Welcome to Multi AI agent systems with CrewAI, built in partnership with CrewAI and taught by its founder and CEO, João Moura. I think AI agent workflows will be a key driver of AI progress in the near term. Multi agent workflows let you break down the complex tasks into subtasks that can be executed by agents, each of which plays a particular defined role. For example, if your goal is get a research report written, the roles might be researcher, writer, and fact checker. Or if you want to get a website built, perhaps the roles could be a web designer, software engineer and testing engineer. I've really enjoyed using crewAI myself, and I'm delighted that its creator João, is teaching this course. João had created crewAI when he needed a tool to build better agents, to help him write LinkedIn posts, and he has a lot of experience designing workflows to collections of agents. Execute. Thanks, Andrew. Really, I'm excited to work with you and your team and this is and has the potential to enable engineers to build great things. In this course, you learn the major building blocks for agentic systems with an emphasis on multi-agent systems. Building blocks you learn include: role-playing, tool use, memory, guardrails, and collaboration. And you use these components to build a collection of agents, to customize a resume, to job description, and to perform financial analysis, and also to perform event planning. As part of assembling your agentic workflow, you also define how these agents cooperate, which ones are able to delegate to other agents to perform certain tasks like research, and whether certain agents should execute their tasks in parallel or in series, or in a hierarchical fashion, with a manager agent delegating to a number of worker agents. João will go through these concepts using the crewAI Open Source library. Yes, this course will help engineers trying to understand how to build AI agentic applications and how they differ from regular applications that we have been building up to this point. After watching this, you will be equipped with everything you need to build multi-agent systems and reap all the benefits from it. I like to think of good multi-agent systems designs like being a manager. You are now promoted into this manager of agents and get to identify the goals and the various roles that will work together to achieve those goals, and also define clear expectations for what success looks like. It's a very interesting mental shift from regular engineering. Yes, indeed, many people have worked to create this course. I'd like to thank the whole CrewAI team and from DeepLearning.AI, Eddy Shyu, also contributed to this course. The first lesson will give you an overview of AI agents, and also an overview of the rest of the course. So make sure to stick around. So let's go on to the next video and dive into the key building blocks of AI agents.
Multi AI Agent Systems with crewAI
- Introduction
- Overview
- AI Agents
- Create agents to research and write an article (code)
- Key elements of AI agents
- Multi agent customer support automation (code)
- Mental framework for agent creation
- Key elements of agent tools
- Tools for a customer outreach campaign (code)
- Recap of tools
- Key elements of well defined tasks
- Automate event planning (code)
- Recap on tasks
- Multi agent collaboration
- Mutli agent collaboration for financial analysis (code)
- Build a crew to trailor job applications (code)
- Next steps with AI agent systems
- Conclusion
- How to get your completion badge