当 AI 能替你写代码,真正的危险不是它写错,而是你以为它不会错。
An AI asked to build a network and its own tooling refused — no human had signed. Six weeks later the same machinery governed bare metal serving a 740B-parameter model, every step on a committed record. This book builds that lab from the ground up: the gate, the run records, the GitLab nervous system, the audit trail — AI doing real infrastructure work you can prove afterwards.
从任务、基线和证据出发,验证 AI 的真实价值。为个人、管理者与中小企业建立责任链、趋势判断、持续学习,以及停止、导出、迁移和恢复能力。
Something is learning to shop. Not a person tapping a screen, an AI agent that reads intent, compares offerings across thousands of merchants and completes a purchase in seconds, with no browser and no forms. What it needs is a common language and that language is the Universal Commerce Protocol. In this book, you'll go inside UCP from first principles to production: how agents discover merchants at a well-known endpoint, how capabilities are negotiated in milliseconds, how money moves through cryptographic tokens without anyone touching a card number and how a working merchant server and buyer agent actually talk to each other, request by signed request. The protocol is real. The implementations are real. The question, answered in these pages, is whether commerce's next infrastructure layer will be open. For engineers, the answer starts here.
Build MCP servers that are ready for real production. This hands on guide shows you how to design, secure, deploy and operate stateless Model Context Protocol servers that scale with confidence. Packed with practical examples and proven patterns, it gives you the skills to build reliable AI infrastructure from the ground up.
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.
Everyone talks about large language models. Very few actually understand the machine.Whoever you are in the room — the one being asked, or the one deciding — this book puts you on the side of the conversation that understands the machinery.
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.
This book shows how to structure project information so that AI produces software that is consistent, predictable, and aligned with your engineering practices.
AI changes the security game. New attack paths demand new ways of thinking. This practical guide shows you how to build, deploy and defend AI systems with confidence using proven patterns, real code and production-tested techniques. Built for engineers who need security that works in the real world.
Turn AI-generated code into production software. Use observable requirements, architectural boundaries, TDD, review, release gates, security, payment, delivery, and operations to ship maintainable AI-assisted systems.
Build Model Context Protocol servers that go beyond demos. This hands-on guide walks you from the fundamentals to production deployment with practical examples in Python, TypeScript, Go, Rust and Java. Learn the patterns, tools and real-world practices needed to build secure, scalable MCP servers that are ready for enterprise AI.
This book is a workshop where things go wrong on the page, in front of you, and then get fixed in code, with the output that proves the fix worked. There's no need to be a security expert to follow along. We'll be moving from the interpreter to the supply chain, from the token to the human clicking Allow, and from a single tool to a whole host of untrusting servers.
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.