What do you think?
Rate this book
AI Agents in Action
Create LLM-powered autonomous agents and intelligent assistants tailored to your business and personal needs.
From script-free customer service chatbots to fully independent agents operating seamlessly in the background, AI-powered assistants represent a breakthrough in machine intelligence. In AI Agents in Action, you'll master a proven framework for developing practical agents that handle real-world business and personal tasks.
Author Micheal Lanham combines cutting-edge academic research with hands-on experience to help
• Understand and implement AI agent behavior patterns
• Design and deploy production-ready intelligent agents
• Leverage the OpenAI Assistants API and complementary tools
• Implement robust knowledge management and memory systems
• Create self-improving agents with feedback loops
• Orchestrate collaborative multi-agent systems
• Enhance agents with speech and vision capabilities
You won't find toy examples or fragile assistants that require constant supervision. AI Agents in Action teaches you to build trustworthy AI capable of handling high-stakes negotiations. You'll master prompt engineering to create agents with distinct personas and profiles, and develop multi-agent collaborations that thrive in unpredictable environments. Beyond just learning a new technology, you'll discover a transformative approach to problem-solving.
About the technology
Most production AI systems require many orchestrated interactions between the user, AI models, and a wide variety of data sources. AI agents capture and organize these interactions into autonomous components that can process information, make decisions, and learn from interactions behind the scenes. This book will show you how to create AI agents and connect them together into powerful multi-agent systems.
About the book
In AI Agents in Action, you’ll learn how to build production-ready assistants, multi-agent systems, and behavioral agents. You’ll master the essential parts of an agent, including retrieval-augmented knowledge and memory, while you create multi-agent applications that can use software tools, plan tasks autonomously, and learn from experience. As you explore the many interesting examples, you’ll work with state-of-the-art tools like OpenAI Assistants API, GPT Nexus, LangChain, Prompt Flow, AutoGen, and CrewAI.
What's inside
• Knowledge management and memory systems
• Feedback loops for continuous agent learning
• Collaborative multi-agent systems
• Speech and computer vision
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.
Table of Contents
1 Introduction to agents and their world
2 Harnessing the power of large language models
3 Engaging GPT assistants
4 Exploring multi-agent systems
5 Empowering agents with actions
6 Building autonomous assistants
7 Assembling and using an agent platform
8 Understanding agent memory
From script-free customer service chatbots to fully independent agents operating seamlessly in the background, AI-powered assistants represent a breakthrough in machine intelligence. In AI Agents in Action, you'll master a proven framework for developing practical agents that handle real-world business and personal tasks.
Author Micheal Lanham combines cutting-edge academic research with hands-on experience to help
• Understand and implement AI agent behavior patterns
• Design and deploy production-ready intelligent agents
• Leverage the OpenAI Assistants API and complementary tools
• Implement robust knowledge management and memory systems
• Create self-improving agents with feedback loops
• Orchestrate collaborative multi-agent systems
• Enhance agents with speech and vision capabilities
You won't find toy examples or fragile assistants that require constant supervision. AI Agents in Action teaches you to build trustworthy AI capable of handling high-stakes negotiations. You'll master prompt engineering to create agents with distinct personas and profiles, and develop multi-agent collaborations that thrive in unpredictable environments. Beyond just learning a new technology, you'll discover a transformative approach to problem-solving.
About the technology
Most production AI systems require many orchestrated interactions between the user, AI models, and a wide variety of data sources. AI agents capture and organize these interactions into autonomous components that can process information, make decisions, and learn from interactions behind the scenes. This book will show you how to create AI agents and connect them together into powerful multi-agent systems.
About the book
In AI Agents in Action, you’ll learn how to build production-ready assistants, multi-agent systems, and behavioral agents. You’ll master the essential parts of an agent, including retrieval-augmented knowledge and memory, while you create multi-agent applications that can use software tools, plan tasks autonomously, and learn from experience. As you explore the many interesting examples, you’ll work with state-of-the-art tools like OpenAI Assistants API, GPT Nexus, LangChain, Prompt Flow, AutoGen, and CrewAI.
What's inside
• Knowledge management and memory systems
• Feedback loops for continuous agent learning
• Collaborative multi-agent systems
• Speech and computer vision
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.
Table of Contents
1 Introduction to agents and their world
2 Harnessing the power of large language models
3 Engaging GPT assistants
4 Exploring multi-agent systems
5 Empowering agents with actions
6 Building autonomous assistants
7 Assembling and using an agent platform
8 Understanding agent memory
344 pages, Paperback
Published March 25, 2025
55 people are currently reading
99 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 12 of 12 reviews
May 29, 2025
Mixed feelings ;/
My impression is that the book oversells, but what it delivers is a rather generic RAG+Agents intro, that can be found in many tutorials over the web:
- chapters have quite a specific focus (each of them), but I didn't find them very educative - each of them uses different tools (CrewAI, LangChain, Semantic Model, etc.) without introducing the basic abstractions of the tool OR even pinpointing key differences between them (they partially overlap, but not in 100%): you just get a wall of code for yourselves to interpret (TBH the code is rather simple, so it's not a show-stopper, but kinda annoyed me)
- the author did very little to highlight the importance of semantic interfaces - the whole book is basically doing "as they do, because they do" - that's actually a very interesting topic, because the value is not obvious (the same goal(s) can be achieved in different ways)
- this is a happy-path tutorial and there's very little on practical issues related to building AI agents (regression and quality assessment, guardrails & case-specific observability, authorisation, etc.)
- the book has just recently been published, but ... it's already outdated (not the author's fault really - this field of study just moves so fast), e.g., there's nothing on MCP here (which pretty much invalidates the idea of this book being a proper intro to AI agents)
Long story short, I can't recommend this one. It's not bad, but if you want to start your agentic adventure here, you're need to add a lot to your "onboarding".
2-2.2 stars only :(
My impression is that the book oversells, but what it delivers is a rather generic RAG+Agents intro, that can be found in many tutorials over the web:
- chapters have quite a specific focus (each of them), but I didn't find them very educative - each of them uses different tools (CrewAI, LangChain, Semantic Model, etc.) without introducing the basic abstractions of the tool OR even pinpointing key differences between them (they partially overlap, but not in 100%): you just get a wall of code for yourselves to interpret (TBH the code is rather simple, so it's not a show-stopper, but kinda annoyed me)
- the author did very little to highlight the importance of semantic interfaces - the whole book is basically doing "as they do, because they do" - that's actually a very interesting topic, because the value is not obvious (the same goal(s) can be achieved in different ways)
- this is a happy-path tutorial and there's very little on practical issues related to building AI agents (regression and quality assessment, guardrails & case-specific observability, authorisation, etc.)
- the book has just recently been published, but ... it's already outdated (not the author's fault really - this field of study just moves so fast), e.g., there's nothing on MCP here (which pretty much invalidates the idea of this book being a proper intro to AI agents)
Long story short, I can't recommend this one. It's not bad, but if you want to start your agentic adventure here, you're need to add a lot to your "onboarding".
2-2.2 stars only :(
April 11, 2025
I couldn't help but laugh at this excerpt from the author:
"WARNING: While writing this book and working with and building agents over many hours, I have encountered several instances of agents going rogue with actions, from downloading files to writing and executing code when not intended, continually iterating from tool to tool, and even deleting files they shouldn’t have. Watching an agent emerge new behaviors using actions can be fun, but things can quickly go astray."
The future looks bright!
Possibly on fire. But bright!
"WARNING: While writing this book and working with and building agents over many hours, I have encountered several instances of agents going rogue with actions, from downloading files to writing and executing code when not intended, continually iterating from tool to tool, and even deleting files they shouldn’t have. Watching an agent emerge new behaviors using actions can be fun, but things can quickly go astray."
The future looks bright!
Possibly on fire. But bright!
April 30, 2025
This can hardly be called a book. it's an amalgam of infographics and code snippets rendering it unreadable.
in terms of agentic AI itself, not sure about the longer term prospect but as of 2025 it's dismal, much ado about nothing.
in terms of agentic AI itself, not sure about the longer term prospect but as of 2025 it's dismal, much ado about nothing.
April 20, 2025
This book contains a huge amount of information about the inner structure and the practical building and commissioning of intelligent angents using some state-of-the-art tools. While the clarity in the exposition is undiscussed, what is striking to me, is the excellent technical quality, that guarantees all the information are not only understandable, but also objectively presented and correct.
Reading all the chapters and practicing all the example is not enough to become an expert, nor to build your own AI agent, but this lays the basis to experiment autonomously, learn by doing and, ultimately, gives the reader the necessary know-how to dig deeper with more advanced books.
Too bad that some of the tools chosen by tha author are not exactly my favorite ones and that some of the resources required are not free (so that one has to be carefull to avoid paying unwanted fees for online services). Yet, I respect author's choices because in this case they are sensible and, specially for the commercial ones, there are few, if any, free alternatives with the exact same features.
Reading all the chapters and practicing all the example is not enough to become an expert, nor to build your own AI agent, but this lays the basis to experiment autonomously, learn by doing and, ultimately, gives the reader the necessary know-how to dig deeper with more advanced books.
Too bad that some of the tools chosen by tha author are not exactly my favorite ones and that some of the resources required are not free (so that one has to be carefull to avoid paying unwanted fees for online services). Yet, I respect author's choices because in this case they are sensible and, specially for the commercial ones, there are few, if any, free alternatives with the exact same features.
April 7, 2025
This is an excellent book that focuses on the foundations of creating intelligent agents.
All chapters have details about the importance of planning by focusing on planning within an agent framework, while exploring the use of the OpenAI Assistants platform and the implementation of generic planners also this book shows how to build GPTs with capabilities such as code interpretation, using custom actions, and integrating knowledge via files.
The book also covers some advanced aspects of multi-agent systems and autonomy, building multi-agent systems using AutoGen Studio and CrewAI to solve complex problems, by addressing how agents act outside of themselves using actions, OpenAI functions, and Semantic Kernel it shows the creation of a hosted agent system with SK.
This book also covers how to build autonomous assistants using behavior trees to guide agentic systems, exploring the implementation of actions on the OpenAI Assistants platform via the GPT Assistants Playground, and addressing the monitoring of these autonomous systems.
Finally, AI in actions address the creation of agent platforms, memory and knowledge management, and the importance of systematic prompt engineering, introduces Nexus, which teach the fundamental concepts of building complete AI agents. It also explores the role of memory and knowledge in agents, focusing on information retrieval (RAG) with LangChain, and discussing document indexing techniques, vector databases, and memory compression.
If you are interested in learning how to build AI agents, this book is must-read.
All chapters have details about the importance of planning by focusing on planning within an agent framework, while exploring the use of the OpenAI Assistants platform and the implementation of generic planners also this book shows how to build GPTs with capabilities such as code interpretation, using custom actions, and integrating knowledge via files.
The book also covers some advanced aspects of multi-agent systems and autonomy, building multi-agent systems using AutoGen Studio and CrewAI to solve complex problems, by addressing how agents act outside of themselves using actions, OpenAI functions, and Semantic Kernel it shows the creation of a hosted agent system with SK.
This book also covers how to build autonomous assistants using behavior trees to guide agentic systems, exploring the implementation of actions on the OpenAI Assistants platform via the GPT Assistants Playground, and addressing the monitoring of these autonomous systems.
Finally, AI in actions address the creation of agent platforms, memory and knowledge management, and the importance of systematic prompt engineering, introduces Nexus, which teach the fundamental concepts of building complete AI agents. It also explores the role of memory and knowledge in agents, focusing on information retrieval (RAG) with LangChain, and discussing document indexing techniques, vector databases, and memory compression.
If you are interested in learning how to build AI agents, this book is must-read.
April 15, 2025
AI Agents in Action is a valuable resource for anyone looking to master the design and deployment of autonomous agents. Its practical focus and wide-ranging coverage make it a standout guide in the field of AI development. However, it may not be the best fit for beginners or those seeking a more theoretical exploration of AI systems. Additionally, it might not fully meet the needs of advanced programmers, as many of the proposed solutions heavily rely on third-party products. Experienced developers may prefer a deeper dive into building complex systems from the ground up.
Overall, this book earns a solid 4 out of 5 for its depth, practicality, and relevance to the evolving landscape of AI technology.
Overall, this book earns a solid 4 out of 5 for its depth, practicality, and relevance to the evolving landscape of AI technology.
May 16, 2025
I didn’t get this book. It’s beautifully illustrated, but the structure and content is a mess.
E.g. there is a diagram claiming “fine-tuning” as a “constituent part” of LLM…what?
Almost every chapter has some new tool and some code listings for something. Really, more a study notes by author vs. a book. DNF.
E.g. there is a diagram claiming “fine-tuning” as a “constituent part” of LLM…what?
Almost every chapter has some new tool and some code listings for something. Really, more a study notes by author vs. a book. DNF.
March 26, 2025
This book is excellent for those seeking for references on how to build AI Agents using (mainly) OpenAI's capabilities. You will find some content on GPT Nexus, LangChain, Prompt Flow, AutoGen, and CrewAI, but I think it shines on explaining on how to build AI Agents without code.
May 25, 2025
The book is ~350 pages long, if you subtract from it (the preface and postface,) the codes, images and installation how-to which you can look up on Google, you have ~50 pages remaining that are worth reading. Honestly it is too long but too little to read from.
September 5, 2025
Good Book to start learning about AI Agent. Just went through the theory of this book. Suggest to do practical while reading.
This book can be less than 100 pages, if you remove all images and code snippets.
This book can be less than 100 pages, if you remove all images and code snippets.
March 7, 2025
As usual, lots of references to diagrams and programs making it inconvenient as an audio book.
July 14, 2025
poorly written, however i found chapters about memory management and evaluation of agents useful. but not a deep book, more a tutorial and in blog post format.
Displaying 1 - 12 of 12 reviews