Back to Catalog

Agentic AI: Build a Multi-Agent App with CrewAI & Gradio

BeginnerGuided Project

Discover how to build a multi-agent app using CrewAI, Gradio, and multimodal AI. This app will analyze uploaded food images to extract nutrition data, and create personalized recipes. This guided project teaches skills in multi-agent systems, computer vision, LLMs, and agentic AI. Perfect for developers or AI engineers, you'll integrate cutting-edge AI tools to design a user-friendly app that empowers users with actionable meal insights. Apply advanced AI methods to solve real-world challenges and expand your expertise in artificial intelligence.

4.7 (167 Reviews)

Language

  • English

Topic

  • Artificial Intelligence

Enrollment Count

  • 425

Skills You Will Learn

  • Multi-Agent System, Computer Vision, LLM, Gradio, Multimodal AI, AI Agent

Offered By

  • IBMSkillsNetwork

Estimated Effort

  • 60 minutes

Platform

  • SkillsNetwork

Last Update

  • October 15, 2025
About this Guided Project

Innovating Nutrition with Multi-Agent Systems: Build a Smart Nutritional App

Imagine using the power of AI to analyze a photo of your meal and instantly get detailed nutritional insights, along with recipe ideas tailored to specific dietary needs. We will build NourishBot, an AI-driven nutrition assistant that leverages Meta’s advanced multimodal model, Llama 3.2 90B Vision Instruct, alongside Flask.

But what if we could do more? What if NourishBot could evolve beyond just recognizing food to offering dynamic, real-time advice based on various factors—like dietary preferences and suggesting recipes based on what you have in your fridge? That’s exactly what we’re doing in this project. We’re stepping into the world of Multi-Agent Systems (MAS)—a framework where multiple AI agents collaborate to make complex decisions and offer tailored guidance.

In this project, you'll build a smart nutritional app that combines CrewAI's multi-agent system, various LLMs and multimodal AI to do exactly that. Whether you're exploring AI's real-world applications or looking for an engaging project to expand your portfolio, this project will guide you through creating a cutting-edge tool that showcases the potential of combining AI and software development.




What You'll Learn

By the end of this project, you'll be able to:
  • Analyze Food Images: Use image recognition tools such as multimodal AI to extract detailed nutrient information from uploaded food photos.
  • Implement Multi-Agent Systems: Harness CrewAI's multi-agent framework to manage complex workflows like nutritional analysis and recipe generation.
  • Generate Personalized Recipes: Leverage LLMs to produce creative, diet-friendly recipes based on analyzed food content.
  • Apply AI in Practical Use Cases: Explore how AI technologies can be used to build impactful and helpful tools.


What You'll Need

To get started, make sure you have:
  • A good understanding of Python programming.
  • Familiarity with AI concepts, such as image recognition and natural language processing.
  • A modern web browser (e.g., Chrome, Firefox, Edge, or Safari).

Who Should Complete This Project?

This project is perfect for:
  • Software Developers and Engineers: Looking to explore real-world applications of AI and multi-agent systems in app development.
  • AI Enthusiasts and Students: Interested in gaining hands-on experience with cutting-edge AI tools like CrewAI and LangChain.
  • Portfolio Builders: Developers seeking to create an impressive project that demonstrates their skills in AI integration and practical application.
  • Hackathon Participants: Those wanting to build innovative, helpful tools for competitive events or team projects.

This project isn't just about building a useful app; it's a deep dive into the practical implementation of AI in software development. Whether you're aiming to boost your portfolio, learn new tools, or explore creative AI applications, this tutorial offers the perfect opportunity to build something cool and impactful.

Instructors

Hailey Quach

Data Scientist

Hi, I'm Hailey. I enjoy teaching others to build creative and impactful AI projects. By day, I’m a Data Scientist at IBM; by night, an Honors BSc student at Concordia University in Montreal, always exploring new ways to combine learning with innovation.

Read more

Contributors

Ricky Shi

Data Scientist at IBM

Ricky Shi is a Data Scientist at IBM, specializing in deep learning, computer vision, and Large Language Models. He applies advanced machine learning and generative AI techniques to solve complex challenges across various sectors. As an enthusiastic mentor, Ricky is committed to helping colleagues and peers master technical intricacies and drive innovation.

Read more

Boyun Leung

UX Designer

Creating and designing delightful experiences.

Read more

Karan Goswami

Data Scientist at IBM

I am a dedicated Data Scientist and an AI enthusiast, currently working at IBM's Skills Builder Network. Learning how some simple mathematical operations could be used to make predictions and discover patterns sparked my curiosity, leading me to explore the exciting world of AI. Over the years, I’ve gained hands-on experience in building scalable AI solutions, fine-tuning models, and extracting meaningful insights from complex datasets. I'm driven by a desire to apply these skills to solve real-world problems and make a meaningful impact through AI.

Read more

Wojciech "Victor" Fulmyk

Data Scientist at IBM

I am a data scientist and economist with a strong background in econometrics, time series analysis, causal inference, and statistics. I stand out for my ability to combine technical expertise with clear communication, turning complex data findings into practical insights for stakeholders at every level. Follow my projects to learn about data science principles, machine learning algorithms, and artificial intelligence agents.

Read more