Look inside
Automate complex, multi-step tasks and jobs with a system of specialized AI agents.
AI agents are a great way to automate individual tasks within an application. Combining many agents into a coordinated workflow–a multi-agent system–amplifies the potential for agents to solve complex problems.
Multi-Agent Systems with AutoGen teaches you how to build collaborative teams of AI agents that can tackle tasks far beyond the capabilities of the standard prompt-and-response approach.
Inside
Multi-Agent Systems with AutoGen you’ll learn how:
- Autonomous task completion using AutoGen
- Best practices for multi-agent workflows in user-facing applications
- Controlling application UI—including the web and operating systems
- Evaluate multi-agent applications
- Optimize multi-agent applications
Multi-Agent Systems with AutoGen is written by the creator of AutoGen Studio Dr. Victor Dibia.. These expert authors distill their collective research and insights into a practical guide to building your first multi-agent systems. Complex concepts are made simple with concrete diagrams, examples, and code. You’ll design and implement AI applications that can solve tasks from telling you the weather all the way to developing software.
about the book
In
Multi-Agent Systems with AutoGen you’ll get familiar with building multi-agent applications and AutoGen, an open source AI framework to create AI assistants that can handle tasks once impossible to automate. You’ll apply the techniques you learn to building a whole host of useful AI assistants—from AI financial analysts capable of analyzing stocks and providing data-grounded responses, to travel agents that can search and book flights to your budget and preferences.
The book goes far deeper than the fundamentals of agent implementation to explore the other factors vital to your agent’s success. You’ll find best practices for building the right human-AI user interface, evaluation techniques that help you learn from failures, performance optimizations, and methods for ensuring user security and privacy.
about the reader
For AI/ML engineers, software developers, and product architects who know the basics of building with generative AI.
about the author
Victor Dibia (PhD) is a Principal Research Software Engineer at Microsoft Research and has contributed to projects like GitHub Copilot that service millions of customers. He is the creator of LIDA, a widely used tool for automated visualizations using generative AI models, and AutoGen Studio, a low-code tool for prototyping multi-agent applications. Victor holds a PhD in Information Systems from City University of Hong Kong and an MSc in Computer Science from Carnegie Mellon University.