Price: ~~$59.99~~ - $41.64
(as of Jan 29,2026 18:34:17 UTC – Details)

Buy Now

From the Publisher

“Couldn’t put this book down! It’s so comprehensive and clear that I felt like I was learning from a master teacher.”

Radhika Kanubaddhi, Amazon

“An enlightening journey! This book transformed my questions into answers.”

Jose San Leandro, ACM-SL

“Expertly guides through creating agent profiles, using tools, memory, planning, and multi-agent systems. Couldn’t be more timely!”

Grigory Sapunov, author of JAX in Action

• Chapter 1: Introduction to agents and their world

Defines AI agents, differentiating direct LLM interaction from proxy, assistant, and autonomous agents. It explores multi-agent systems and the five core components—profile, actions, knowledge, reasoning, and planning—essential for building robust, effective AI systems. It highlights the shift towards natural language interfaces.

• Chapter 2: Harnessing the power of large language models

Covers LLMs, focusing on generative pretrained transformers (GPTs) for chat completions. It details connecting to OpenAI’s API, explores local LLM hosting with LM Studio, and introduces prompt engineering tactics like detailed queries and personas, vital for optimizing LLM responses and agent behavior.

• Chapter 3: Engaging GPT assistants

Delves into OpenAI’s GPT Assistants platform, demonstrating how to build, customize, and publish assistants via ChatGPT. It highlights practical applications like data science analysis with code interpretation and extending capabilities using custom actions and file uploads for a static knowledge base.

• Chapter 4: Exploring multi-agent systems

Introduces multi-agent platforms like AutoGen and CrewAI. It demonstrates conversational agents, group chat collaborations for complex tasks, and how to build structured agent crews. It emphasizes the benefits of internal feedback and evaluation among agents for robust problem-solving, and managing costs.

• Chapter 5: Empowering agents with actions

Explores agent actions via function calling, from OpenAI’s native functions to Microsoft’s Semantic Kernel (SK). It demonstrates how SK defines and orchestrates semantic plugins and native functions, enabling agents to interact with external APIs and services, creating adaptable and extensible AI applications.

• Chapter 6: Building autonomous assistants

Explores orchestrating multiple coordinated agents using behavior trees, a staple in robotics. It shows how to build and manage custom actions, enabling autonomous assistants to tackle complex challenges like code competitions and social media content creation, emphasizing self-driven task execution.

• Chapter 7: Assembling and using an agent platform

Introduces Nexus, an advanced platform for orchestrating multiple agents and LLMs. It covers developing agent profiles, personas, and powering the agent engine. It highlights how Nexus provides actions and tools, facilitating complex agentic workflows for diverse application development.

• Chapter 8: Understanding agent memory and knowledge

Focuses on Retrieval Augmented Generation (RAG) for extending LLM agent capabilities. It explores semantic search, document indexing with vector databases, and LangChain for RAG construction. It details implementing agent memory, providing crucial context and recall for robust, informed agent operations.

• Chapter 9: Mastering agent prompts with prompt flow

Emphasizes systematic prompt engineering using Microsoft’s Prompt Flow. It covers setting up prompt flows, defining agent profiles, and evaluating prompt performance via rubrics and grounding. It demonstrates automating prompt testing to achieve more robust and effective agentic behavior.

• Chapter 10: Agent reasoning and evaluation

Delves into agent reasoning techniques, including direct solution prompting, chain of thought (CoT), and prompt chaining. It explains how agents evaluate reasoning strategies during inference, enhancing their autonomous problem-solving capabilities and ensuring consistent, intelligent solutions for complex tasks.

• Chapter 11: Agent planning and feedback

Covers agent planning as a critical skill for achieving goals. It details sequential and stepwise planning processes and how feedback loops refine these plans. It integrates actions, memory, knowledge, reasoning, and evaluation into practical agentic systems for real-world problem-solving.

about Manning

Manning helps developers and tech professionals stay ahead in a fast-moving industry with expert-led books, videos, and projects. Learning never stops, but it’s hard to keep up, so we focus on content that’s practical, clear, and trusted. As an independent publisher, we adapt quickly, from pioneering early-access books to offering DRM-free eBooks. Our series, like “In Action” and “In a Month of Lunches”, reflect a commitment to making complex topics accessible.

Add to Cart

Customer Reviews

4.6 out of 5 stars 415

4.6 out of 5 stars 25

4.8 out of 5 stars 6

4.8 out of 5 stars 8

4.7 out of 5 stars 4

4.4 out of 5 stars 12

Price

$49.24$49.24 $50.66$50.66 $59.99$59.99 $54.14$54.14 $37.23$37.23 $44.08$44.08

Level of proficiency
Intermediate Intermediate Intermediate Intermediate Intermediate Advanced

About the reader
Readers need intermediate Python skills and some knowledge of machine learning. For data scientists and ML engineers. For intermediate Python programmers. For developers, engineers, and product managers. For data scientists and data analysts. For data scientists and machine learning engineers.

Special features
Includes liveBook with out built-in AI assistant. Includes liveBook with out built-in AI assistant. Includes liveBook with out built-in AI assistant. Includes liveBook with out built-in AI assistant. Includes liveBook with out built-in AI assistant. Includes liveBook with out built-in AI assistant.

Pages
368 456 688 328 232 520

Publisher ‏ : ‎ Manning
Publication date ‏ : ‎ March 25, 2025
Language ‏ : ‎ English
Print length ‏ : ‎ 344 pages
ISBN-10 ‏ : ‎ 1633436349
ISBN-13 ‏ : ‎ 978-1633436343
Item Weight ‏ : ‎ 1.25 pounds
Dimensions ‏ : ‎ 7.38 x 0.8 x 9.25 inches
Best Sellers Rank: #86,106 in Books (See Top 100 in Books) #15 in Natural Language Processing (Books) #39 in Artificial Intelligence Expert Systems #109 in Artificial Intelligence & Semantics
Customer Reviews: 4.2 4.2 out of 5 stars (34) var dpAcrHasRegisteredArcLinkClickAction; P.when(‘A’, ‘ready’).execute(function(A) if (dpAcrHasRegisteredArcLinkClickAction !== true) dpAcrHasRegisteredArcLinkClickAction = true; A.declarative( ‘acrLink-click-metrics’, ‘click’, “allowLinkDefault”: true , function (event) if (window.ue) ue.count(“acrLinkClickCount”, (ue.count(“acrLinkClickCount”) ); ); P.when(‘A’, ‘cf’).execute(function(A) A.declarative(‘acrStarsLink-click-metrics’, ‘click’, “allowLinkDefault” : true , function(event) if(window.ue) ue.count(“acrStarsLinkWithPopoverClickCount”, (ue.count(“acrStarsLinkWithPopoverClickCount”) ); );