 |
VOOZH | about |
|
VOOZH | about |
Download the free Kindle app and start reading Kindle books instantly on your smartphone, tablet, or computer - no Kindle device required.
Read instantly on your browser with Kindle for Web.
Using your mobile phone camera - scan the code below and download the Kindle app.
OK
This book is a practical resource designed to help developers master the art of building sophisticated AI agents. As artificial intelligence evolves from simple reactive programs to autonomous entities capable of understanding context and making complex decisions, this book provides the essential Design Patterns and proven techniques needed to construct intelligent systems effectively. Each of the 21 Design Patterns represents a fundamental building block for creating agents that can perceive their environment, make informed decisions, and execute actions autonomously.
Agentic Design Patterns: A Hands-On Guide to Building Intelligent Systems is structured as a comprehensive hands-on guide, with each chapter dedicated to a single agentic pattern. Within each chapter, you will find a detailed pattern overview, practical applications and use cases, one or more hands-on code example, and key takeaways for quick review. From foundational concepts such as Prompt Chaining and Tool Use to advanced topics like Multi-Agent Collaboration and Self-Correction, readers will gain practical knowledge they can immediately apply. While the chapters build on each other, you can also use the book as a handy reference, jumping to patterns that address your specific challenges.
To provide a tangible "canvas" for the code examples, this guide utilizes three prominent agent development frameworks: LangChain and its extension LangGraph, which offer a flexible way to build complex operational sequences; Crew AI, which provides a structured framework for orchestrating multiple agents; and the Google Agent Developer Kit (Google ADK), which offers tools for building, evaluating, and deploying agents. By showcasing examples across these tools, you will gain a broad understanding of how these patterns can be applied in any technical environment.
Building effective agentic systems requires more than just a powerful language model; it demands structure and design. Agentic patterns provide reusable, battle-tested solutions to common challenges, much like design patterns in software engineering. They offer a common language that makes an agent's logic clearer, more maintainable, and more robust. By the end of this journey, you will possess both the theoretical understanding and the practical skills to implement these 21 essential patterns, enabling you to build more intelligent, capable, and autonomous systems on your chosen development canvas.
Included in the book are
Antonio Gulli is a highly experienced Senior Director at Google, currently leading the Engineer Director role in the Office of CTO.
All author royalties will be donated to charity
This book is a practical resource designed to help developers master the art of building sophisticated AI agents. As artificial intelligence evolves from simple reactive programs to autonomous entities capable of understanding context and making complex decisions, this book provides the essential patterns and proven techniques needed to construct intelligent systems effectively. Each of the 21 patterns represents a fundamental building block for creating agents that can perceive their environment, make informed decisions, and execute actions autonomously.
Agentic Design Patterns: A Hands-On Guide to Building Intelligent Systems is structured as a comprehensive hands-on guide, with each chapter dedicated to a single agentic pattern. Within each chapter, you will find a detailed pattern overview, practical applications and use cases, a hands-on code example, and key takeaways for quick review. From foundational concepts such as Prompt Chaining and Tool Use to advanced topics like Multi-Agent Collaboration and Self-Correction, readers will gain practical knowledge they can immediately apply. While the chapters build on each other, you can also use the book as a handy reference, jumping to patterns that address your specific challenges.
To provide a tangible "canvas" for the code examples, this guide utilizes three prominent agent development frameworks: LangChain and its extension LangGraph, which offer a flexible way to build complex operational sequences; Crew AI, which provides a structured framework for orchestrating multiple agents; and the Google Agent Developer Kit (Google ADK), which offers tools for building, evaluating, and deploying agents. By showcasing examples across these tools, you will gain a broad understanding of how these patterns can be applied in any technical environment.Building effective agentic systems requires more than just a powerful language model; it demands structure and design. Agentic patterns provide reusable, battle-tested solutions to common challenges, much like design patterns in software engineering. They offer a common language that makes an agent's logic clearer, more maintainable, and more robust. By the end of this journey, you will possess both the theoretical understanding and the practical skills to implement these 21 essential patterns, enabling you to build more intelligent, capable, and autonomous systems on your chosen development canvas.
The cover image is AI-generated.
Antonio Gulli is a highly experienced Senior Director at Google, currently leading the Engineer Director role in the Office of CTO. With over 30 years of relevant experience, Antonio is a well-known figure in the industry, with a strong background in AI, Search, and Cloud technologies. Antonio has extensive experience managing technical teams and providing Google Cloud technology solutions across EMEA industry. He has previously served as Site Lead and Engineering Director for Google, where he managed cloud teams and led cross-functional teams in strong collaboration with international sites and sales functions. Antonio has also authored the book "Deep Learning for Keras" to increase science culture awareness. Antonio's educational background is impressive, with a Ph.D. in Computer Science from the University of Pisa and a Master's degree in Engineering from the same university. He also holds a Master's degree in Practice Engineering from the University of Pisa and a Bachelor's degree in Computer Science from the University of Pisa. Antonio's technical expertise includes Senior Software Engineer, AI, Search, Cloud Kubernetes, Keras, and Deep Learning. He is also a Board Member and VC Advisor, making him a valuable asset to any organization.
Antonio has a passion for establishing and managing global technological talent, for innovation and execution. His core expertise is in cloud computing, deep learning, and search engines. Currently, he serves as Eng Director for the Office of the CTO, Google Cloud. Previously, he served as Google Warsaw Site leader, more than doubling the size of the engineering site.
So far, Antonio has been lucky enough to gain professional experience in 4 countries in Europe and has managed teams in 6 countries in EMEA and U.S: In Amsterdam, as Vice President for Elsevier, a leading scientific publisher; in London, as Engineering Site Lead for Microsoft working on Bing, Search; in Italy and U.K, as CTO, Europe and UK for Ask.com; and in several co-funded startups including one of the first web search companies in Europe.
Antonio has co-invented a number of technologies for search, smart energy, environment, and AI, with 20+ patents issued/applied, and he has published several books about coding and machine learning, also translated into Japanese and Chinese. Antonio speaks Spanish, English, Italian, and he is currently learning Polish and French. Antonio is a proud father of 2 boys, Lorenzo, 18, Leonardo, 13, and a little queen Aurora, 9 years.
Customer Reviews, including Product Star Ratings help customers to learn more about the product and decide whether it is the right product for them.
To calculate the overall star rating and percentage breakdown by star, we don’t use a simple average. Instead, our system considers things like how recent a review is and if the reviewer bought the item on Amazon. It also analyzed reviews to verify trustworthiness.
Learn more how customers reviews work on AmazonEager to delve into the realm of Agentic AI?
21+ chapters of focused insight, covering every facet you'd encounter within Agentic AI.
Excellent book, I would have given 5 stars except the code examples are unreadable because of terrible formatting. Please fix in the next version!
This book, if I could force people to, would be the one resource I would recommend to catch everyone up to our current point in time.
To me it is targeted to the non-technical or the people that understand some concepts and not others or those that want to feel ok knowing that they have the basics down.
I wouldn't say this is for a data scientist, it is for those that want to have a conversation with a data scientist. For someone that wants to have enough of a general overview to dive in and have intelligent discussions for their business and personal life incorporating Agentic AI.
Sure, things may change quickly after the publish date but I agree that enough in the industry has consolidated that an AI catch-up recap book is merited and to me, this is it. 😊 These concepts will still exist as the platforms and vendors evolve on top of it. But you need to understand the baseline elements first.
I also find it very easy to read.
Well-written and good information, but the code examples are horrendous; there's no vertical spacing, syntax highlighting, or even a printing of the execution results.
Great Book! Very easy to read. It’s written very easy to understand. It’s not like most “Boring Tech manuals”. It’s written in a way you understand the what and the why. And in my opinion that’s what makes it so great. It’s not “Bland”. I’m in college and have taken an interest to agentic AI. I’ve read a lot of books and this so far is my favorite. If you want to “Understand”, then this is the book for you.
Great Book! Very easy to read. It’s written very easy to understand. It’s not like most “Boring Tech manuals”. It’s written in a way you understand the what and the why. And in my opinion that’s what makes it so great. It’s not “Bland”. I’m in college and have taken an interest to agentic AI. I’ve read a lot of books and this so far is my favorite. If you want to “Understand”, then this is the book for you.
This is definitely one of my favorite books of the year. It has become a key tool in my learning and understanding of emerging technologies related to agent systems. The patterns described not only include use cases but also code proposals for their implementation. The prologue is a good introduction to AI Systems and Agents, and Part 2 (the supplement) complements what's needed for studying the patterns. I highly value these kinds of resources. Highly recommended.
This is definitely one of my favorite books of the year. It has become a key tool in my learning and understanding of emerging technologies related to agent systems. The patterns described not only include use cases but also code proposals for their implementation. The prologue is a good introduction to AI Systems and Agents, and Part 2 (the supplement) complements what's needed for studying the patterns. I highly value these kinds of resources. Highly recommended.
It's a good high level book, but it doesn't go deep into actual agent design patterns. "Error handling" isn't a design pattern to me. Would like to have seen real production patterns for building agents
I would recommend this book for anyone getting started building Agents. I find myself rushing to my development environment after completing each chapter to experiment with the patterns and core design principles. Well organized and easy to follow as well. The book is careful not to overemphasize only Google's ecosystem and has examples using multiple frameworks for each pattern.
The consistent structure across patterns, especially the ‘At a Glance’ section at the end, really helped cement the concepts for me. Given that a lot of things are getting added we might have an updated version of this in the times ahead.
Antonio Gullí's Agentic Design Patterns: A Hands-On Guide to Building Intelligent Systems is an exceptional resource. I found the print version so valuable that I also purchased the PDF for quick reference. All of my agentic systems are now architected based on the foundational knowledge gained from this book. Gullí clearly explains the fundamental principles of agentic AI, successfully cutting through the hype and noise of the current AI landscape. It truly captures the essence of building intelligent systems.
Muy didactico y al grano
Agentic Design Patterns is a concise, practical guide to building reliable AI agents. It breaks down 21 repeatable patterns with clear explanations and runnable code, helping you move from toy LLM prototypes to robust, structured agent systems. Great for engineers and tech leaders who want a solid architectural foundation for multi-agent workflows, planning, tools, and memory. A bit technical for beginners, but extremely useful for anyone building real AI products
Das Buch ist für mich mehr ein CookBook als eine Sammlung von Pattern, aber es werden viele Herausforderungen die bei einem produktiven einsatz von AI-Agenten auftreten mit Beispielen geschildert. Meistens beziehen sich diese auf eines der folgenden Frameworks: LangChain, LangGraph, CrewAI & Googles ADK. Die Beispiele sind sehr kompakt gehalten mit dem Fokus auf die wichigsten Prinzipien. Für mich was es nicht nur en guter Überblick sondern ist auch ein kleines Nachschlagewerk in der täglichen Arbeit geworden.
