Pages
344
Year
2025
Level
intermediate
Read time
9h
Micheal Lanham · Manning Publications · 2025
Reviewed by Ashish Sheth · Updated April 2026
AI Agents in Action
4.1 / 5
AMAZON · 35 RATINGS
ai agents · llm
SUBJECTS
What you'll come away with
01.
How to build agents step-by-step using current APIs and frameworks
02.
Memory architectures and when each type matters
03.
Tool use patterns that work in production
04.
Multi-agent orchestration with AutoGen and similar frameworks
05.
How behavior trees apply to LLM-based agents
06.
What 'agent evaluation' actually means and how to do it
Strengths
+Practical, code-first approach with runnable examples throughout
+Manning's quality editing makes it more readable than rushed competitors
+Covers OpenAI Assistants, AutoGen, and LangChain in one volume
+Author's game-AI background brings useful patterns (behavior trees) to LLM agents
Caveats
−Some readers find the OpenAI Assistants focus dating quickly
−Coverage of newer agent frameworks (LangGraph, CrewAI) is thinner than expected
−Code examples occasionally hit API breakage as providers evolve
★ 4.1 FROM 35 READERS ON AMAZON
Check Price on Amazon →
Read this if
→Developers who want to build a working agent in a weekend, not just read about them
→Engineers comparing OpenAI Assistants, AutoGen, and other frameworks
→Game developers or animation engineers seeing parallels in LLM agents
Skip this if
—Engineers wanting deep theoretical agent foundations
—Teams committed to LangGraph or CrewAI (coverage is lighter)
—Beginners with no LLM API experience yet
Head-to-head comparisons
AI Agents in Action vs Building Agentic AI Systems → AI Agents in Action vs AI Engineering → AI Agents in Action vs Building LLMs for Production → Frequently asked
How is AI Agents in Action different from Building Agentic AI Systems?
Lanham's book is more code-first and beginner-friendly. Biswas/Talukdar's book is more architectural and patterns-focused. Read Lanham to build, Biswas to design.
Will the OpenAI Assistants API examples still work?
OpenAI deprecated some Assistants endpoints in 2025. The patterns transfer to the Responses API and other providers, but expect to update some code.
Is this book good for someone new to LLMs?
You should know what an LLM API call looks like. If you've made one OpenAI or Claude call, you're ready. If not, read Hands-On Large Language Models first.
Read this next
3 alternatives
Ready?
Check Price on Amazon →