AI agent technology is changing fast! This totally revised Second Edition of AI Agents in Action by Micheal Lanham guides you through the latest breakthroughs in large language model (LLM)-powered autonomy, from the Model Context Protocol (MCP) to advanced multi-agent collaboration and deployment.
Whether you're upgrading your customer service systems, creating a research assistant, or deploying a fleet of internal agents to automate enterprise tasks, this hands-on guide will help you build trustworthy agents that can handle high-stakes tasks. Extensively revised, this second edition contains new chapters on MCP, containerized deployment, and voice agent orchestration, along with refreshed coverage of LangChain, Prompt Flow, CrewAI, and more.
In AI Agents in Action, Second Edition you'll learn how to:
• Design and deploy production-grade autonomous agents
• Use MCP, the OpenAI Assistants API, and tools to build adaptable systems
• Take advantage of retrieval-augmented memory, feedback loops, and self-improving behaviors
• Orchestrate voice and vision-enabled agents
• Containerize and scale your agents
About the book
AI Agents in Action, Second Edition provides a solid foundation for readers just starting with agents, and it also introduces more advanced techniques and tools for experienced AI developers. You'll work through the core layers of an agentic system, including prompt engineering, working with tools, reasoning and planning, knowledge and memory, evaluation, and feedback patterns. Each chapter combines practical, real-world examples that cover reasoning frameworks like ReAct and Sequential Thinking MCP, advanced RAG systems, and multi-agent collaboration patterns. Plus, you'll find extensive tips, tricks, and best practice advice taken from Micheal Lanham's extensive AI career.
About the reader
For intermediate Python programmers.
About the author
Micheal Lanham is a software and technology innovator with over 20 years of industry experience. He has authored books on deep learning, including Manning's Evolutionary Deep Learning.
