Books

Bestselling book on building LLMs. A practical, project-driven manual for engineers who want to understand how modern language models are built — and where they fail — by writing every layer themselves. From a scalar autograd engine to RLHF to fused specialists, in 36 hands-on projects with deliberate sabotage experiments. Build it. Break it. Measure it.

It's never been easier to build an AI agent — and never been harder to make one that actually works. This book takes you from language model foundations to production-ready multi-agent systems with the depth to predict failure before it happens, engineer graceful degradation over catastrophic failure, and take absolute architectural ownership. Get the paperback from amazon.

Top-k is not relevance, retrieved text is not evidence and an LLM judging another LLM is not verification. Beyond “Chunk and Pray” shows how to build RAG that answers through a verified knowledge graph, preserves exact numbers, cites its sources and abstains when it cannot prove the answer.

Your pilot went well. That was never the question. In a regulated industry, an AI system is acceptable only when it can prove what it did: which source it used, what stopped it acting, why it decided as it did eleven months ago. A field guide for the executives who have to sign.

Mastering Claude Code montre comment collaborer avec des agents d’IA pour écrire du code, automatiser des flux de travail et réaliser des projets d’envergure. De la configuration aux bonnes pratiques d’ingénierie logicielle, ce guide pratique explique comment les logiciels modernes sont conçus en 2026.

Learn how to build, run, and optimize llama.cpp from the ground up. This book covers everything from compiling the code and working with GGUF models to deploying fast, production-ready local LLM inference.

Learn Claude Code by building real projects. This hands-on companion turns the Claude Code Masterclass workshop into a practical self-paced guide for planning, coding, testing, reviewing, refactoring, and shipping software with AI.

A language model predicts tokens. An agent acts—and must be held accountable. Learn to replace “prompt and pray” with governed tools, geometric memory, independent verification and auditable runtime controls.

Learn how to build reliable AI agents with PydanticAI, from simple chatbots to production-ready multi-agent systems. With practical examples, clear explanations, and hands-on projects, this book helps you write AI applications that are structured, testable, and easy to maintain.

Go beyond prompts and learn how to build AI systems that hold up in production. This book shows how to make context the foundation of reliable LLM applications, covering practical patterns, real trade-offs and proven engineering techniques with clear examples you can put to work right away.

Unlock the full potential of Moonshot AI's groundbreaking Kimi K3 with practical prompting techniques, real-world examples and production-ready strategies. Whether you are building AI applications, conducting research or deploying autonomous agents, this guide helps you get better results from one of the world's most capable open models.

Envoy Proxy is the foundation of modern cloud-native networking, powering service meshes, API gateways and AI infrastructure. This practical guide shows you how to design, deploy and operate Envoy in production with expert guidance, real-world configurations and advanced patterns for scalable, resilient systems.

PyTorch Deep Dive is a practical guide to mastering modern deep learning with PyTorch. From core concepts to advanced topics like transformers, diffusion models, and production deployment, it combines clear explanations, hands-on examples, and real-world best practices to help you build and scale AI applications with confidence.

Build AI agents that do real work with the Google Agent Development Kit (ADK), Python, and Google Cloud. Through complete, runnable examples, you'll learn how to build, orchestrate, and deploy production-ready multi-agent systems with practical skills you can apply from day one.

Build smarter AI systems that go beyond the limits of large language models. Retrieval-Augmented Generation is a practical guide to designing, implementing, and scaling RAG applications with modern retrieval techniques, vector databases, and real-world deployment strategies.