Back to Catalog

Build and Execute Your Own Tools for LLMs

IntermediateGuided Project

Connect language models to the digital world by building tools that serve as their hands and eyes. This project shows you how to create specialized functions that let LLMs interact with YouTube videos and external services. You'll master the process of designing tools and controlling their execution through manual tool calling. Learn to build functions that extract video IDs, fetch transcripts, and analyze trending content. In just 1 hour, gain the expertise to create AI systems that search and analyze video content and understand the mechanics behind today's most powerful AI assistants.

Language

  • English

Topic

  • Artificial Intelligence

Skills You Will Learn

  • Python, Generative AI, Tool Calling, AI Agent, LangChain, LLM

Offered By

  • IBMSkillsNetwork

Estimated Effort

  • 1 hour

Platform

  • SkillsNetwork

Last Update

  • April 23, 2025
About this Guided Project
Language models become dramatically more powerful when they can interact with external services and data. In this hands-on guided project, you'll learn how to build this critical bridge between AI and the digital world through custom tool development.

Using YouTube content analysis as our example, you'll create specialized tools that enable language models to perform actions they couldn't accomplish alone. You'll build functions that extract video IDs, fetch transcripts, search for content, retrieve metadata, and access trending videos—giving your AI assistant comprehensive media analysis capabilities.

The project focuses on manual tool calling—controlling how LLMs select and execute tools. You'll learn how language models decide which tools to use, how to extract their requests, execute the appropriate functions, and return results in the expected format. This understanding is essential for debugging, customization, and building reliable AI systems.

What you'll learn

After completing this project, you will be able to:
  • Design custom tools with proper documentation, type hints, and error handling
  • Understand how LLMs select appropriate tools based on user requests
  • Extract tool call information from LLM responses
  • Execute tool calls manually with correct parameter formatting
  • Structure and manage conversations that include multiple tool calls
  • Build organized tool mappings for complex applications
  • Implement chains that handle multi-step tool execution workflows

Who should enroll

This project is perfect for:
  • AI developers seeking to extend language model capabilities
  • Software engineers building LLM-powered applications
  • Data scientists interested in programmatic content analysis
  • Technology professionals implementing practical AI solutions
  • Content creators looking to automate YouTube data collection

What you'll need

Before beginning this guided project, you should have:
  • Basic understanding of Python programming
  • Familiarity with language models and their capabilities
  • Access to a modern web browser for the IBM Skills Network Labs environment
  • Optional: Prior experience with LangChain is helpful but not required

Why enroll

By the end of this project, you'll understand the mechanics behind today's most advanced AI assistants. The ability to create custom tools and control their execution is what separates basic chatbots from powerful AI systems that can search databases, analyze content, and interact with external services.

As organizations increasingly adopt AI solutions, the demand for developers who understand tool integration continues to grow. Whether you're building research assistants, content analysis tools, or customer service agents, mastering custom tool development will enable you to create AI applications that deliver real-world value by combining the reasoning capabilities of language models with access to specialized functions and external data sources.

Instructors

Kunal Makwana

Data Scientist

I’m a passionate Data Scientist and AI enthusiast, currently working at IBM on innovative projects in Generative AI and machine learning. My journey began with a deep interest in mathematics and coding, which inspired me to explore how data can solve real-world problems. Over the years, I’ve gained hands-on experience in building scalable AI solutions, fine-tuning models, and leveraging cloud technologies to extract meaningful insights from complex datasets.

Read more

Contributors

Karan Goswami

Data Scientist

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

Joseph Santarcangelo

Senior Data Scientist at IBM

Joseph has a Ph.D. in Electrical Engineering, his research focused on using machine learning, signal processing, and computer vision to determine how videos impact human cognition. Joseph has been working for IBM since he completed his PhD.

Read more