[Book Review] Amazon Bedrock AgentCore Practical Introduction: A Book for Building and Operating AI Agents on AWS

Introduction

Hello, I'm Jinno from the consulting department, and I love Amazon Bedrock AgentCore.

This time, I'd like to introduce the book Amazon Bedrock AgentCore Practical Introduction, which will be released on May 29, 2026!

https://www.sbcr.jp/product/4815641238/

I was fortunate enough to be given the opportunity to read the manuscript as a technical reviewer for this book from the writing stage. Throughout the review process, I repeatedly felt that this was an amazing book packed with knowledge about my beloved AgentCore.

This is my first time writing a book review blog, but as someone who has read through every chapter, I hope to share my honest impressions!

Book Overview

The three authors are also the authors of the bestselling previous work, Amazon Bedrock Generative AI App Development Introduction.

I always deeply respect these individuals who are active at the forefront of the generative AI and AI agent field. When I first read "Amazon Bedrock 生成AIアプリ開発入門", I understood nothing about Bedrock and was able to catch up in an easy-to-understand way through that book, so I had been privately admiring the three of them ever since. I never dreamed that I would have the opportunity to review their follow-up book, and I'm truly grateful that such a day has come.

Target Readers

The cover of this book lists the following as "Target Readers":

• Those who want to learn how to build efficiently on AWS
• Those who want to take on the challenge of developing high-performance AI agents
• Those who want to learn through hands-on practice
• Those who want to learn systematically from the overall structure

While IT engineers and developers are the primary audience, the book is also structured with consideration for those who have become interested in in-house development through AI. There is plenty of sample code, and since tools like ChatGPT have web search functionality, even those who don't normally do development can steadily advance with understanding by leveraging AI. Actually building things is the best way to learn.

A sample code repository is also available, so make great use of it as a reference when building things yourself!

https://github.com/minorun365/agentcore-book

Table of Contents

The book is structured into 4 parts, 16 chapters, plus appendices.

Part 1: Fundamentals

• Chapter 1: Generative AI Basics and Introduction to Amazon Bedrock
• Chapter 2: Introduction to AI Agents

Part 2: Strands Agents

• Chapter 3: Introduction to Strands Agents
• Chapter 4: [Hands-on] Let's Build a Research Agent

Part 3: AgentCore

• Chapter 5: Overview of AgentCore and Its Main Feature "Runtime"
• Chapter 6: "Memory" for Managing Memories
• Chapter 7: "Identity" for Controlling External Authentication
• Chapter 8: "Gateway" for Bundling Tools
• Chapter 9: "Policy" for Controlling Tool Usage
• Chapter 10: "Built-in Tools" Unique to the Cloud
• Chapter 11: "Observability" for Visualizing Operational Status
• Chapter 12: "Evaluation" for Automatically Assessing Quality
• Chapter 13: [Hands-on] Let's Build a Full-Stack Agent

Part 4: Advanced Applications

• Chapter 14: Leverage Internal Data for Agents with RAG
• Chapter 15: [Hands-on] Let's Build an Ambient Agent with CDK
• Chapter 16: Introducing AI Agents into Your Business

Appendices

• Appendix 1: Preparing Your AWS Account
• Appendix 2: Setting Up the Development Environment
• Appendix 3: Bedrock Service Quotas

The AgentCore section in Part 3 alone accounts for approximately 40% of the entire book. True to its title of "AgentCore Practical Introduction," a key feature is that each AgentCore function is covered carefully with one dedicated chapter.

My Personal Recommended Highlights!

Full Color with Abundant Diagrams — Exceptionally Easy to Understand

The first thing you notice when reading the book is the sheer volume and quality of the diagrams.

AgentCore covers a wide range of functions, and organizing the individual features as well as their relationships can be quite challenging...

The book carefully explains these concepts with original diagrams, allowing you to intuitively grasp how each function works and how they interact.

Even parts that are difficult to understand from the official documentation alone become clear with the combination of diagrams and text — those "oh, so that's what it means" moments come naturally, which is incredibly helpful.

Truly Keeping Up with the Latest Updates

There are many instances where I thought, "they've incorporated even this update..." — I was simply impressed.

While AgentCore and Strands Agents are rapidly evolving services, this book continues to incorporate the latest updates. New features such as AgentCore Payments (payment functionality from agents), AgentCore Optimization (continuous improvement based on evaluation results), HTTP target support for Gateway, and the OBO (On Behalf Of) flow for Identity are reflected in columns and body text, and I felt the authors' sheer determination throughout.

This field changes so rapidly that having everything systematically compiled as of May 2026 is itself tremendously valuable, and no other book keeps up with developments to this extent.

Hands-on That Extends to SaaS Integration

This is my personal top recommendation!

In Chapter 13 of this book, you can experience a truly "full-stack" hands-on by building a calendar assistant that integrates with the Google Calendar API via OAuth, managing credentials with AgentCore Identity, and deploying all the way to a frontend with Next.js + Amplify.

When actually implementing AI agents in business settings, frontend implementation and authentication integration with external SaaS are unavoidable challenges. Hands-on content that directly tackles these issues is rarely found in other books or online resources. While 3LO leveraging Identity can be complex, this hands-on breaks it down in a very understandable way, allowing you to build it with full comprehension.

The frontend is also built with a modern UI, making it suitable for incorporation into actual business settings, which is great.

Highlights by Section

Part 1: Fundamentals — Grasping the Big Picture of AI Agents

Chapter 1 starts from the basics of generative AI and Amazon Bedrock, and even includes a hands-on using the Converse API / ConverseStream API. The structure is such that even those encountering Bedrock for the first time can read through it with confidence.

The AI agent introduction in Chapter 2 covers a wide range of topics, from the ReAct pattern and agent design patterns to commonly appearing standard protocols like MCP/A2A. With abundant diagrams and clear explanations, just this chapter alone gives you a fairly clear picture of "what AI agents are."

Part 2: Strands Agents — Understanding the Framework

You can learn step by step from the basic usage of Strands Agents through to the implementation of multi-agent patterns.

The hands-on in Chapter 4 involves building a research agent using the Swarm pattern (a pattern where multiple agents cooperate with each other). The mechanism by which five agents — PlanAgent, WhatsNewSearchAgent, RetrievalAgent, ReviewAgent, and OrchestratorAgent — cooperate and produce output is fascinating in a near-futuristic way, seeing how agents communicate with each other to deliver results. Practical samples like this for Swarm are rare, so it's very informative. Using different models — Opus, Sonnet, and Haiku — depending on each agent's role, and setting prompt caching to reduce costs, are touches that feel genuinely practical.

Part 3: AgentCore — The Heart of the Book

This is the thickest part of the book, explaining each of AgentCore's 8 functions one chapter at a time.

Each chapter follows a consistent structure, organized as: concept explanation → code examples → pricing. The fact that pricing is addressed in each chapter is a welcome point, preventing concerns about "I want to try it, but what about costs..."

As this book also explains, AgentCore is feature-rich and you don't need to use every feature — it's best to adopt the features you need in an à la carte fashion. Therefore, it's important to understand each function individually, so having them explained carefully one by one is very helpful. Even functions like Gateway, whose benefits may not be immediately obvious, are explained carefully — definitely worth checking out.

Part 4: Advanced Applications — The Path to Business Implementation

Chapter 14 on RAG delves into leveraging internal data using Bedrock Knowledge Base, and Chapter 15 covers building an ambient agent using CDK, stepping into more practical territory.

AI agents + RAG continues to be in demand for document search, and the essential configurations you'll want to know are explained carefully. Additionally, methods for improving search accuracy in Knowledge Bases, such as query decomposition and reranking, are introduced, allowing you to implement them as needed — which is very helpful. It's not just about building and you're done; accuracy verification and improvement are also essential.

The "3-step recommended RAG implementation procedure" introduced in a column is also practical, organizing the flow as: first build simply with S3 Vectors → gradually introduce Advanced RAG → measure accuracy quantitatively with evaluation. Since it's easy to get lost on where to start with RAG, it's important to first try out the effects quickly and inexpensively.

The hands-on for ambient agents in Chapter 15 is also a highlight. Simply by uploading a receipt image to S3, the agent automatically handles everything from image analysis to expense categorization, sending approval request emails, and even recording in Confluence after approval. Rather than giving instructions through chat, this operates autonomously in the background triggered by events, and since integration with SaaS is often used in actual work, it's a great reference.

Furthermore, this hands-on uses AWS CDK to define infrastructure as code, deploying resources such as AgentCore Runtime, S3, DynamoDB, and Lambda together. IaC is indispensable for production deployment, and being able to reuse infrastructure definitions you've created once in other projects is also a major benefit. Since the book explains CDK fundamentals (such as the App/Stack/Construct hierarchy) from scratch, even CDK beginners can tackle it with confidence.

Chapter 16 is written from an organizational and business perspective on "how to introduce AI agents into business operations." Personally, this chapter resonated with me more than any other.

In my own work supporting customers with AI agent adoption, it's not uncommon to start from a state where "what AI agents can actually do" is vaguely understood. This book introduces the idea of viewing AI agents not as automation tools like RPA, but as "a capable newly hired subordinate." If you prepare the business rules and procedures as prompts and documents, and set up the necessary tool access permissions, the agent will handle work appropriately. This analogy is easy to understand and something I want to keep in mind at all times.

The book also emphasizes the importance of "narrowing the scope and first showing something that works." Applications leveraging LLMs involve uncertainty, so trying to build a large-scale system from the start will lead to struggles with the gap between expectations and actual output. Even at 50% completion, first build something that works and show it to stakeholders, accumulate "small successes," and gradually get a feel for how to leverage AI while making the goal of AI utilization more concrete. I strongly empathize with this approach from my own experience.

Another thing that resonated with me is that many implementation failures are not technical challenges but the problem that "nobody uses it." Integrating it into users' daily workflows, and making it possible to call the agent from UI interfaces like Slack or email — it would truly be a shame to build something that goes unused...!

I hope everyone — engineers and non-engineers alike — will read this content.

Who This Book Is Recommended For

• Those who want to build AI agents on AWS but don't know where to start
• Those who want to learn Strands Agents and AgentCore systematically
• Those who want to acquire knowledge that covers not just building AI agents but also operating them
• Those who want to learn by getting hands-on experience with actual code
• Those who are in a position to propose AI agent adoption to customers

Since the content covers a wide range from theoretical learning to actual code implementation, while the main audience is engineers, the content is accessible enough for non-engineers to dive into while leveraging generative AI. For those who have decided to build AI agents on AWS — please give it a read!

Closing

There is no other Japanese-language book that has compiled the construction and operation of AI agents centered around the feature-rich AgentCore into such a practical and systematic form. The structure — carefully explaining the basics of generative AI and each AgentCore feature in individual chapters, while combining them holistically through hands-on exercises — gave me a sense of understanding deepening step by step, which made reading it a pleasure. For me personally, it served as a great review, and it's a book I want to keep coming back to. Lately, I've been reading it every morning during my commute on the train.

2026 has the potential to become the inaugural year of AI agent development. For those who are considering introducing self-built AI agents into their business during this turbulent year, I believe this is the book you should pick up first!
Let's catch up with this book and go all in on creating AI agents leveraging AgentCore!!!
I'll also keep sharing the latest AgentCore information through my blog, not to be outdone!

https://dev.classmethod.jp/author/yjinn/

Thank you so much for reading this article to the end! Nothing would make me happier than if even a little of this book's appeal has come through!