finelybook
A Common-Sense Guide to AI Engineering: Build Production-Ready LLM Applications
Author(s): Jay Wengrow (Author), Katherine Dvorak (Editor)
- Publisher Finelybook 出版社: Pragmatic Bookshelf
- Publication Date 出版日期: May 26, 2026
- Language 语言: English
- Print length 页数: 340 pages
- ASIN: B0FY5MMX89
- ISBN-13: 9798888651933
Book Description
Want to build an LLM-powered app but don’t know where to begin? With this step-by-step guide, you can master the underlying principles of AI engineering by building an LLM-powered app from the ground up. Tame unpredictable models with prompt and context engineering. Use evals to keep them on track. Give chatbots the knowledge to answer anything a user wants to know. Equip agents with the tools and smarts to actually get the job done. By the end, you’ll have the intuition and the confidence to build on top of LLMs in the real world.
Fragmented documentation, obsolete tutorials, and frameworks that deliver a prototype but flop in production can make AI engineering feel overwhelming. But it doesn’t have to be that way. With real-world code and step-by-step instructions as your guide, you can learn to build robust LLM-powered apps from the ground up while mastering both the how and why of the most crucial underlying concepts.
Harness context engineering and retrieval systems to create AI assistants that understand your proprietary data. Create chatbots that answer organization-specific questions and help solve users’ issues. Design agents that conduct research, make decisions, and take action in the real world. Level up your prompt engineering and get an LLM to do your bidding—not its own. Use automated evals to keep constant tabs on your app’s quality while setting up guardrails to protect your users and organization. And implement observability systems that make it easy to debug your app when things do go wrong.
With a systematic approach grounded in the core principles of building AI apps for real users, you’ll easily evolve and adapt even as the hype and tools come and go.
Editorial Reviews
Editorial Reviews
Review
- Iyanuoluwa Ajao, Senior Applied AI Engineer, Dataligence Labs
This is the guide I wish I had when I started building with LLMs. It masterfully bridges the gap between theory and the practical realities of shipping AI products, teaching the crucial, hard-won lessons about iteration and trade-offs that define professional AI engineering.
- Nithin Singh Mohan, AI and Supercomputing Leader, Hewlett Packard Enterprise
Finally, a book that provides a clear explanation of how prompt engineering works. Jay Wengrow offers a no-nonsense guide to understanding important concepts of AI and ultimately a road map to change the world.
- Jon Glass, Software Engineer, NinjaTrader, LLC
Most LLM failures are not model problems—they are engineering problems. This book stands out by treating agents, tools, guardrails, observability, and evaluation as first-class engineering concerns, making it easier to reason about where systems fail and how to design them responsibly.
- Sree Ram Kishore Kumbham, Senior Software Engineer
I can’t recommend this book enough. It works equally well for people who are completely new to AI and want to get up to speed and those with fragmented knowledge who are looking for a more complete, structured understanding.
- Uberto Barbinin, Author of Process over Magic: Beyond Vibe Coding
Jay Wengrow has a knack for explaining complex ideas in a simple and intuitive way. His latest book will help anyone understand the ins and outs of AI engineering. I highly recommend this book to anyone looking to get into this field.
- Monsur Khan, Senior Associate Data Engineer
Given the limitations of basic LLM usage, I wouldn’t blame readers who quickly become disheartened. However, with advanced techniques, your optimism will grow. Surprisingly, very little code is involved, and much is achieved by fine-tuning the words supplied to the LLM, so a non-technical reader could pick this up.
- Nigel Lowry, Company Director and Principal Consultant, Lemmata
No programming knowledge is needed for the concepts in this book. The writing is clear and easy to follow. Chapters 2 and 3 alone will quickly inform technical and nontechnical readers about what LLMs really do and disabuse them of mistaken ideas about “intelligence” and LLM hallucinations. For those who can program, the book builds, chapter by chapter, upon a simple LLM chatbot toward one using RAG, evaluations, and other, more advanced techniques.
- Robert Ladyman, Director, File-Away, Limited
