Books

Legacy modernization is an evidence problem before it is a code-generation problem. Use Claude Code to recover hidden behavior, build a verification harness, and move critical systems in controlled, reversible slices without handing production decisions to AI. Includes 26 practical chapters, 86 diagrams, and a runnable companion lab.

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.

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.

Learn to build production-ready LLM applications with DSPy through hands-on tutorials, complete runnable examples, and real-world projects. Master DSPy's core abstractions and create AI systems that improve with data instead of endless prompt tweaking.

Written for people who never asked to become AI users and now are. Not a tour of the technology, but a practical guide to working with it well — the habits that make good results repeatable, and the judgement to know when to check.

A vendor-neutral, mechanism-level field guide to operating and extending agentic coding harnesses (538 manuscript pages).

The hardest part of building AI is not the model. It is everything around it. The Art of Harness Engineering is a practical guide to turning AI prototypes into reliable products. It covers testing, guardrails, observability and governance, giving you the tools to build AI systems people can trust and organizations can run with confidence.

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.

Building fast LLM inference is about far more than turning the right knobs. This book takes you inside vLLM and the systems behind it, showing how memory, scheduling, GPUs and distributed serving shape real-world performance. Learn how to measure what matters, find bottlenecks and build inference infrastructure that scales without wasting money.

Software development is changing fast, and Claude Code is at the center of that shift. Learn how to work effectively with AI agents to write code, automate workflows, and build larger projects with confidence. From setup and prompt design to real-world engineering practices, this book provides a practical guide to modern software development in 2026.

A hands-on guide to downloading, running, serving, and maintaining open-weight LLMs on your own machine (489 manuscript pages).

Mastering Qdrant for RAG Applications is your practical guide to building production-ready RAG systems with the leading open-source vector database. Learn how to design, optimize, and scale high-performance vector search using Qdrant through clear explanations, real-world examples, and hands-on code.

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.

Most AI systems can talk, but few can actually do. This book shows you how to build AI agents that reliably use tools, call APIs and automate real workflows. Using DSPy, Pydantic AI, the Claude Agent SDK, the OpenAI Agents SDK and Google ADK, you'll learn practical patterns for building reliable agents that work in production.

Learn how large language models work instead of relying on black-box APIs. Building Large Language Models from Scratch takes you through training a Transformer model in PyTorch, from raw text to a working inference API, covering tokenization, attention, distributed training, and alignment along the way.