🌟 New Course! Enroll in Multi AI Agent Systems with crewAI

Enroll Now!

What you’ll learn in this course

Learn key principles of designing effective AI agents, and organizing a team of AI agents to perform complex, multi-step tasks. Apply these concepts to automate 6 common business processes.

Learn from João Moura, founder and CEO of crewAI, and explore key components of multi-agent systems:

  • Role-playing: Assign specialized roles to agents
  • Memory: Provide agents with short-term, long-term, and shared memory
  • Tools: Assign pre-built and custom tools to each agent (e.g. for web search)
  • Focus: Break down the tasks, goals, and tools and assign to multiple AI agents for better performance
  • Guardrails: Effectively handle errors, hallucinations, and infinite loops
  • Cooperation: Perform tasks in series, in parallel, and hierarchically

Throughout the course, you’ll work with crewAI, an open source library designed for building multi-agent systems. You’ll learn to build agent crews that execute common business processes, such as:

  • Tailor resumes and interview prep for job applications
  • Research, write and edit technical articles
  • Automate customer support inquiries
  • Conduct customer outreach campaigns
  • Plan and execute events
  • Perform financial analysis

By the end of the course, you will have designed several multi-agent systems to assist you in common business processes, and also studied the key principles of AI agent systems.


I was excited to check this out, and overall found it to be a good intro to agentic architectures. However, when running the code examples in the course, the results returned by my Crews were hilariously bad, often erroring out and unable to glean basic data from websites, or recover from 404 errors. I’m guessing these are errors that can be mitigated with guardrails in the agentic workflows, but for a quick course, which is at least partially meant to demonstrate the power of these architectures, I was left a bit cold.

The videos implemented gpt-4-turbo as the model, but the Jupyter notebooks specified gpt-3.5-turbo and i was unable to modify to gpt4 without triggering an error in the notebook. Perhaps the more advanced model would have led to more fruitful outcomes.

Hello Chris,

Thanks for your interest in our short courses! We have a dedicated Q&A category for short courses where you can connect with other learners. Feel free to join the discussion there – our amazing Mentors or Learning Technologists will be happy to answer your questions and connect with you as well.

1 Like