AI Agents in Action by Micheal Lanham | Build Autonomous Multi-Agent AI Systems

AI Agents in Action by Micheal Lanham

AI Agents in Action: Build, Orchestrate, and Deploy Autonomous Multi-Agent Systems is a practical guide to building intelligent AI agents and autonomous multi-agent systems using modern Large Language Models. Written by software and technology innovator Micheal Lanham, the book takes readers beyond basic chatbot development and explores how AI agents can understand tasks, use tools, access knowledge, maintain memory, reason through problems, collaborate with other agents, and operate with greater autonomy.

Published by Manning in 2025, this book is designed for developers and technology professionals who want to understand how AI agents can be designed and deployed for real-world applications. It combines concepts with practical development approaches, covering LLMs, GPT assistants, multi-agent systems, agent actions, autonomous assistants, memory, knowledge management, prompt engineering, reasoning, evaluation, planning, and feedback.

About This Book

AI agents represent an important evolution beyond traditional conversational AI. Instead of simply responding to a prompt, an agent can be designed to interact with tools, retrieve information, plan actions, maintain context, and complete multi-step tasks.

AI Agents in Action introduces readers to the architecture and behavior patterns behind these systems. The book explains how individual agents can be connected into multi-agent workflows capable of handling increasingly complex tasks.

The first edition covers the development of production-ready assistants, agent platforms, knowledge and memory systems, prompt workflows, reasoning, evaluation, planning, and feedback.

Understanding AI Agents

The book begins by establishing a foundation for understanding what an AI agent is and how agents differ from conventional AI interfaces and assistants.

Readers explore:

• Agent definitions and behavior patterns
• Components of an AI agent
• Agent-based architectures
• The relationship between LLMs and agents
• Autonomous decision-making
• Agent interaction with external systems
• AI assistants versus autonomous agents
• The emerging agent ecosystem

This foundation helps readers understand how language models can become components within larger intelligent systems rather than functioning only as text-generation tools.

Large Language Models and GPT Assistants

A strong understanding of Large Language Models is essential for developing effective AI agents. The book introduces the role of LLMs in agent systems and demonstrates how they can provide reasoning and language capabilities.

Readers learn how to work with GPT-based assistants and explore techniques for connecting language models to applications and external functionality.

The book also introduces practical concepts surrounding prompts, model interaction, agent behavior, and application development.

Building Multi-Agent Systems

One of the central themes of AI Agents in Action is the development of multi-agent systems.

Instead of relying on one AI agent to perform every task, developers can create multiple specialized agents that collaborate or operate as part of an orchestrated workflow. Different agents can take responsibility for different stages of a problem, allowing complex tasks to be divided into manageable components.

Topics include:

• Multi-agent architectures
• Agent collaboration
• Agent orchestration
• Specialized AI agents
• Agent workflows
• Communication between agents
• Autonomous multi-agent applications
• Coordinating multiple AI capabilities

These concepts are particularly useful for developers exploring advanced generative AI and agentic application architectures.

Giving AI Agents Actions and Tools

An important characteristic of an AI agent is its ability to do more than generate text. Agents can be connected to tools and external services that allow them to perform actions.

The book explores how developers can empower agents with actions and create systems capable of interacting with software, data, and other resources.

This approach can transform an LLM-powered application from a simple conversational interface into an intelligent system capable of carrying out practical tasks.

Autonomous Assistants

The book demonstrates how to move from basic assistants toward more autonomous AI applications.

Readers learn how agents can be designed to:

• Understand user objectives
• Break complex tasks into steps
• Select appropriate actions
• Work with external tools
• Retrieve relevant information
• Maintain useful knowledge
• Evaluate results
• Respond to changing circumstances
• Operate with reduced human supervision

This makes the book particularly relevant to developers interested in agentic AI, autonomous assistants, and intelligent workflow automation.

Agent Memory and Knowledge

Memory and knowledge management are essential when AI systems need to work across multiple interactions or handle information beyond what can fit into a single prompt.

AI Agents in Action explores approaches for giving agents access to knowledge and memory so that they can maintain useful context and retrieve information when needed.

The book covers concepts related to:

• Agent memory
• Knowledge management
• Retrieval-augmented knowledge
• Information retrieval
• Context management
• Persistent information
• Agent knowledge systems

These capabilities help developers design agents that can work with domain-specific information and more complex application environments.

Prompt Engineering and Agent Behavior

Prompt engineering becomes especially important when prompts are used to control the behavior and personality of an autonomous agent.

The book explores prompt workflows and techniques for creating agents with specific roles, behaviors, and objectives. Readers learn how carefully designed instructions can influence how agents interact with users, tools, and other agents.

This makes the book useful for developers who want to move beyond basic prompting toward structured AI-agent behavior.

Reasoning, Planning and Evaluation

Autonomous systems need mechanisms for deciding what to do next, evaluating results, and adapting their behavior.

The book examines agent reasoning and evaluation as well as planning and feedback. These concepts are important for creating AI systems that can handle multi-step tasks instead of producing isolated responses.

Readers gain an understanding of how planning and feedback can be incorporated into agent architectures to improve their ability to complete tasks and respond to changing conditions.

Building an Agent Platform

Beyond individual agents, the book explores how developers can assemble an agent platform that provides the infrastructure needed to create and manage intelligent applications.

This perspective is useful for engineers who want to build reusable systems rather than isolated AI demonstrations.

The book's practical progression covers agent development from introductory concepts through assistants, multi-agent applications, actions, autonomy, platforms, memory, prompts, reasoning, evaluation, planning, and feedback.

Key Topics Covered

• Artificial Intelligence
• AI Agents
• Agentic AI
• Large Language Models
• LLM Applications
• GPT Assistants
• Autonomous Agents
• Autonomous Assistants
• Multi-Agent Systems
• Multi-Agent Architecture
• Agent Orchestration
• AI Workflows
• Agent Tools and Actions
• Agent Platforms
• AI Memory
• Knowledge Management
• Retrieval-Augmented Knowledge
• Prompt Engineering
• Prompt Flow
• Agent Reasoning
• AI Planning
• Agent Evaluation
• Feedback Loops
• Intelligent Automation
• Python Development
• Generative AI
• Natural Language Processing

Why Read This Book?

AI Agents in Action is valuable for readers who want to understand how modern AI systems can move beyond simple question-and-answer interactions toward autonomous, tool-using applications.

Rather than focusing exclusively on the theory of artificial intelligence, Micheal Lanham takes a practical approach to building agents and connecting them into larger systems. The book provides a progression from understanding agent concepts to developing assistants, multi-agent systems, agent platforms, memory and knowledge capabilities, reasoning, planning, evaluation, and feedback.

For developers entering the rapidly evolving field of agentic AI, the book provides a useful foundation for understanding the architecture and engineering principles behind AI agents.

Who Should Read This?

This book is particularly suitable for:

• Software developers
• Python programmers
• AI engineers
• Machine learning engineers
• Data scientists
• Developers building LLM applications
• Generative AI enthusiasts
• MLOps and AI infrastructure professionals
• Technology professionals exploring agentic AI
• Students studying artificial intelligence
• Developers interested in autonomous assistants
• Professionals exploring multi-agent systems

The publisher positions the book toward readers interested in creating LLM-powered autonomous agents and intelligent assistants for practical business and personal applications.

Product Details

• Book Title: AI Agents in Action: Build, Orchestrate, and Deploy Autonomous Multi-Agent Systems
• Author: Micheal Lanham
• Publisher: Manning
• Publication: 2025
• Language: English
• Genre: Artificial Intelligence / Machine Learning / Software Development
• Category: AI & Machine Learning
• Length: 344 pages
• ISBN-13: 9781633436343
• Format: English Paperback / Trade Paperback
• Level: Intermediate
• Primary Topics: AI Agents, LLMs, Multi-Agent Systems, Prompt Engineering, Autonomous Assistants

The publisher lists the 2025 edition at 344 pages with ISBN 9781633436343.

About the Author

Micheal Lanham is a software and technology innovator with more than 20 years of industry experience. His professional work has covered software applications across areas including games, graphics, web, desktop, engineering, artificial intelligence, GIS, and machine learning. He has also authored books on deep learning, including Manning's Evolutionary Deep Learning.

Final Overview

AI Agents in Action by Micheal Lanham is a practical resource for developers who want to learn how AI agents can be designed, orchestrated, and deployed as useful intelligent systems. From Large Language Models and GPT assistants to autonomous agents, multi-agent architectures, tools, memory, knowledge, prompts, reasoning, evaluation, planning, and feedback, the book provides a broad introduction to building modern agentic AI applications.