cybersecurity, applying AI-assisted reconnaissance, exploit generation, and anomaly detection to enhance both offensive and defensive strategies.<br /><br /></div><div>Each lab challenges you to prove your mastery through practical exercises, culminating in a final project that demonstrates your ability to investigate, defend, and report on simulated cybersecurity incidents.<br /><br /></div><div>If you’re ready to validate your cybersecurity and ethical hacking skills with a portfolio-ready capstone project, enroll today!<br /><br /></div><div><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>The following skills are required to be successful with this course: </div><ul><li>We recommend completing all previous courses in the <strong>IBM Ethical Hacking with OS Tools Professional Certificate</strong> before starting this capstone.</li></ul><div><br /></div><h1>Course Syllabus</h1><div><strong>Module 1: Initial Access </strong></div><ul><li>Lesson 0: Welcome</li><li>Lesson 1: Network Reconnaissance and Exploitation </li><li>Lesson 2: Initial Access: Checklist and Graded Quiz</li></ul><div><strong>Module 2: Privilege Escalation </strong></div><ul><li>Lesson 1: Privilege Escalation and Post-Exploitation Techniques</li><li>Lesson 2: Privilege Escalation: Checklist and Graded Quiz </li></ul><div><strong>Module 3: Persistence Techniques </strong></div><ul><li>Lesson 1: Persistence Techniques and Evasion </li><li>Lesson 2: Persistence Techniques: Checklist and Graded Quiz</li></ul><div><strong>Module 4: Detection and Response </strong></div><ul><li>Lesson 1: Threat Detection and Response</li><li>Lesson 2: Detection and Response: Checklist and Graded Quiz</li></ul><div><strong>Module 5: Generative AI in Cybersecurity </strong></div><ul><li>Lesson 1: Generative AI in Offensive Cybersecurity</li><li>Lesson 2: Generative AI in Defensive Cybersecurity</li><li>Lesson 3: Checklist and Graded Quiz</li></ul><div><strong>Module 6: Reporting, Recovery, Final Project, and Course Wrap-Up </strong></div><ul><li>Lesson 1: Writing, Compiling, and Submitting Your Incident Report </li><li>Lesson 2: Final Assessment</li><li>Lesson 3: Course Wrap-Up</li></ul>
</div>
</div>


Capstone Project: Ethical Hacking with Gen AI

Master red and blue team cybersecurity skills with hands-on labs in ethical hacking, defense, and AI-assisted threat detection. Simulate real-world cyberattacks and responses to boost your career in just 6 weeks.

<div class="trix-content">
  <div class="trix-content">
  <div>Build job-ready cybersecurity skills through practical experience in vulnerability assessment and incident response using OpenVAS.<br /><br />After completing this course, you will be able to:</div><ul><li>Install and configure OpenVAS in a Linux environment, setting up scan targets and running initial vulnerability assessments.</li><li>Interpret and analyze OpenVAS scan results, applying CVSS scoring to assess and prioritize vulnerabilities.</li><li>Evaluate risks based on asset value, exploitability, and impact to develop effective remediation plans.</li><li>Detect and contain active threats by correlating system logs, indicators of compromise, and OpenVAS results.</li><li>Produce structured, professional post-incident reports integrating threat intelligence and policy recommendations.</li><li>Simulate a complete incident response lifecycle using OpenVAS, from detection and containment to remediation and reporting.</li></ul><div>Designed for cybersecurity professionals and aspiring ethical hackers, this 4-week course immerses you in realistic scenarios where you’ll install and configure OpenVAS, run vulnerability scans, interpret CVSS scores, and identify security gaps across networked systems.<br /><br /></div><div>You’ll analyze system and network logs, correlate scan results with attack frameworks like MITRE ATT&amp;CK, and apply containment strategies to mitigate active threats. Moving beyond detection, you’ll learn to prioritize risks, plan effective remediation, and document findings in structured, evidence-based reports.<br /><br /></div><div>The course concludes with a full incident response simulation where you’ll apply OpenVAS to detect, contain, and remediate an attack scenario while producing a professional-grade incident report.<br /><br /></div><div>Through guided labs, assignments, and a final project, you’ll gain real-world skills that strengthens your cybersecurity portfolio and prepares you for roles in vulnerability management and incident response.<br /><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>Working knowledge of networking, operating systems (especially Linux), and cybersecurity concepts is helpful, but you don’t need to be an expert to get started.<br /><br /></div><h1>Course Syllabus</h1><div><strong>Module 1: Installation and Configuration of OpenVAS</strong></div><ul><li>Module Summary and Learning Objectives</li><li>Understanding Vulnerability Assessment and its Role in Defense </li><li>What is OpenVAS and How Does it Work</li><li>GVM Core Concepts and Terminology</li><li>OpenVAS Architecture and Components</li><li>Comparison: OpenVAS vs Nessus vs Qualys</li><li>Step-by-Step OpenVAS Setup Explained</li><li>Feed Synchronization, GVM Services and Startup Logic</li><li>Navigating the OpenVAS Dashboard: A Guided Tour</li><li>GVM Overview</li><li>Configuring Scan Targets and Credentials in OpenVAS</li><li>Understanding GVM Daemon Dependencies</li></ul><div><strong>Module 2: Vulnerability Analysis and Remediation Planning</strong></div><ul><li>Module Summary and Learning Objectives</li><li>Anatomy of an OpenVAS Report: Key Metrics and Tags</li><li>Common Vulnerabilities Identified by OpenVAS</li><li>CVSS in Practice: Interpreting Real-World Scores</li><li>CVSS Scoring Explained</li><li>Vulnerability Lifecycle Management</li><li>Ranking Risk: Asset Context, CVSS, and Exploitability</li><li>Patching vs Mitigation: Choosing the Right Response</li><li>Mitigation Planning for Enterprise Environments</li><li>Using Asset Value and Threat Intelligence to Prioritize Fixes</li></ul><div><strong>Module 3: Threat Detection and Incident Containment</strong></div><ul><li>Module Summary and Learning Objectives</li><li>How Vulnerability Data Supports Threat Hunting</li><li>OpenVAS Alerts and Real-Time Threat Intelligence</li><li>Correlating Logs and Scans to Identify Anomalies</li><li>Network Behavior and Anomalies</li><li>Mapping Scan Results to MITRE ATT&amp;CK Tactics</li><li>Containment Strategies</li><li>Response Strategy: When and How to Isolate a Host  </li><li>When to Disconnect or Reimage a Host</li><li>Key Tools and Techniques for Threat Containment </li></ul><div><strong>Module 4: Post-Incident Analysis, Final Project, Final Exam, and Course Wrap-Up</strong></div><ul><li>Module Summary and Learning Objectives</li><li>Writing and Structuring a Post-Incident Report</li><li>Integrating Threat Intelligence into After-Action Reports</li><li>Turning Lessons Learned into Policy Improvements</li><li>Best Practices for Report Writing</li><li>Final Project </li><li>Final Graded Quiz</li><li>Course Wrap-Up and Next Steps </li></ul>
</div>
</div>


OpenVAS for Vulnerability Assessment and Incident Response

Learn OpenVAS for vulnerability assessment and incident response. Install, configure, and use OpenVAS to detect, prioritize, and remediate cybersecurity threats in real-world simulations.

<div class="trix-content">
  <div>Metasploit is one of the most widely used cybersecurity frameworks for ethical hacking and penetration testing. This course builds your job-ready skills in exploitation techniques and attack simulation using Metasploit—skills employers actively seek.<br /><br />After completing this course, you will be able to:</div><ul><li>Explain the structure, components, and functionalities of the Metasploit Framework and its role in penetration testing.</li><li>Configure and operate Metasploit to perform reconnaissance, exploitation, and post-exploitation tasks in controlled environments.</li><li>Develop and modify exploits using auxiliary modules and fuzzing techniques to identify vulnerabilities in systems and applications.</li><li>Simulate real-world attack scenarios, including privilege escalation, persistence, and social engineering tactics.</li><li>Analyze and document penetration test results to produce actionable security recommendations and mitigation strategies.</li><li>Integrate Metasploit into ethical hacking workflows to enhance red teaming and vulnerability assessment processes.</li></ul><div>You’ll start by learning how to install and configure the Metasploit Framework, exploring its architecture, payloads, and session management. You’ll then simulate exploits and apply auxiliary modules to identify vulnerabilities, modify attacks, and perform fuzz testing. <br /><br /></div><div>You will move into advanced post-exploitation techniques, including privilege escalation, persistence, and evasion tactics. The course concludes with a simulated penetration test where you’ll apply your skills to conduct a full assessment and generate a professional report.<br /><br /></div><div>By the end of this course, you’ll be able to execute sophisticated exploits, automate penetration testing workflows, and understand how attackers compromise systems, preparing you to strengthen defenses and pursue advanced cybersecurity roles.<br /><br /></div><div>If you want hands-on penetration testing experience you can showcase on your resume, enroll today!</div><div><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>Working knowledge of networking, operating systems (especially Linux), and cybersecurity concepts is helpful, but you don’t need to be an expert to get started. <br /><br /></div><h1>Course Syllabus</h1><div><strong>Welcome to this course</strong></div><ul><li>Welcome</li></ul><div><strong>Module 1: Metasploit Setup and Core Exploitation Techniques </strong></div><ul><li>Module Summary and Learning Objectives</li><li>Introduction to Metasploit and Exploitation Basics</li><li>Exploring the Metasploit Framework</li><li>Glossary, Cheat Sheet, and Graded Quiz </li></ul><div><strong>Module 2: Exploit Development and Auxiliary Module Usage</strong></div><ul><li>Module Summary and Learning Objectives</li><li>Exploring the Metasploit Auxiliary Modules</li><li>Exploit Development and Advanced Techniques</li><li>Glossary, Cheat Sheet, and Graded Quiz </li></ul><div><strong>Module 3: Post-Exploitation and Attack Simulations </strong></div><ul><li>Module Summary and Learning Objectives</li><li>Privilege Escalation and Maintaining Access </li><li>Persistence and Evasion</li><li>Simulated Network Attacks</li><li>Glossary, Cheat Sheet, and Graded Quiz </li></ul><div><strong>Module 4: Web and Social Engineering Attacks </strong></div><ul><li>Module Summary and Learning Objectives</li><li>Web Application Exploitation </li><li>Phishing and Credential Harvesting </li><li>USB and Physical Social Engineering Attacks </li><li>Glossary, Cheat Sheet, and Graded Quiz </li></ul><div><strong>Module 5: Final Project: Simulated Penetration Test Using Metasploit</strong></div><ul><li>Final Project </li><li>Course Wrap-Up</li></ul><div><br /></div><div><br /></div>
</div>


Metasploit for Exploitation and Pen Testing

Learn Metasploit for ethical hacking and penetration testing. Gain hands-on skills in exploitation, post-exploitation, and attack simulations to identify and defend against cybersecurity threats in just a few hours.

<div class="trix-content">
  <div>Kali Linux is the go-to operating system for ethical hackers, penetration testers, and cybersecurity professionals. This course combines practical hands-on learning with foundational knowledge to help you confidently use Kali Linux for security testing.<br /><br />After completing this module, you will be able to:</div><ul><li>Apply job-ready skills to perform ethical hacking and penetration testing using Kali Linux tools.</li><li>Configure and install Kali Linux in virtualized environments for secure and efficient testing setups.</li><li>Utilize Kali Linux tools to investigate, analyze, and exploit vulnerabilities in simulated environments.</li><li>Develop Python and Bash scripts to automate system maintenance, security, and penetration workflows.</li><li>Customize and optimize Kali Linux tools to enhance performance and adapt them to specific security needs.</li><li>Integrate scripting, automation, and tool configuration to design efficient solutions for real-world cybersecurity challenges.</li></ul><div><br />You’ll begin by setting up and configuring Kali Linux, securing your environment, and exploring its architecture. You’ll dive into powerful cybersecurity tools for reconnaissance, forensics, and exploitation, gaining hands-on experience in real-world testing scenarios. <br /><br /></div><div>Then you will learn automation using Bash and Python scripting, customizing and streamlining tasks to enhance efficiency and precision. Finally, you’ll apply your skills in a project that challenges you to automate a security workflow and demonstrate your mastery of Kali Linux.<br /><br /></div><div>If you’re ready to elevate your cybersecurity career with the power of Kali Linux, enroll today!</div><div><br /></div><div><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>The following skills are required to be successful with this course: </div><ul><li> Foundational cybersecurity knowledge.</li></ul><div><br /></div><h1>Course Syllabus</h1><div><strong>Module 1: Overview of Kali Linux</strong></div><ul><li>Exploring Kali Linux</li><li>Hardening Kali Linux</li></ul><div><strong>Module 2: Kali Linux Tools</strong></div><ul><li>Kali Linux Tools for Investigation</li><li>Kali Linux Tools for Exploitation and Penetration Testing</li></ul><div><strong>Module 3: Scripting and Automation</strong></div><ul><li>Scripting with Python</li><li>Scripting with Bash</li></ul><div><strong>Module 4: Final Project and Course Wrap-Up</strong></div><ul><li>Final Project</li><li>Course Wrap-Up</li></ul><div><strong>Module 5 (Optional): Linux Overview</strong></div><ul><li>Linux Operating System</li><li>Navigating the Linux Operating System</li></ul><h1><br /></h1>
</div>


Kali Linux for Ethical Hacking

Learn Kali Linux for ethical hacking and cybersecurity. Master installation, configuration, scripting, and automation with Kali Linux tools for penetration testing and vulnerability assessment in just a few hours.

<div>Get ready to build the generative AI (GenAI) skills employers need and future-proof your UI/UX career!&nbsp;<br><br></div><div>Recruiters are actively looking for design professionals who can combine creativity and expert design thinking with AI fluency. This IBM specialization gives you the practical skills and understanding you need to work with popular AI tools confidently and enhance every stage of the UI and UX design process.&nbsp; From ideation to prototyping and delivering innovative user experiences, you can leverage GenAI to work faster and smarter.&nbsp;<br><br></div><div>During this specialization, you will:&nbsp;</div><ul><li>Build the job-ready skills to design innovative UI/UX solutions, and create dynamic, personalized user experiences and interfaces (UX UI), powered by GenAI&nbsp;</li><li>Master the fundamentals of generative AI and explore real-world applications across text, images, audio, video, design, and data&nbsp;</li><li>Apply prompt engineering techniques to craft precise prompts and generate creative, usable design outputs&nbsp;</li><li>Learn to use a variety of AI tools, including ChatGPT, Google Gemini, IBM WatsonX, Miro, Figma, Uizard, Visily, and UXPilot, for faster ideation, automated prototyping, design personalization, and streamlined user testing&nbsp;</li></ul><div>&nbsp;</div><div><strong>Program overview</strong>&nbsp;</div><div>During this program, you’ll learn how to use generative AI to ideate faster, automate repetitive design tasks, and produce innovative, user-centered solutions. Through guided projects and real-world design challenges, you’ll explore how AI can assist in user research, journey mapping, prototyping, and usability testing. Plus, you’ll gain valuable hands-on experience using leading tools such as ChatGPT, Google Gemini, IBM WatsonX, Miro, Figma, Uizard, Visily, and UXPilot to generate ideas, create design assets, and evaluate user feedback effectively.&nbsp;</div><div>&nbsp;</div><div>As you progress, you’ll also gain experience in prompt engineering, multimodal design generation, and conversational UX. And you’ll learn how to apply human-centered design principles to ensure that AI-powered interfaces remain accessible, ethical, and inclusive.&nbsp;</div><div>&nbsp;</div><div>The program then culminates in a project where you’ll apply your new skills to design a complete, AI-enhanced user experience, demonstrating your ability to merge design creativity with emerging technologies. By the end, you will have the skills to bring generative AI into your UI/UX design workflow, create dynamic and adaptive interfaces, and stay ahead in the evolving world of digital product design.&nbsp;</div><div>&nbsp;</div><div><strong>Job outlook</strong>&nbsp;</div><div>The demand for UI/UX professionals who can integrate generative AI into design and creative processes is rapidly increasing across industries. Organizations are seeking designers and innovators who can use AI tools to improve efficiency, personalization, and user engagement.&nbsp;</div><ul><li>&nbsp;</li><li>LinkedIn’s Global Talent Report identifies AI fluency and UX design among the top in-demand skills for digital professionals worldwide.&nbsp;</li><li>Glassdoor reports that UI and UX designers in the United States earn an average annual salary of over $90,000, with rising demand for professionals skilled in AI-powered design tools and workflows.&nbsp;</li></ul><div><br><strong>Prerequisites</strong>&nbsp;</div><div>This specialization is ideal for professionals who already have basic UI/UX knowledge and design tool skills. No AI experience needed, and it is suited to diverse backgrounds.&nbsp;</div>

Generative AI for UI/UX Design Specialization 

Future-proof your UI/UX career with GenAI skills that power human-centered, data-driven UI/UX experiences. Plus, get hands-on experience using popular AI tools and techniques. 

<div>Ready to build the hands-on skills that turn ideas into intuitive, accessible, and visually engaging experiences? Want to become the go-to UI/UX designer businesses are looking for?&nbsp;</div><div>This beginner-friendly IBM Professional Certificate is specifically designed for aspiring designers, career changers, and existing creative professionals who want to build the complete set of UI/UX skills to research, design, and prototype user-centred digital experiences. No prior experience required.&nbsp;</div><div>&nbsp;</div><div>After completing this Professional Certificate, you will be able to:&nbsp;</div><ul><li>Conduct user research and design paper prototypes, wireframes, and interactive mockups using Figma&nbsp;</li><li>Design adaptive and responsive layouts for mobile, tablet, and desktop screens that deliver seamless user experiences&nbsp;</li><li>Apply usability testing, design thinking, and microinteraction techniques to enhance accessibility and engagement&nbsp;</li><li>Build a professional design portfolio that showcases your ability to create user-focused digital products&nbsp;</li></ul><div>&nbsp;</div><div><strong>Program overview</strong>&nbsp;</div><div>&nbsp;</div><div>UI/ UX designers play a critical role in shaping how people experience technology. They combine creativity, research, and technical understanding to make digital products simple, effective, and enjoyable to use. &nbsp;</div><div>During this program, you’ll explore every step of the design process, including user research, journey mapping, wireframing, and usability testing. You’ll gain practical experience designing paper prototypes, interactive mockups, and high-fidelity prototypes in Figma. Plus, you’ll learn how to design adaptive layouts that look and feel consistent across different screen types.&nbsp;</div><div>&nbsp;</div><div>As you learn, you’ll get hands-on in projects and realistic design challenges that mirror what professionals do in the workplace. You’ll create user personas, test design ideas, and refine your interfaces based on user feedback. You’ll also master topics such as accessibility, information architecture, and interaction design, learning how to use microinteractions to make designs more intuitive and engaging.&nbsp;</div><div>&nbsp;</div><div>You will work through a comprehensive capstone project that ties all your skills together. In this project, you’ll design a complete, user-centered experience from concept to prototype and compile your work into a professional portfolio. &nbsp;</div><div>&nbsp;</div><div>If you’re keen to earn an IBM Professional Certificate that confirms your job-ready UI/UX skills, enhances your resume, and demonstrates your practical readiness for roles such as UX Designer, UI Designer, Product Designer, or Interaction Designer, enroll today! <br><br><strong>Job outlook</strong>&nbsp;</div><div>Professionals with UI and UX design skills are in high demand around the world:&nbsp;</div><ul><li>Employment for web and digital interface designers is expected to grow 7% till 2034 (U.S. Bureau of Labor Statistics)&nbsp;</li><li>The global UX services market is forecast to grow to 54.9 billion dollars by 2032 (Fortune Business Insights)&nbsp;</li><li>More than 100,000 open positions worldwide list UI or UX design as a key skill across industries, including technology, e-commerce, healthcare, and finance (LinkedIn Jobs)&nbsp;</li></ul><div><br><strong>Prerequisites</strong>&nbsp;</div><div>This is a beginner-level program designed for anyone interested in starting or advancing a career in design. No previous experience in design, coding, or software tools is required. Curiosity, creativity, and a willingness to learn are the only prerequisites.&nbsp;</div>

IBM UI/UX Designer Professional Certificate 

Master the UX/UI skills businesses need to design engaging, functional, and accessible digital designs that help them stand out and grow in today’s competitive world. 

<div class="trix-content">
  <div>Creating beautiful poetry no longer needs to be daunting. This AI Poetry Studio is a <strong>multilingual</strong>, <strong>multi-agent</strong> system that transforms your poem’s theme and preferences into a fully crafted, polished piece—<strong>in any language you choose</strong>.</div><div>The journey begins with a single input from you: the theme of your poem, plus optional details like language, poetic form, and tone. From there, a team of specialized AI agents takes over, each with a distinct role in the creative process:</div><ul><li><strong>Author Agent</strong> captures your theme and preferences in one clear brief to kick off the session.</li><li><strong>Muse Agent</strong> proposes three distinct poetic directions—titles, moods, and concepts—and selects the strongest one to pursue.</li><li><strong>Verse Agent</strong> develops the selected idea into a complete poem with crisp line breaks and imagery tailored to your style.</li><li><strong>Editor Agent</strong> lightly polishes for rhythm and clarity while preserving meaning, then signals completion with POEM_COMPLETE.</li></ul><div>Working together via the AutoGen framework and powered by the GPT-5 nano model, these AI agents collaboratively create poetry that is <strong>well-structured and elegant</strong>, delivered in your chosen language. By the end of the session, you receive a beautifully finished poem that showcases the seamless orchestration of multiple intelligent agents blending creativity with precision.</div><div><br />This system empowers you to co-create original poetry with AI, experiencing the harmony between your input and advanced multi-agent workflows.<br /><br /></div><h1>Who Should Enroll</h1><ul><li>Developers, data scientists, and AI enthusiasts interested in building creative applications with multi-agent systems</li><li>Writers, educators, and poetry lovers curious about how AI can assist in narrative generation and content design</li><li>Learners eager to explore practical applications of <strong>AutoGen (AG2) &amp;</strong> <strong>OpenAI’s GPT-5 </strong>in collaborative creative workflows.</li></ul><div><br /></div><h1>A Look at the Project Ahead</h1><div>After completing this guided project, you will be able to do:</div><ul><li><strong>Understand AutoGen’s multi-agent architecture</strong> – Learn how to design and coordinate specialized agents to simulate a real-world poetry creation workflow.</li><li><strong>Build intelligent writing agents</strong> – Create agents with defined roles such as Muse Generator, Verse Crafter, and Poetry Editor to handle different stages of poetic composition.</li><li><strong>Orchestrate collaborative book creation</strong> – Combine individual agent contributions to generate cohesive poems with consistent rhythm, tone, and literary quality.</li><li><strong>Learn to build and run agent workflows with AutoGen</strong> – Use Python and AutoGen to define agents, manage communication, and streamline task execution.</li><li><strong>Deliver personalized poetic experiences</strong> – Produce customized poems based on user inputs like theme, mood, or phrase.</li></ul><h1>What You'll Need</h1><div><strong>Technical Requirements:</strong> A basic understanding of Python programming. Experience with AI or LLMs is helpful but not required.</div><div><strong>Browser Setup:</strong> A modern web browser to access CrewAI tools, follow the guided environment, and run your code.</div>
</div>


Multilingual AI Agents for Poetry using GPT-5 & AutoGen/AG2

Learn how to use AutoGen’s multi-agent framework with GPT-5 to collaboratively generate and refine poetry. The agents are multilingual—generate poems in any language you choose. You provide the theme (plus optional form and tone); a Muse proposes and selects the concept, a Verse Crafter writes the poem, and a Poetry Editor lightly polishes and signals POEM_COMPLETE. A simple, guided flow that shows how GPT-5 + AutoGen turn your idea into a finished poem—without the heavy technical setup. Learn AutoGen's multi-agent architecture by taking this hands-on project now!

<div class="trix-content">
  <div>Choosing the perfect outfit can often feel overwhelming—but not anymore. AutoGen Wardrobe Wizard is a multi-agent AI system designed to help you effortlessly plan stylish looks tailored to your wardrobe, personal style, and the occasion.</div><div><br />The process begins with <strong>Meta's Llama vision model</strong>, which analyses your uploaded photo and extracts clothing items to build a digital wardrobe—laying the groundwork for personalised recommendations.</div><div>Powered by <strong>Microsoft’s AutoGen</strong> framework, the system brings together a team of specialised AI agents that function like your own virtual styling team:</div><ul><li><strong>Color Analyst</strong> picks colors that complement your skin tone</li><li><strong>Style Planner</strong> recommends outfit types based on your preferences and the occasion</li><li><strong>Silhouette Analyst</strong> suggests flattering cuts and designs</li><li><strong>Outfit Board Creator</strong> assembles everything into a cohesive final look</li></ul><div>To complete the experience, <strong>OpenAI’s DALL·E</strong> generates a photorealistic outfit board, presenting your styled ensemble in a magazine-inspired flat lay.</div><div><br />By the end of this project, you'll have created a smart fashion assistant that combines visual recognition, collaborative AI, and creative design. It's a fun, real-world example of how multi-agent systems can solve everyday problems—with intelligence and style.</div><div><br /></div><h1>A Look at the Project Ahead</h1><div>After completing this guided project, you will be able to do:</div><ul><li><strong>Understand AutoGen’s multi-agent architecture</strong> – Learn how to define and coordinate specialized agents to simulate real-world fashion consulting workflows.</li><li><strong>Build intelligent fashion agents</strong> – Create agents with defined roles such as color analysis, style planning, and style advising.</li><li><strong>Orchestrate collaborative outfit generation</strong> – Combine individual agent insights to produce a cohesive final outfit recommendation.</li><li><strong>Learn to build and run agent workflows with AutoGen</strong> – Use Python and AutoGen to define agents, manage communication, and control task execution.</li><li><strong>Generate visual outputs with DALL·E </strong>– Transform final outfit descriptions into AI-generated fashion boards using prompt-based image generation.</li><li><strong>Deliver personalized styling experiences </strong>– Generate tailored fashion suggestions based on user profile inputs like skin tone, occasion, and preferences.</li></ul><h1>What You'll Need</h1><div><strong>Technical Requirements:</strong> A basic understanding of Python programming. Familiarity with AI agents or large language models (LLMs) is helpful but not mandatory.</div><div><strong>Browser Setup:</strong> A modern web browser to access the AutoGen tools, follow the guided project environment, and run your code seamlessly.</div>
</div>


AutoGen Wardrobe Wizard: A MultiAgent Fashion System

Learn how to combine Meta's Llama vision model, OpenAI’s DALL·E, and Microsoft’s AutoGen, a framework for orchestrating collaborative AI agents, to build an AI-powered virtual fashion stylist. This project uses modular agents such as a Color Analyst, Style Planner, Silhouette Analyst, and Outfit Board Creator to generate personalised outfit recommendations based on your uploaded photos. By the end, you’ll have a complete multi-agent system that blends computer vision, intelligent coordination, and creative design for real-world fashion use.

<div class="trix-content">
  <div>AI agents are transforming how we interact with technology, automating tasks that once took hours into just a few clicks. By learning to build a Model Context Protocol (MCP) server and a LangGraph agent, you’ll gain hands-on experience in connecting AI models to real-world tools. This project is especially exciting because it shows how AI can manage everyday tasks, like email, using natural language—making technology smarter and more accessible. Completing this project will give you practical skills that can be applied to productivity tools, automation workflows, and modern AI applications.</div><div><br /><br /></div><h1>A Look at the Project Ahead</h1><div><strong>In this guided project, you will:</strong></div><ul><li>Build a <strong>Model Context Protocol (MCP) server</strong> to provide AI agents with structured access to tools and resources.</li><li>Develop a <strong>LangGraph ReAct agent</strong> that can send, search, and reply to Gmail messages using natural language commands.</li><li>Create a <strong>ReactJS frontend</strong> and <strong>Express backend</strong> to handle UI interactions and server communication.</li><li>Integrate <strong>Gmail OAuth authentication</strong> to securely manage user emails.</li></ul><div><strong>By the end of this lab you'll:</strong></div><ul><li>Understand what MCP server's are, how they work, and their typical use cases.</li><li>Build an AI agent that interact with external tools through MCP servers.</li><li>Design intelligent workflows using LangGraph agents.</li><li>Implement practical AI-powered automation in a web application.</li></ul><div><br /></div><h1>What You'll Need</h1><div><strong>Before starting this project, you should have</strong>:</div><ul><li>An interest in agentic AI and general understanding of how they work</li><li>A good understanding of how client-server HTTP interactions work</li><li>A good understanding of JavaScript and HTML/CSS in a web development context</li><li>Familiarity with the ReactJS framework and common hooks</li><li>Familiarity with Node environments and package management</li><li>A modern browser to run this CloudIDE environment (Chrome, Firefox, Safari, etc.)</li></ul>
</div>


Build an MCP Server and LangGraph.js Agent to manage Gmail

Build a Model Context Protocol (MCP) server to enable smart Gmail actions in a LangGraph agent. This intermediate level project guides you through creating a smart email management system using OpenAI's GPT models and Anthropic's MCP. You’ll implement Gmail OAuth, design a React user interface with an Express backend, and build an agent that can manage emails with natural language prompts. By the end of the project, you'll be proficient with the MCP SDK and understand it's many practical use cases. Enroll now to learn this cutting-edge technology used across countless industries.

<div class="trix-content">
  <div>Have you ever struggled to decide where to eat? With countless options and ever-changing food trends, choosing a restaurant can be overwhelming. In this project, you’ll build an <strong>AI-powered restaurant recommender system</strong> that goes far beyond simple filtering by cuisine or price. By orchestrating multiple <strong>CrewAI agents</strong> and integrating <strong>Retrieval-Augmented Generation (RAG)</strong> with a <strong>WatsonX Slate embedding model</strong> and <strong>Chroma vector database</strong>, you’ll create an intelligent dining assistant that learns from user history, interprets dining photos, and adapts to real-time food trends. This system doesn’t just suggest popular spots—it builds a nuanced profile of the user’s tastes and recommends restaurants that fit their preferences, budget, and style of dining.<br /><br /></div><h1>What You’ll Learn</h1><div>By the end of this project, you will be able to:</div><ul><li><strong>Build a RAG-powered retriever for restaurants</strong>: Encode restaurant data with WatsonX Slate embeddings and store them in Chroma for efficient similarity search.</li><li><strong>Create and coordinate multi-agent systems with CrewAI</strong>: Define agents like the <strong>Profile Builder</strong>, <strong>Coarse RAG Recommender</strong>, <strong>Food Trend Analyst</strong>, and <strong>Recommendation Finalizer</strong> to work collaboratively.</li><li><strong>Analyze multimodal user data</strong>: Use vision-capable LLMs to extract insights from dining photos and integrate them with textual reviews.</li><li><strong>Incorporate real-time web search</strong>: Use Serper to fetch trending cuisines and new restaurants, ensuring recommendations stay current.</li><li><strong>Deliver structured outputs with Pydantic</strong>: Standardize agent outputs for reliability and seamless downstream processing.</li><li><strong>Run and orchestrate an end-to-end pipeline</strong>: From user history to final ranked recommendations, you’ll deploy a fully functional AI restaurant recommender.</li><li><strong>Build a Gradio Web App for online chatbot!</strong></li></ul><div><br /></div><h1>Who Should Enroll</h1><ul><li><strong>Early-career data scientists and ML engineers</strong> who want hands-on experience building multi-agent systems.</li><li><strong>AI enthusiasts</strong> curious about CrewAI, RAG, and multimodal LLM applications.</li><li><strong>Students and researchers</strong> interested in applying cutting-edge AI to real-world recommendation challenges.</li><li><strong>Developers in food-tech or hospitality</strong> who want to explore AI-driven personalization.</li></ul><div><br /></div><h1>Why Enroll</h1><div>This project bridges <strong>recommender systems, multimodal AI, and agent orchestration</strong> to show how intelligent assistants can transform the way people discover restaurants. Instead of just listing top-rated spots, your system will <strong>understand the user’s preferences, stay updated with trends, and deliver personalized, trustworthy suggestions</strong>. By the end, you’ll have a working <strong>multi-agent CrewAI restaurant recommender</strong>, practical experience with <strong>RAG pipelines and multimodal LLMs</strong>, and insights into how AI can power the next generation of personalized dining experiences.</div><div><br /></div><h1>What You’ll Need</h1><div>To get the most out of this project, you should have:</div><ul><li>Basic Python programming knowledge.</li><li>Familiarity with LLM concepts and vector databases (helpful but not required).</li><li>(Optional) Sign up for a <strong>free</strong> Serper API account as a part of the project for real-time online search.</li><li>Interest in <strong>AI agents, recommender systems, and multimodal data</strong>.</li></ul><div>All dependencies are pre-configured in the environment, and the project runs best on current versions of Chrome, Edge, Firefox, or Safari.</div>
</div>


Multi-Agent Restaurant Chatbot with Vision LLM, CrewAI & RAG

Build your own multi-agent restaurant recommendation chatbot with Multimodal LLM, CrewAI, Chroma DB and RAG. Learn to orchestrate agents through YAML-defined configurations and Pydantic schemas to ensure structured, reliable outputs. Use IBM watsonx slate embeddings and a Chroma vector database to power restaurant retrieval. Integrate a Vision LLM to analyze dining photos and a Serper web tool to capture real-time food trends. Explore how CrewAI enables collaborative agent workflows that combine RAG retrieval and online trend analysis to create an adaptive, smart dining assistant.

<div class="trix-content">
  <div>Ready to leverage the power of generative AI (GenAI) to elevate your UI/UX design skills? This course equips designers and creative professionals with job-ready skills and hands-on experience integrating AI across every stage of the user experience workflow—from ideation and research to prototyping and conversational design. <br /><br /></div><div> </div><div> </div><div><strong><em>You will:</em></strong>  </div><ul><li>Design a portfolio-ready, AI-enhanced UX project that demonstrates your ability to integrate generative AI tools into modern design workflows. </li><li>Use UXPilot, Miro, Visily, Uizard, and Figma to streamline UX/UI processes and accelerate ideation, prototyping, and testing. </li><li>Leverage prompt-based AI to craft user personas, empathy maps, journey maps, and UX microcopy that reflect real user needs. </li><li>Transform design briefs and user stories into interactive prototypes and conversational interfaces that balance empathy, intent, and usability. </li></ul><div> </div><div><strong>Course overview</strong>  </div><div>During this course, you’ll explore leading tools such as UXPilot, Miro, Visily, Uizard, and Figma. You’ll learn how to use GenAI to streamline tasks such as generating personas and journey maps, crafting UX microcopy, and simulating chatbot interactions. And you’ll discover how to ensure that your designs are human-centered, inclusive, and accessible. </div><div> </div><div>Through guided labs, you’ll gain practical experience in AI-assisted wireframing, usability testing, and conversational UX design. And for your final project, you’ll design an AI-powered experience, apply prompt engineering techniques, and refine your solution through iterative feedback loops. </div><div> </div><div>If you’re keen to leverage GenAI as your collaborative design partner to work faster, smarter, and more creatively, enroll today! </div><div> </div><div> </div><div><strong>Prerequisites</strong> </div><div>This course is designed for aspiring and practicing UI/UX designers, product designers, researchers, and creative professionals interested in applying generative AI to their design work. A basic understanding of UI, UX, and generative AI concepts is recommended. Familiarity with design tools, prompts, and user research methods will help you maximize the benefits of the hands-on projects. </div><div> </div><div><strong>Related</strong><em> </em><strong>Professional Certificate</strong> </div><div>This course is part of the IBM UI/UX Designer Professional Certificate. If you’re looking to master UI/UX design and use generative AI to transform your design workflows, we recommend enrolling in the full program and completing the courses in sequence. In just a few months, you’ll build job-ready UX/UI skills, create a professional design portfolio, and stand out to employers in the growing field of digital design.   </div><div> </div><div><strong>Course syllabus</strong> </div><div>The course consists of the following modules </div><ul><li>Foundations of UI UX Design with Generative AI </li><li>AI-Powered UX Research and Analysis </li><li>AI-Driven Prototyping and Conversational UX </li><li>Final Project and Final Quiz </li></ul>
</div>


Generative AI Skills for UI/UX Design

Transform your UX/UI workflow with generative AI. Use tools such as Figma, Uizard & Miro to design AI-powered prototypes, chatbots & user experiences.

<div class="trix-content">
  <div>Ready to take your UI/UX design skills to the next level with Figma?  Figma has become an industry standard across companies of all sizes, and mastering it is essential for any UI/UX design career. This course gives you job-ready skills in wireframing, prototyping, and usability testing using Figma; essential skills for your resume! </div><div> </div><div><strong><em>You will:</em></strong>  </div><ul><li>Design a portfolio-ready, end-to-end UX project in Figma that showcases your ability to plan, structure, and deliver user-centered digital experiences. </li><li>Create low- to high-fidelity wireframes and interactive prototypes using grids, components, and advanced layout techniques aligned with industry workflows. </li><li>Conduct usability testing and apply Gestalt principles, responsive design, and accessibility standards to refine and optimize cross-device user experiences. </li><li>Learn to collaborate effectively in Figma using shared libraries, version control, and design systems to maintain consistency and efficiency in team-based projects. </li></ul><div> </div><div><strong>Course overview</strong> </div><div> </div><div> </div><div>During this course, you’ll get hands-on designing user flows, structured wireframes, and interactive prototypes, including those with gesture-based interfaces. </div><div> </div><div>You’ll apply Gestalt principles to create strong visual hierarchy, organize content through effective information architecture, and adopt a mobile-first design approach. Plus, through real-world challenges and usability testing, you’ll refine your designs based on feedback and learn to solve UX problems with confidence and clarity. </div><div> </div><div>In a final project, you’ll then create a high-fidelity prototype and your own reusable design system; great experience to chat about in interviews!  </div><div>Enroll today and build Figma skills in wireframing and prototyping that can power your UI/UX career forward.  </div><div><strong>Prerequisites</strong> </div><div>This course is designed for beginners or experienced professionals looking to transition into or deepen their expertise in UI/UX design. Learners are expected to have a basic understanding of UI/UX principles and design concepts. While no prior hands-on design experience is required, familiarity with fundamental design principles is recommended to make the most of the hands-on activities in this course. </div><div> </div><div><strong>Related</strong><em> </em><strong>Professional Certificate</strong> </div><div> </div><div>This course is part of the <strong>IBM UI/UX Designer Professional Certificate</strong>. If you’re looking to master UI/UX design, including using Figma, prototyping, and usability testing, we recommend enrolling in the full program and progressing through the courses in sequence. In just a few months, you’ll build job-ready UX/UI skills, create a professional design portfolio, and stand out to employers in the growing field of digital design. </div><div> </div><div><strong>Course syllabus</strong> </div><div>The course consists of the following modules: </div><ul><li>Wireframing Fundamentals with Figma </li><li>Prototyping and Usability Testing </li><li>UI Patterns and Design Systems </li><li>Interactive and Gesture-Based UI </li><li>Final Project and Final Exam </li></ul><div> </div>
</div>


UI/UX Design: Wireframing & Prototyping with Figma

Master Figma essentials for designing user-centered prototypes. Create structured wireframes, gesture-based interfaces, and Hi-Fi designs for your UI/UX portfolio.

<div class="trix-content">
  <div>The U.S. Bureau of Labor Statistics projects about 12-13% job growth for computer systems and network architects in the coming years. This course is your first step toward entering the field of IT systems architecture. <br /><br /></div><div>You’ll begin looking at systems and solutions architects’ roles, responsibilities, and skills, and exploring career paths with certifications to enhance your expertise. <br /><br />You'll then explore systems thinking, identify key system components, and learn how they interact within an organization. You'll also analyze business processes and apply the systems development life cycle (SDLC) to guide project planning. <br /><br />Next, you’ll analyze systems/software architecture and design principles to visualize system structure with tools like UML, apply object-oriented analysis, and grasp architectural patterns such as layered, client-server, and microservices. Plus, you’ll examine deployment models and production environments to learn how real-world systems are delivered.  <br /><br />You’ll work with tools like data flow diagrams (DFDs), entity-relationship diagrams (ERDs), and prototyping software to support documentation and stakeholder communication.  <br /><br />Through hands-on labs and a project, you'll start to design scalable, maintainable systems tailored to business needs.  <br /><br />Enroll today to kickstart your journey to becoming a successful systems or solutions architect!<br /><br /></div><h1><strong>What will you learn?</strong></h1><ul><li>Explore the exciting world of systems architecture and learn the fundamentals to design scalable, reliable system solutions </li><li>Explain the solutions architect’s role, required skills, career paths, certifications, and how they use systems thinking and SDLC to meet business needs </li><li>Gain hands-on experience by applying systems design fundamentals and tools to design IT systems and solutions</li><li>Utilize requirement-gathering, prototyping, and modeling tools to analyze business needs and develop documented solutions for real-world applications </li></ul><h1>Course Syllabus</h1><div>This course comprises the following four modules: <br /><br /></div><div><strong>Module 1: Introducing the Systems &amp; Solutions Architect Roles </strong></div><ul><li>Lesson 0: Welcome </li><li>Lesson 1: Getting Started with the Systems Architect Role </li><li>Lesson 2: Module Glossary and Assessment </li></ul><div><strong>Module 2: Introduction to Systems Analysis and Architecture </strong></div><ul><li>Lesson 1: What is a System? </li><li>Lesson 2: Understanding Systems and the Analyst's Role in Business </li><li>Lesson 3: Module Glossary and Assessment  </li></ul><div><strong>Module 3: Software Architecture, Design, and Patterns </strong></div><ul><li>Lesson 1: Software Architecture and Design </li><li>Lesson 2: Software Architecture Patterns and Deployment Technologies </li><li>Lesson 3: Module Glossary and Assessment </li></ul><div><strong>Module 4: Module 4: Tools Used by Systems Architects </strong></div><ul><li>Lesson 1: Tools Used by Systems Architects </li><li>Lesson 2: Applying Systems Architect Tools in Practice </li><li>Lesson 3: Module Glossary and Assessment </li></ul><div><strong>Module 5: Final Project, Final Quiz, and Course Wrap-Up </strong></div><ul><li>Lesson 1: Final Project </li><li>Lesson 2: Course Glossary, Final Quiz, and Wrap-Up </li></ul>
</div>


Introduction to Systems Architecture

This course offers a foundational introduction to systems architecture and the essential principles behind designing robust, scalable IT systems. Learners will explore the role of the systems architect, gaining insight into how they bridge business needs with technical solutions. Through a combination of videos, expert insights, and hands-on activities, the course covers core topics such as system components, system development life cycle (SDLC) models, software design, and architectural patterns.

<div class="trix-content">
  <div>Take on the role of a UI/UX designer and bring a real-world project to life in this hands-on capstone course. <br /><br /></div><div>You’ll apply the full design thinking process, from conducting user research to building high-fidelity, accessible interfaces. Create wireframes and interactive prototypes in Figma, design scalable systems, and prepare developer-ready handoffs. <br /><br /></div><div>By course completion, you’ll have a polished project demonstrating your ability to craft user flows, test and iterate designs, and apply industry-standard practices. You’ll also learn to present your work through a professional case study, build a compelling UX resume, and develop a portfolio ready for potential employers and clients. <br /><br /></div><div>This capstone focuses on designing an e-commerce platform from concept to final design, giving you practical experience and tangible work to showcase your skills. <br /><br /></div><div>Step into a design role, pitch your ideas confidently, and advance your design career with a portfolio that stands out—enroll now! </div><div><br /></div><h1>Learning Objectives</h1><div>• Take a real-world UX/UI project from research to polished high-fidelity designs using the full design thinking process. </div><div>• Plan, prototype, and test intuitive, user-focused interfaces with Figma and other industry-standard UX tools. </div><div>• Build scalable design systems and developer-ready handoffs that prioritize accessibility. </div><div>• Showcase your skills through a professional case study, portfolio, and UX-focused resume to impress potential employers. <br /><br /></div><h1>Course Syllabus</h1><div>Welcome to the Course </div><ul><li>Video: Course Introduction </li><li>Reading: Course Overview </li><li>Reading: Helpful Tips for Course Completion </li></ul><div> </div><div>Module 1: Getting Started with the Capstone Project </div><div>Module Summary and Learning Objectives </div><div>Lesson 1: Project Overview and Expectations </div><ul><li>Video: Project Overview </li><li>Reading: Capstone Project: Getting Started Guide </li><li>Reading: Capstone Tools and Workflow Checklist </li><li>Reading: Capstone Project Brief </li><li>Reading: Project Scoping Guide </li><li>Lab: Analyzing the Project Brief </li><li>Lab: Creating a Project Scope Summary </li></ul><div>Lesson 2: Module Summary and Assessments </div><ul><li>Reading: Summary and Highlights: Getting Started with the Capstone Project </li><li>Practice Quiz: Checklist: Project Overview and Expectations </li><li>Graded Quiz: Project Overview and Expectations </li></ul><div> </div><div>Module 2: Empathize and Define </div><div>Module Summary and Learning Objectives </div><div>Lesson 1: Conducting UX Research </div><ul><li>Reading: Competitive Analysis Tips and Templates </li><li>Lab: Performing Competitive Analysis </li><li>Reading: User Interview Planning Guide </li></ul><div>Lesson 2: Synthesizing Research </div><ul><li>Reading: Empathy Map and Persona Templates </li><li>Lab: Creating an Empathy Map </li><li>Lab: Developing a User Persona </li><li>Reading: Framing Problems and Identifying Opportunities </li><li>Lab: Writing a Problem Statement </li></ul><div>Lesson 3: Module Summary and Assessments </div><ul><li>Summary and Highlights: Empathize and Define </li><li>Practice Quiz: Checklist: Empathize and Define </li><li>Graded Quiz: Empathize and Define </li></ul><div> </div><div>Module 3: Ideate and Plan </div><div>Module Summary and Learning Objectives </div><div>Lesson 1: Structuring Ideas </div><ul><li>Reading: Best Practices for Sketches, Flowcharts, and Information Architecture </li><li>Lab: Creating Initial Sketches </li><li>Lab: Creating User and Task Flows </li><li>Lab: Create an Initial Sitemap </li></ul><div>Lesson 2: Planning Your Design  </div><ul><li>Reading: Key Feature Planning and Prioritization Matrix Guide </li><li>Lab: Identifying Key Versus Optional Features </li><li>Lab: Developing a Prioritization Matrix </li><li>Reading: Examples of Success Metrics </li><li>Lab: Defining Success Metrics   </li><li>Lab: Creating a Wireframe Planning Outline </li></ul><div>Lesson 3: Module Summary and Assessments </div><ul><li>Summary and Highlights: Ideate and Plan </li><li>Practice Quiz: Checklist: Ideate and Plan </li><li>Graded Quiz: Ideate and Plan </li></ul><div> </div><div>Module 4: Wireframing and Prototyping </div><div>Module Summary and Learning Objectives </div><div>Lesson 1: Building Wireframes </div><ul><li>Reading: Wireframe Guidelines and Layout Tips </li><li>Lab: Designing Wireframe Screens in Figma </li></ul><div>Lesson 2: Creating Interactive Prototypes </div><ul><li>Reading: Prototyping Guide: Links, Components, and States </li><li>Lab: Connecting Wireframes Screens </li><li>Lab: Adding Interactions Using Components and Variants </li></ul><div>Lesson 3: Module Summary and Assessments </div><ul><li>Summary and Highlights: Wireframing and Prototyping </li><li>Practice Quiz: Checklist: Wireframing and Prototyping </li><li>Graded Quiz: Wireframing and Prototyping </li></ul><div> </div><div>Module 5: Usability Testing and Iteration </div><div>Module Summary and Learning Objectives </div><div>Lesson 1: Testing Your Prototype </div><ul><li>Reading: Usability Test Planning Guide and Template </li><li>Lab: Conducting Usability Tests </li><li>Reading: Task Writing Template and Feedback Tips </li><li>Lab: Translating and Summarizing Feedback </li></ul><div>Lesson 2: Making Iterations </div><ul><li>Reading: Severity Rating Scale and Design Fix Guidelines </li><li>Lab: Prioritizing Feedback </li><li>Lab: Iterating and Updating a Prototype </li></ul><div>Lesson 3: Module Summary and Assessments </div><ul><li>Summary and Highlights: Usability Testing and Iteration </li><li>Practice Quiz: Checklist: Usability Testing and Iteration </li><li>Graded Quiz: Usability Testing and Iteration </li></ul><div> </div><div>Module 6: Final User Interface Design and Handoff  </div><div>Module Summary and Learning Objectives </div><div>Lesson 1: Creating a Design System and Hi-Fi User Interface </div><ul><li>Reading: Style Guide and UI Components Guides and Tips </li><li>Lab: Building a Style Guide and Component Library </li><li>Reading: High-Fidelity Mock-Ups Tips and Guides </li><li>Lab: Designing High-Fidelity Mock-Ups </li></ul><div>Lesson 2: Developer Handoff  </div><ul><li>Reading: Handoff Preparation Guide </li><li>Lab: Preparing for Developer Handoff </li></ul><div>Lesson 3: Module Summary and Assessments </div><ul><li>Summary and Highlights: Final UI Design and Handoff </li><li>Practice Quiz: Checklist: Final User Interface Design and Handoff </li><li>Graded Quiz:  Final User Interface Design and Handoff </li></ul><div>Lesson 4: Project Submission and Evaluation </div><ul><li>Reading: Preparing Your Project Submission </li><li>Final Project: Part I - Submission and Evaluation </li><li>Final Project: Part II - Submission and Evaluation </li></ul><div> </div><div>Module 7: [Bonus] Launch Your UI/UX Career and Course Wrap-up </div><div>Module Summary and Learning Objectives </div><div>Lesson 1: Building Your Resume and Portfolio </div><ul><li>Video: Resume Writing Guide </li><li>Lab: Drafting a UI/UX Resume </li><li>Video: Writing and Building a Portfolio: Case Study Tips </li><li>Lab: Drafting a Case Study Summary Based on the Capstone Project </li><li>Lab: Building a Case Study </li></ul><div>Lesson 2: Exploring Career Paths and Interview Preparation </div><ul><li>Video: Freelancing and Job Search Guide </li><li>Lab: Writing a Freelance and Job-Ready Profile </li><li>Video: Common UI/UX Interview Questions and Tips </li></ul><div>Lesson 3: Module Summary </div><ul><li>Summary and Highlights: Launch Your UI/UX Career </li><li>Practice Quiz: Checklist: Launch Your UI/UX Career </li></ul><div>Lesson 4: Course Wrap-Up </div><ul><li>Reading: Congratulations and Next Steps </li><li>Reading: Team and Acknowledgments </li><li>Feedback Form </li></ul><div><br /></div><h1>General Information</h1><div>This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer or Safari. </div><div><br /></div><h1>Recommended Skills Prior to Taking this Course</h1><div>The following skills are required to be successful with this course:  </div><ul><li>We recommend completing all previous courses in the IBM UI/UX Designer Professional Certificate before starting this capstone. </li></ul>
</div>


UI/UX Design: Capstone Project

Step into a UI/UX designer role and complete a hands-on capstone project. Apply the full design thinking process, create prototypes in Figma, and build a portfolio-ready showcase for an e-commerce platform. 

<div>Prepare for a career in the high-demand field of digital marketing with the IBM Digital Marketing and Growth Hacking Professional Certificate. This program equips you with the most up-to-date skills and tools needed to succeed as a digital marketer or growth hacker, with no prior experience required.<br><br>In this Professional Certificate, you will:&nbsp;</div><ul><li>Master practical, up-to-date skills in digital marketing, SEO, content marketing, paid advertising, and social media.</li><li>Apply growth hacking techniques to design, test, and optimize multi-channel campaigns for maximum reach and ROI.</li><li>Create, manage, and analyze data-driven marketing campaigns across major platforms like Google, LinkedIn, and YouTube.</li><li>Leverage GenAI to automate and personalize marketing content, including ad copy, product recommendations, and email campaigns.</li><li>Develop and optimize e-commerce strategies and conversion-focused product pages.</li><li>Build a professional portfolio featuring projects that showcase job-ready digital marketing and analytics skills.</li><li>Complete a real-world capstone project integrating AI-enhanced strategies, analytics, and presentation skills.</li></ul><div><br>This program is ideal for anyone interested in starting a career in digital marketing as well as entrepreneurs and small business owners who want to learn how to effectively leverage online marketing channels for growth.<br><br></div><div>You’ll master key areas such as digital advertising, search engine optimization (SEO), content marketing, social media management, email marketing, and data analytics. Through interactive projects and labs, you’ll gain the skills employers look for in entry-level roles and build a portfolio that demonstrates your hands-on expertise.<br><br></div><div>You’ll learn how to design and optimize campaigns across multiple channels, leveraging modern marketing tools such as Google Ads, Meta Advertising, and Yoast SEO. You’ll also gain practical experience with e-commerce optimization, influencer marketing, and schema markup creation. To stay ahead of industry trends, you’ll use generative AI tools like ChatGPT and Gemini to automate and enhance tasks in SEO, content creation, and campaign management.<br><br></div><div>The program culminates in a capstone project where you’ll design and execute a comprehensive digital marketing strategy for a hypothetical brand, integrating all the skills you’ve developed. You’ll leave the program with a portfolio-ready campaign, an IBM Professional Certificate, and a verified IBM Digital Badge showcasing your job-ready expertise.<br><br></div><div>Career resources, such as mock interviews, resume optimization, and LinkedIn support, are included to help you confidently pursue roles like Digital Marketing Specialist, SEO Strategist, Content Marketer, or Growth Hacker. Whether you’re beginning your career or pivoting into digital marketing, this certificate provides the knowledge and credibility to stand out in a competitive field.<br><br><strong>Applied Learning Project<br><br></strong>Throughout the program, you’ll complete projects and labs to gain a firm grasp on the required skills commonly used by digital marketers.<br><br>Examples of labs and projects included in the program:</div><ul><li>Develop advertising campaigns for various social media channels, including Google, Instagram, Facebook, and LinkedIn</li><li>Optimize a campaign based on data</li><li>Perform influencer marketing selection</li><li>Create and optimize rich snippets and schema markups</li><li>Build campaigns on Google AdWords</li><li>Optimize e-commerce campaigns using Google Shopping</li><li>Generate personalized product recommendations</li><li>Leverage GenAI tools in digital marketing areas, such as content creation, email marketing, SEO, and social media</li></ul><div><br>The program includes a capstone project that provides a hands-on opportunity to apply your skills in a real-world scenario, guiding you to develop a comprehensive digital and growth hacking marketing strategy.<br><br>No college degree or prior experience is required. All you need is a willingness to learn, and have the basic computer literacy to take online courses.&nbsp;</div>

IBM Digital and Growth Marketing Professional Certificate

Launch your career in digital marketing with IBM. Gain job-ready skills in SEO, social media, content creation, paid ads, and data analytics. Learn AI-driven growth hacking and earn your IBM Professional Certificate in under 3 months.

<div class="trix-content">
  <div>Ready to build the strong creative foundation you need for a successful UI/UX career? This beginner-friendly course helps you master essential design principles, user-centered methods, and hands-on prototyping skills using tools like Miro and Figma. It’s ideal for aspiring designers and career switchers who are keen to build job-ready UX/UI design skills and demonstrate them in a portfolio-worthy project. <br /> </div><div><strong><em>You will:</em></strong>  </div><ul><li>Conduct user research, competitor analysis, and heuristic evaluations to identify usability gaps and deliver better user experiences. </li><li>Apply typography, color theory, and layout principles to create visually cohesive, accessible, and intuitive designs. </li><li>Build interactive prototypes and microinteractions in Figma, Miro, and Draw.io to demonstrate advanced design and prototyping skills. </li><li>Design a portfolio-ready, user-centered interface project that showcases your ability to solve real-world UX/UI challenges and impress potential employers. </li></ul><div> </div><div><strong>Course overview</strong> </div><div>During this course, you’ll master essential UI/UX tasks, including conducting heuristic evaluations to identify usability issues, using user journey mapping to optimize flows, and applying A/B testing for data-driven design improvements. You’ll also explore microinteraction design to enhance engagement and learn to create responsive interfaces that ensure consistency across devices. </div><div> </div><div>Throughout the course, you’ll work hands-on with industry-standard tools, such as Figma and Miro, tackling real-world design challenges and usability testing exercises. For your final project, you’ll design an interactive prototype for a health and fitness app. You’ll then conduct tests, gather feedback, and refine your design to produce a polished, portfolio-ready product. </div><div> </div><div>By the end, you’ll have the UX/UI design foundation and practical experience employers look for. Enroll now to start creating impactful, user-centered digital experiences. </div><div> </div><div><strong>Prerequisites</strong> </div><div>This course is designed for both UX/UI beginners and experienced professionals looking to deepen their design expertise . A basic familiarity with digital tools and an understanding of visual or interaction design principles can be helpful, but are not essential. No prior experience in UX/UI design is necessary to get started. </div><div> </div><div><strong>Related</strong><em> </em><strong>Professional Certificate</strong> </div><div>This course is part of the <strong>IBM UI/UX Designer Professional Certificate</strong>. If you’re looking to build hands-on skills in user research, interaction design, and usability testing, we recommend enrolling in the full program and progressing through the courses in order. In just a few months, you’ll gain job-ready UX/UI design experience, build a professional portfolio, and stand out to employers in the fast-growing design industry. </div><div> </div><div><strong>Course syllabus</strong> </div><div>The course consists of the following modules </div><ul><li>Introduction to UX/UI and Design Thinking </li><li>Usability and Interaction Design </li><li>Visual Design and Aesthetic Usability </li><li>Final Project and Final Exam </li></ul>
</div>


Build hands-on UI/UX skills in design thinking, user flows, A/B testing, and prototyping. Design interactive apps with Figma & Miro. Conduct usability testing. 

<div class="trix-content">
  <div>This hands-on project introduces you to <strong>building AI-interactive web apps</strong> using <strong>Gradio and GPT-5</strong>. You’ll create a <strong>Halloween-themed quiz game</strong> that automatically generates fresh, themed questions using GPT-5 — from spooky riddles to horror movie trivia.<br />Players can use lifelines like <strong>50-50</strong>, <strong>Flip Question</strong>, or <strong>Pass</strong>, and the app will track their score and show final results at the end.</div><div><br />You’ll learn how to design interactive interfaces using <strong>Gradio Components</strong>, connect GPT-5 for <strong>real-time content generation</strong>, and handle user logic such as scoring, timers, and state persistence. The result is a fun, AI-driven game that demonstrates real-world concepts of LLM-based interactivity, event handling, and creative user experience design.<br /><br /></div><h1><strong>Who Should Enroll</strong></h1><ul><li>Beginners in AI or Python looking for a creative, hands-on project</li><li>Developers who want to learn Gradio for building quick AI demos</li><li>Educators or students who want to design interactive AI-based games</li><li>Anyone curious about combining GPT models with real-time user interfaces</li></ul><h1><strong>Why Enroll</strong></h1><div>In just 30 minutes, you’ll go from idea to execution — building a <strong>complete AI quiz game</strong> that can be hosted locally or shared via Gradio’s public URL. You’ll understand how to turn GPT-5 prompts into dynamic gameplay elements and walk away with a working interactive app that’s fun, educational, and portfolio-ready.</div><div>Whether you’re showcasing your AI skills or just want to create something unique for Halloween, this project gives you a perfect blend of <strong>learning and entertainment</strong>.</div><div><br /><br /></div><h1><strong>A Look at the Project Ahead</strong></h1><div>After completing this guided project, you will be able to:</div><ul><li>Understand Gradio’s architecture — Build and organize components for user input, output, and UI flow.</li><li>Generate AI-based quiz questions — Use GPT-5 to create creative, random Halloween-themed questions.</li><li>Implement game logic — Manage lifelines (50-50, flip, pass), scoring, and player progression.</li><li> Host and share — Run your quiz locally or deploy it with Gradio’s public share link for friends or students to play.</li></ul><h1><strong>What You’ll Need</strong></h1><div><strong>Technical Requirements:</strong></div><ul><li>Basic knowledge of Python programming</li><li>No prior AI or web development experience required</li></ul><div><strong>Browser Setup:</strong></div><ul><li>A modern web browser (e.g., Chrome, Firefox) to access Gradio interface.</li><li> Internet connection for GPT-5 model access.</li></ul><div><br /></div>
</div>


Build an AI-Powered Halloween Quiz Game with Gradio & GPT-5

Create a spooky AI-powered Halloween Quiz Game using the powerful UI framework Gradio and OpenAI’s GPT-5 model. Learn how to auto-generate themed questions, add lifelines like 50-50 and Flip Question, track player scores, and design an interactive game interface. Build and launch a fully functional AI-driven web app without writing complex frontend code — the perfect beginner-friendly project that blends Python, AI, and creativity into one engaging experience.

Your portal gives you access to
Courses and
Guided Projects

Featured Courses

Prompt Engineering for Everyone

Artificial Intelligence, Generative AI, LLM
, +1 more

OpenShift Tekton Pipelines for CI-CD

DevOps, Kubernetes, SRE

Deploy a Web Server Using Python and IBM Code Engine

Python

Introduction to Cloud

Cloud Computing

Python for Data Science

Data Science, Python

Make an Impact!

Your portal gives you access toCourses andGuided Projects