Books

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.

What if TransE, ComplEx, RotatE and the rest of the knowledge graph “model zoo” were different views of one geometric operator? Learn the mathematics, code and practical design principles behind structured memory for trustworthy AI.

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.

Claude Code puede trabajar solo durante horas. La pregunta no es si confiar en él — es cómo dirigirlo para que ese tiempo no se convierta en el tuyo, limpiando después.

AI made implementation cheap and shared understanding scarce. This is the book about how teams should adapt the process.

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.

Two architectures. One choice: process a sequence step by step, or all at once. From that single decision flows almost every difference between RNNs and Transformers: how fast they train, how far they remember, and why parallelism won. A rigorous, diagram-rich comparison that derives the field instead of just surveying it.

The system design book for the AI era. Five complete end-to-end designs (chat service, RAG, content moderation, coding assistant, multi-modal platform), a structured six-step framework, and chapters on cost optimization, reliability, and observability — all with realistic capacity estimates and production-grade code.