4 Exploring multi-agent systems

This chapter covers

Building multi-agent systems using AutoGen Studio
Building a simple multi-agent system
Creating agents that can work collaboratively over a group chat
Building an agent crew and multi-agent systems using CrewAI
Extending the number of agents and exploring processing patterns with CrewAI

Now let’s take a journey from AutoGen to CrewAI, two well-established multi-agent platforms. We’ll start with AutoGen, a Microsoft project that supports multiple agents and provides a studio for working with them. We’ll explore a project from Microsoft called AutoGen, which supports multiple agents but also provides a studio to ease you into working with agents. From there, we’ll get more hands-on coding of AutoGen agents to solve tasks using conversations and group chat collaborations.

Then, we’ll transition to CrewAI, a self-proposed enterprise agentic system that takes a different approach. CrewAI balances role-based and autonomous agents that can be sequentially or hierarchically flexible task management systems. We’ll explore how CrewAI can solve diverse and complex problems.

4.1 Introducing multi-agent systems with AutoGen Studio

4.1.1 Installing and using AutoGen Studio

4.1.2 Adding skills in AutoGen Studio

4.2 Exploring AutoGen

4.2.1 Installing and consuming AutoGen

4.2.2 Enhancing code output with agent critics

4.2.3 Understanding the AutoGen cache

4.3 Group chat with agents and AutoGen

4.4 Building an agent crew with CrewAI

4.4.1 Creating a jokester crew of CrewAI agents

4.4.2 Observing agents working with AgentOps

4.5 Revisiting coding agents with CrewAI

4.6 Exercises

Summary