Books

Build real-world web applications faster with Claude Code by your side. This hands-on guide takes you from web development fundamentals to production-ready full-stack engineering with React, Next.js, TypeScript and PostgreSQL. Learn practical AI-assisted workflows while building, testing, securing and deploying applications that are ready for real users.

Discover how the Model Context Protocol is transforming the way AI applications connect to tools, data, and external systems. With clear explanations and practical guidance, this book shows you how to build, secure, and deploy production-ready MCP solutions, from your first server to enterprise-scale AI applications.

Answered sounds like it worked. Twice, it didn't. This book measures exactly where six seconds of silence goes in a real phone call, and does not stop measuring for the next thirty-four chapters.

Rapid-development frameworks across Ruby on Rails, Node.js, PHP, Python, and .NET revolutionized how quickly we can ship software. But what happens when your business domain grows complex? Relying on Active Record and heavy ORM patterns tightly couples your database to your business logic. As your product matures, this coupling creates brittle, difficult-to-maintain codebases that resist change and slow down your team. The solution is the Domain Model Pattern (the foundation of Domain-Driven Design). It isolates business rules from infrastructure, creating a pure, scalable architecture. Historically, however, this pattern required a massive amount of effort and boilerplate, making it too slow for fast-paced development. That changes today. We are at an AI inflection point. Modern AI coding assistants excel at generating boilerplate and wiring infrastructure, effectively eliminating the traditional drawbacks of DDD. AI finally bridges the gap between the rapid speed of framework scaffolding and the architectural purity of a Domain Model. But to harness AI reliably, you cannot simply let it generate code unguided. You need a structured methodology to guide the machine. In this book, you will learn:How to build reliable, maintainable software using a strict, AI-assisted pipeline: Use Cases → Gherkin → Event Storming → Strategic & Tactical DDD.How to create implementation-agnostic class diagrams that serve as universal blueprints, allowing you to generate code in OOP languages (Java, C#, PHP, Python) or Functional languages (Elixir, Clojure, F#).How to future-proof your systems with a timeless methodology that prioritizes the longevity of business logic over the ephemeral nature of web frameworks.How to scale your architecture gracefully from a Majestic Monolith to Microservices without a complete rewrite. The methodology is language agnostics but in this edition all codes samples are in TypeScript. Whether you want to accelerate your development velocity, improve your system's resilience, or simply reclaim your craft by building beautiful, majestic systems, this book provides the blueprint.Discover how to combine the timeless principles of DDD with the power of AI.

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.

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.

You leave Claude Code running and come back to something missing. This book is arranged by the accident, not the mechanism: databases dropped, files deleted, git history rewritten, the rewind command taking work with it. Three of the four get the exact hook that blocks the command before it runs, with the recovery if it already happened; no PreToolUse hook sees the rewind command, and the book gives the settings-level lever and names the one place a refusal could still live. Appendix B prints all 195 commands the guards were fired at, refusals and allowances both.

An accessible guide to how large language models become agents that can reason, use tools, remember, plan, interact with software, and collaborate with other agents. Written for readers who understand the basics of LLMs but do not want a mathematics-heavy treatment.

ဥပမာအားဖြင့်၊ သင်က AI ကို "မိုးရွာရင် ထီးယူသွားပါ" ဟု ခိုင်းထားလျှင်၊ မိုးသည်းထန်စွာ ရွာနေသော်လည်း အိမ်ခေါင်မိုး ပြိုကျနေပါက ၎င်းသည် ထီးကိုသာ ကိုင်၍ အိမ်ထဲတွင် ငုတ်တုတ်ထိုင်နေပေလိမ့်မည်။ အဘယ်ကြောင့်ဆိုသော် "အိမ်ခေါင်မိုး ပြိုလျှင် ပြေးပါ" ဟူသော စည်းမျဉ်းကို သင်က ထည့်မပေးထား သောကြောင့် ဖြစ်သည်။

Installing safety hooks for Claude Code takes about thirty seconds. Proving they actually refuse anything is the step almost everyone skips — and an unverified guard looks exactly like a working one. Free: the pre-flight checklist, which event can refuse a tool call and which only watches, how to make a guard fire on purpose, what a broken hook does, and a catalogue of all 916 example hooks in cc-safe-setup.

A working engineer's guide to building and maintaining production software with autonomous terminal coding agents (382 manuscript pages).

Most writing about AI and infrastructure stops at the demo. This book starts on the day the model is confidently wrong at 3 a.m. and an auditor asks who authorised the action it took. Seven working labs — MCP servers with real identity and audit, closed-loop remediation behind a reversibility gate, and autonomy that can be revoked — for platform engineers in safety-critical and regulated industries.

Your agent passed every load test and timed out in production anyway. This free practitioner's guide shows why the traditional performance playbook breaks for agentic AI, and what replaces it: latency budgets, bounded autonomy, token SLOs, and production-grade observability, from a performance engineering and observability architect with two decades in production.

Your AI-generated code passes 18,000 tests and reports healthy — while entire data pipelines silently produce nothing. Silent Wiring names the failure mode nobody's tooling catches, and shows you how to find it before your users do.

A local model returns the expected answer. How do we know which layers ran on the GPU? In Local AI on RTX Spark Laptops, we investigate questions like this through 251 hands-on WSL2 exercises, following the evidence from model-loader logs down to individual CUDA kernels.