Books

Eight agents, zero coordination, one identical error. That's not a coincidence. It's a signature. Learn to read the five families of failure behaviors in multi-agent systems, reproduce each one in TypeScript, and turn every bias into a CI assertion before it ships.

From your first JAX script to large-scale AI systems, this book shows how to write faster, cleaner Python for modern computing. Learn the ideas behind JAX through practical examples, real projects and clear explanations that help you build everything from scientific simulations to distributed machine learning.

Reclaim your week from the Admin Tax. PRINCE2+AI: The Modern Project Manager's Playbook shows you how to delegate governance to AI, reclaim strategic judgement, and become the AI Editor. Master the workflow—or be replaced by those who do.

A hands-on, failure-first guide to evaluating LLM agents, RAG, tool use, grounding, and production release gates—with executable Python examples and tests.

AI coding agents can write code fast, but they need codebases built for collaboration. This book shows experienced engineers how to design, test and maintain software that works seamlessly with tools like Copilot, Cursor and Claude Code. Practical patterns, real projects and proven workflows help you build systems that scale with AI.

AI agents become truly powerful when they can reason, adapt and recover instead of following a fixed sequence of steps. This book shows you how to design intelligent agent systems with computational graphs, giving you the tools to build scalable, reliable applications that can handle real-world complexity with confidence.

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.

Every news feed is full of AI buzzwords: Transformers, tokens, embeddings, context windows, hallucinations, objective functions. Yet most explanations are either dense academic textbooks or empty marketing fluff. ☕ Coffee Break AI is your practical guide to AI. Written in plain English with warm real-world analogies. It breaks down the core mechanisms of AI into 40 bite-sized chapters.

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.

The future of AI depends on how we measure it. This book cuts through the hype to show what benchmarks really tell us, where they fall short and why better evaluation leads to better models. Practical, clear and grounded in real-world experience, it is an essential guide for anyone building, studying or deploying modern AI.

Build serious AI systems on NVIDIA DGX Spark with a practical guide that goes far beyond setup. Learn to deploy LLMs, create RAG pipelines, orchestrate AI agents, and optimize performance for real production workloads. Whether you are experimenting or scaling enterprise AI, this book shows you how to get there.

A £4.1M PRA compliance failure. A fictional bank called Avon & Wessex. Sixteen chapters and 23 systems showing exactly how to build production-grade, auditable AI for credit, market, operational and liquidity risk, model governance, and regulatory reporting — the practitioner's guide UK banking has been missing.

Discover how to unlock the full potential of Claude Opus 5 with a practical guide built on Anthropic's official documentation and proven best practices. From writing your first effective prompt to designing sophisticated agentic workflows and production-ready systems this book gives you the techniques, patterns and insights needed to achieve more accurate, reliable and consistent results.

An agent can score well on average and still fail exactly where it matters. Beyond “Ship and Pray” shows how to replace benchmark averages with designed experiments, geometric ground truth and failure attribution—so teams can discover when an agent breaks, identify the responsible component and test whether it fails safely under tool faults.

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.