What do you think?
Rate this book
Grokking AI Applications
Grokking AI Applications: An illustrated guide for programmers and other curious people shows you how to create AI applications like chatbots, agents, and systems customized to use your own data—even if you’ve never built one before! Supporting his explanations with graphics and using concrete examples and hands-on implementations, author Andrea De Mauro gets you thinking about system design and mental models rather than boilerplate code and syntax debugging. You’ll quickly focus on the right level: how to manage prompts, data, and application components to get the results you want.
You’ll start with a bare-bones chatbot, as you learn how to create good prompts and improve accuracy using Retrieval Augmented Generation (RAG). To help your applications live in the real world, the book discusses how to connect them to document collections, structured databases, and CRM tools. You’ll build on this foundation, creating your own agents and equipping them with tools for data analysis and complex reasoning. Reviewer Julien Pohie of Thoughtworks commented, “The emphasis on multi-agent orchestration aligns perfectly with modern engineering best practices.”
Step-by-step guidance, rich diagrams, and workflow summaries help you stay oriented, even through advanced material. To emphasize conceptual and design thinking, you’ll start each project using the low-code development tool Langflow. For readers who want to go deeper, every example also includes fully-annotated Python implementations. You’ll see the code, libraries, APIs, and data behind each application, along with practical advice on how to deploy and monitor your applications.
Compact by design, this fast-paced book includes eight fully illustrated chapters that build intuition through engaging, memorable, and relatable real-world scenarios. As you read, you’ll experience a shift from AI as the familiar conversational chatbot to AI as an essential part of your application and, further, to the design of multi-agentic teams with specialized roles and supervised coordination.
You’ll start with a bare-bones chatbot, as you learn how to create good prompts and improve accuracy using Retrieval Augmented Generation (RAG). To help your applications live in the real world, the book discusses how to connect them to document collections, structured databases, and CRM tools. You’ll build on this foundation, creating your own agents and equipping them with tools for data analysis and complex reasoning. Reviewer Julien Pohie of Thoughtworks commented, “The emphasis on multi-agent orchestration aligns perfectly with modern engineering best practices.”
Step-by-step guidance, rich diagrams, and workflow summaries help you stay oriented, even through advanced material. To emphasize conceptual and design thinking, you’ll start each project using the low-code development tool Langflow. For readers who want to go deeper, every example also includes fully-annotated Python implementations. You’ll see the code, libraries, APIs, and data behind each application, along with practical advice on how to deploy and monitor your applications.
Compact by design, this fast-paced book includes eight fully illustrated chapters that build intuition through engaging, memorable, and relatable real-world scenarios. As you read, you’ll experience a shift from AI as the familiar conversational chatbot to AI as an essential part of your application and, further, to the design of multi-agentic teams with specialized roles and supervised coordination.
- GenresArtificial Intelligence
272 pages, Paperback
Published July 1, 2026
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 4 of 4 reviews
September 26, 2026
هل تريد أن تبدأ في هندسة الذكاء الاصطناعي AI Engineering ولا تعلم من أين تبدأ؟
هل عندك رهبة أو حاجز نفسي يمنعك من البدء؟
هل تظن أنك تحتاج لتعلم أشياء كثيرة وهذا يثبطك عن البدء؟
هل تستخدم لغة برمجة غير بايثون وتظن أنك تحتاج لتعلمها أولا؟
هل تعتقد أن الانتقال من مهندس برمجيات software engineer إلى مهندس ذكاء اصطناعي AI engineer يحتاج لأن تنسى مهاراتك القديمة وتبدأ من الصفر؟
هل تعتقد أنك تحتاج لمذاكرة الكثير من الرياضيات لتبدأ في رحلة تعلم الذكاء الاصطناعي وتعلم الآفة الشاقة، حتى قبل أن تبدأ في تطوير أي تطبيق ذكي؟
هل تعتقد أن استخدامك للذكاء الاصطناعي في الcoding كافٍ؟
هل تظن أن بناء تطبيقات ذكية لا يحتاج أكثر من استخدام AI APIs؟
هل لا تعرف الفرق بين الAI Engineering والML Engineering؟
هل تظن أنك تحتاج لدورات Andrew NG في تعلم الآلة والتعلم العميق لتستطيع البدء؟
إذا كانت هذه اعتقاداتك، أو غيرها مما يمنعك من البدء، فإني أرشح لك هذا الكتاب:
Grokking AI Applications
الكتاب صدر منذ بضعة أشهر فقط، ربما في يوليو ٢٠٢٦ أو بعده، وهو مناسب للمبتدئين تماما، وفكرته ببساطة أن يشرح لك أهم المفاهيم التي تحتاجها في هندسة الذكاء الاصطناعي، ويبسطها بالأمثلة والرسومات التوضيحية، ثم عند التنفيذ يعطيك خيارين: استخدام منصات بصرية مثل Langflow و KNIME، وهي تعمل بطريقة السحب والإفلات للمكونات drag and drop على لوحة رسم canvas ويعطيك، هي low code platform، وكذلك خيار كتابة الكود باستخدام بايثون!
وينتقل من المفاهيم الأولية لبناء تطبيق دردشة ذكي، مرورا بال RAG ثم الAgents وبناء تطبيقات ذكية بناء على البيانات المسجلة في أنظمتك المؤسسية وليس الدردشة مع المستخدمين، وأخيرا نشر التطبيق ومراقبته.
الكتاب لا يغطي مفاهيم متقدمة مثل الevals والguardrails والfine-tuning، وغيرها، لكنه حقيقة كسر عندي حاجز البدء الجاد بدل العشوائية.
والمفارقة، رغم حداثة الكتاب فإني احتجت لإجراء بعض التغييرات على الأمثلة لتعمل على Langflow، الذي يتغير هو أيضا بسرعة، مثل بقية المجال كله!
والأجمل، أن الكتاب قصير، أقل من ٣٠٠ صفحة، على ما يحويه من رسومات كثيرة!
أرشحه بشدة!
هل عندك رهبة أو حاجز نفسي يمنعك من البدء؟
هل تظن أنك تحتاج لتعلم أشياء كثيرة وهذا يثبطك عن البدء؟
هل تستخدم لغة برمجة غير بايثون وتظن أنك تحتاج لتعلمها أولا؟
هل تعتقد أن الانتقال من مهندس برمجيات software engineer إلى مهندس ذكاء اصطناعي AI engineer يحتاج لأن تنسى مهاراتك القديمة وتبدأ من الصفر؟
هل تعتقد أنك تحتاج لمذاكرة الكثير من الرياضيات لتبدأ في رحلة تعلم الذكاء الاصطناعي وتعلم الآفة الشاقة، حتى قبل أن تبدأ في تطوير أي تطبيق ذكي؟
هل تعتقد أن استخدامك للذكاء الاصطناعي في الcoding كافٍ؟
هل تظن أن بناء تطبيقات ذكية لا يحتاج أكثر من استخدام AI APIs؟
هل لا تعرف الفرق بين الAI Engineering والML Engineering؟
هل تظن أنك تحتاج لدورات Andrew NG في تعلم الآلة والتعلم العميق لتستطيع البدء؟
إذا كانت هذه اعتقاداتك، أو غيرها مما يمنعك من البدء، فإني أرشح لك هذا الكتاب:
Grokking AI Applications
الكتاب صدر منذ بضعة أشهر فقط، ربما في يوليو ٢٠٢٦ أو بعده، وهو مناسب للمبتدئين تماما، وفكرته ببساطة أن يشرح لك أهم المفاهيم التي تحتاجها في هندسة الذكاء الاصطناعي، ويبسطها بالأمثلة والرسومات التوضيحية، ثم عند التنفيذ يعطيك خيارين: استخدام منصات بصرية مثل Langflow و KNIME، وهي تعمل بطريقة السحب والإفلات للمكونات drag and drop على لوحة رسم canvas ويعطيك، هي low code platform، وكذلك خيار كتابة الكود باستخدام بايثون!
وينتقل من المفاهيم الأولية لبناء تطبيق دردشة ذكي، مرورا بال RAG ثم الAgents وبناء تطبيقات ذكية بناء على البيانات المسجلة في أنظمتك المؤسسية وليس الدردشة مع المستخدمين، وأخيرا نشر التطبيق ومراقبته.
الكتاب لا يغطي مفاهيم متقدمة مثل الevals والguardrails والfine-tuning، وغيرها، لكنه حقيقة كسر عندي حاجز البدء الجاد بدل العشوائية.
والمفارقة، رغم حداثة الكتاب فإني احتجت لإجراء بعض التغييرات على الأمثلة لتعمل على Langflow، الذي يتغير هو أيضا بسرعة، مثل بقية المجال كله!
والأجمل، أن الكتاب قصير، أقل من ٣٠٠ صفحة، على ما يحويه من رسومات كثيرة!
أرشحه بشدة!
August 31, 2026
Review — from a Senior SysAdmin working with Linux and AI tooling
I've been running Linux infrastructure for a long time, and lately a good chunk of my job has involved figuring out where AI tooling actually fits into the automation stack.
Grokking AI Applications, and specifically this chapter on tools and agents, is the clearest explanation I've come across of what an "agent" actually is under the hood, and why that distinction matters operationally.
What I appreciated most as a sysadmin:
It demystifies the black box. The book walks through the literal TOOL_CALL exchange between the LLM and the surrounding framework — you see the prompt, the tool list, the response format, and the loop that ties it together. After reading this, "agentic AI" stops being marketing language and becomes just another process loop you could reason about, debug, or write yourself.
The tool-as-function framing maps directly onto sysadmin thinking. A tool is a described function with parameters and a return value — that's an API contract. Anyone who's written a runbook, a CLI wrapper, or a small automation script will recognize the shape immediately.
For a systems person who's used to precise, deterministic behavior, this chapter respects that instinct — it explicitly acknowledges the probabilistic nature of LLM reasoning while showing how tools bring back the deterministic guarantees (the calculator example makes this point perfectly: don't make the LLM "guess" math, give it a real calculator).
Bottom line: this is the book I'd hand to another sysadmin or platform engineer who keeps hearing "agents" in meetings and wants to actually understand — and build — the thing, not just talk about it.
I've been running Linux infrastructure for a long time, and lately a good chunk of my job has involved figuring out where AI tooling actually fits into the automation stack.
Grokking AI Applications, and specifically this chapter on tools and agents, is the clearest explanation I've come across of what an "agent" actually is under the hood, and why that distinction matters operationally.
What I appreciated most as a sysadmin:
It demystifies the black box. The book walks through the literal TOOL_CALL exchange between the LLM and the surrounding framework — you see the prompt, the tool list, the response format, and the loop that ties it together. After reading this, "agentic AI" stops being marketing language and becomes just another process loop you could reason about, debug, or write yourself.
The tool-as-function framing maps directly onto sysadmin thinking. A tool is a described function with parameters and a return value — that's an API contract. Anyone who's written a runbook, a CLI wrapper, or a small automation script will recognize the shape immediately.
For a systems person who's used to precise, deterministic behavior, this chapter respects that instinct — it explicitly acknowledges the probabilistic nature of LLM reasoning while showing how tools bring back the deterministic guarantees (the calculator example makes this point perfectly: don't make the LLM "guess" math, give it a real calculator).
Bottom line: this is the book I'd hand to another sysadmin or platform engineer who keeps hearing "agents" in meetings and wants to actually understand — and build — the thing, not just talk about it.
September 8, 2026
I really enjoyed reading Grokking AI Applications. What I liked most is that it doesn’t try to overwhelm you with AI terminology or get lost in the latest frameworks. Instead, it focuses on how to actually think about building GenAI applications.
The progression of the book works really well. It starts with the basics of how LLM-based applications work and gradually moves into prompting, RAG, tools, agents, multi-agent workflows, and integrating AI with real-world data. The examples make these concepts much easier to understand, especially if you have some technical background but are still trying to connect all the pieces of the GenAI ecosystem.
I particularly liked the emphasis on understanding the architecture and mental models behind an AI application rather than simply copying code. Frameworks and libraries are changing so quickly, so learning the underlying patterns feels much more valuable in the long run.
The progression of the book works really well. It starts with the basics of how LLM-based applications work and gradually moves into prompting, RAG, tools, agents, multi-agent workflows, and integrating AI with real-world data. The examples make these concepts much easier to understand, especially if you have some technical background but are still trying to connect all the pieces of the GenAI ecosystem.
I particularly liked the emphasis on understanding the architecture and mental models behind an AI application rather than simply copying code. Frameworks and libraries are changing so quickly, so learning the underlying patterns feels much more valuable in the long run.
This entire review has been hidden because of spoilers.
Read
September 1, 2026This is one of the better AI books I've read recently. What I appreciated most was that it spends time on the fundamentals instead of jumping straight into the latest frameworks and buzzwords.
The explanations of the core concepts are very clear and approachable, and I found those chapters to be the strongest part of the book. They provide the kind of foundation that helps you understand why things work, not just how to use a particular tool.
Whether you're starting to explore AI applications or already have some experience, there's a lot here to learn from. I enjoyed reading it and would definitely recommend it to all who want a solid, practical introduction to the field, and also to those who want to deploy their first complex applications based on low code tools.
The explanations of the core concepts are very clear and approachable, and I found those chapters to be the strongest part of the book. They provide the kind of foundation that helps you understand why things work, not just how to use a particular tool.
Whether you're starting to explore AI applications or already have some experience, there's a lot here to learn from. I enjoyed reading it and would definitely recommend it to all who want a solid, practical introduction to the field, and also to those who want to deploy their first complex applications based on low code tools.
Displaying 1 - 4 of 4 reviews