Back to Catalog

Build Agentic and Multi-Agent Systems in Python using BeeAI

IntermediateGuided Project

Build tool calling agents, ReAct agents, and human-in-the-loop multi-agent systems using OpenAI's GPT, IBM Granite, and Meta's Llama in the BeeAI Framework. This comprehensive, hands-on project requires no prior experience with BeeAI and takes you from initial setup to building intelligent systems for cybersecurity, business planning, and travel automation.

Language

  • English

Topic

  • Artificial Intelligence

Skills You Will Learn

  • Artificial Intelligence, LLM, Multi-Agent Systems, AI Agents, Tool Calling, Agentic AI

Offered By

  • IBMSkillsNetwork

Estimated Effort

  • 2 hours

Platform

  • SkillsNetwork

Last Update

  • September 24, 2025
About this Guided Project
In the age of intelligent automation, building AI agents that can reason, act, and collaborate is no longer a futuristic concept; it is a practical necessity. Whether you're working in cybersecurity, business strategy, or travel planning, agentic systems offer a powerful way to automate complex workflows, integrate with external tools, and deliver human-like decision-making.

This project introduces you to the BeeAI Framework, a cutting-edge, open-source platform developed under the Linux Foundation AI and backed by IBM Research. BeeAI is built for production-grade agent development, offering robust support for multiple LLM providers such as OpenAI and watsonx.ai, which give you access to popular models including OpenAI's GPT, IBM Granite, and Meta’s Llama.

With BeeAI, you’ll learn to build intelligent systems that go far beyond simple chatbots—systems that can reason, act, and collaborate, even with human oversight. Whether you're automating cybersecurity analysis, planning business strategies, or coordinating travel, BeeAI equips you with the tools to build real-world, multi-agent AI systems that are flexible, scalable, and ready for deployment.

By completing this hands-on guided project, you’ll gain the skills to build intelligent agents and multi-agent systems, even if you’ve never used BeeAI before.


A Look at the Project Ahead

This project takes you from foundational concepts to advanced multi-agent architectures. You’ll build intelligent systems that solve real problems in cybersecurity, business planning, and travel automation. Along the way, you’ll learn how to integrate tools, enforce reasoning patterns, and include human oversight in your agents.

By the end of this guided project, you will be able to:
  • Design and build intelligent AI agents that can interact naturally, perform tasks, and make decisions based on structured reasoning.
  • Integrate external tools and data sources into your agents to enhance their capabilities, including research, calculations, and weather forecasting.
  • Create collaborative multi-agent systems where specialized agents work together to solve complex problems through coordinated workflows.
  • Implement human oversight and control mechanisms to ensure agents operate safely and transparently in production environments.

What You'll Need

To get started with this guided project, you’ll need:
  • Basic Python programming knowledge
  • General understanding of AI agents and LLMs (helpful but not required)
  • A modern browser, such as a current version of Chrome, Edge, Firefox, Safari, or Internet Explorer
  • No prior experience with BeeAI is required: everything is covered step-by-step

Instructors

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

Contributors

Jianping Ye

Data Scientist Intern at IBM

I'm Jianping Ye, currently a Data Scientist Intern at IBM and a PhD candidate at the University of Maryland. I specialize in designing AI solutions that bridge the gap between research and real-world application. With hands-on experience in developing and deploying machine learning models, I also enjoy mentoring and teaching others to unlock the full potential of AI in their work.

Read more