Artificial Intelligence

执行的成本趋近于零，判断的成本没有变。AI越强，判断力越值钱。

StackPilot shows how to use graph-grounded AI to plan and explain infrastructure changes while keeping authorization, execution, and accountability under deterministic and human control. It is a practical guide for building safer AI-assisted infrastructure operations—from typed intent and evidence retrieval to approval manifests, observation, and earned production authority.

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.

Great software is built through great reviews. This book shows you how to spot hidden bugs, improve design, strengthen security, and review AI-generated code with confidence. Packed with practical examples and proven techniques, it helps you write better software in a world where humans and AI build code together.

Building an impressive AI agent demo is easy. Running one in production—reliably, at scale, with governance—is where most enterprises get stuck. Agentic Orchestration shows how BPMN-based process orchestration governs AI agents at scale, drawing on real deployments across banking, telecom, and healthcare. Reasoning without orchestration is expensive chaos. This book shows the way out.

16 章手写一个 CLI Agent。从 Hello World 到 Skill 插件系统，只用 Python 标准库 + OpenAI SDK。每章附真实项目踩坑笔记——来自 git 提交历史的 bug、设计失误和凌晨调试的教训。读完你会理解 Agent 的底层运作方式，而非只是会用某个框架。

Si creés que la IA "democratiza" la programación, este libro te va a discutir: la vara no baja, sube. Estas herramientas son más peligrosas en manos sin criterio. 30 capítulos para dominarlas —incluido cuándo NO usarlas.

Your AI has not forgotten you. It simply cannot show you what it knows, let you correct it, take it with you, or act on it. This book fixes all four: plain files you own, an assistant with hands on them, rules it will not cross, and work that lands before you wake up. No code, no terminal.

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.

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.

Your tests pass, the agent says it's done — but does your software work? A field manual for verifying what your AI coding agent actually built.

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.