Books
- The Model Context Protocol (MCP) in PracticeBuilding, Integrating, and Scaling Custom Tool Servers for AI AgentsYohan Rodriguez
A hands-on guide to designing, building, testing, and deploying secure stdio and SSE MCP servers in Python and TypeScript (447 manuscript pages).
This book teaches harness engineering as a discipline. Not magic prompts. Not vendor tricks. Engineering practice applied to a new substrate.
- Securing Enterprise AI AgentsA Field Guide to Bounded AI Autonomy, AgentSecOps, and MCP SecurityThomas De Vos
How to put AI agents in production without ending up in the news. A field guide to bounded AI autonomy, MCP security, and AgentSecOps.
- Architect the Solution: The CCAR-P Certification GuideA scenario-based study guide for the Claude Certified Architect Professional examThomas De Vos
The CCAR-P exam tests judgment, not trivia. This scenario-based guide covers all seven domains, from solution design and RAG to governance and stakeholder communication, with 65 sketchnote figures, chapter quizzes, a distractor appendix that explains every wrong answer, and a full 63-question practice exam at the official weighting.
- PydanticAI: Building Production-Grade AI AgentsFrom Fundamentals to Advanced Agent Workflows with Python's Type-Safe FrameworkSteve Publications
Learn how to build reliable AI agents with PydanticAI, from simple chatbots to production-ready multi-agent systems. With practical examples, clear explanations, and hands-on projects, this book helps you write AI applications that are structured, testable, and easy to maintain.
Master Claude Code from zero to production. Build a complete full-stack app across 18 chapters — learning CLAUDE.md, Plan Mode, Skills, Hooks, MCP servers, subagents, the Agent SDK, CI/CD, and security best practices along the way.
Five proven AI side hustles with honest income data. Freelancing, automation services, vibe coding, content creation, and prompt engineering. No coding required, no "get rich quick" — just a 90-day playbook from an engineering leader who builds AI systems for a living.
- AI-Native Software TestingDesigning Self-Generating, Self-Healing, and Intelligent Test Systems with Playwright, AI Agents, and LLMsSrinivas Bommena
Traditional test automation can execute scripts, but it struggles to explain failures, adapt safely to application changes, evaluate AI-powered features, or govern autonomous testing agents. AI-Native Software Testing shows practitioners how to design a modern testing architecture that combines Playwright, AI agents, LLMs, controlled self-healing, and governed CI/CD automation.
AI coding agents can move faster than Git’s staging-and-commit workflow.Juju-chu! shows how Jujutsu🐦⬛ gives you automatic commits, reliable undo, and a safer way to reshape messy AI-generated changes—while staying compatible with Git and GitHub. For developers who already use Git and want a calmer AI workflow.
- Pensare con gli LLM, The Right WayPotenziamo il pensiero critico usando l'AI generativa senza farci usareFrancesco Fullone
«L'AI mi ha confermato X» usato come prova di X. Output che suonano brillanti ma non reggono a una rilettura severa. Una "AI policy" di tre pagine che nessuno legge. Suona familiare? "Pensare con gli LLM the Right Way" è il sistema di pensiero critico applicato agli LLM: il Triangolo del Pensare-Con (Intento / Avversario / Editore), le quattro decisioni meta di governance, le pratiche socratica e avversariale per indagare e verificare. Non prompt engineering: il metodo per non farsi rispecchiare.
- Systems Thinking for Agentic AIA Software Architect’s Guide to Building Reliable LLM and Agent SystemsEdiz Najim
An LLM is not an AI system.Systems Thinking for Agentic AI shows software engineers and architects how to design reliable AI applications with prompts, RAG, tools, memory, orchestration, guardrails, evaluation, observability, and runtime control.Move beyond chatbot demos and learn how to build production-ready agentic AI systems you can reason about, measure, debug, operate, and improve
You shipped the demo. The model worked. Now production is coming, and the demo is not a system. An agentic system is a distributed-systems engineering problem — the reliability lives in the shell, not the model.
Master DeepSeek V3 — one of the most capable AI models of its time.This practical guide teaches students, researchers, and professionals how to use DeepSeek V3 for learning, research, coding, content creation, automation, and productivity — with strong focus on prompt engineering and responsible AI usage.
소프트웨어 개발 환경이 빠르게 변화하는 가운데, Claude Code는 이러한 변화의 중심에 있습니다. 이 책은 개발자가 AI 에이전트와 효과적으로 협업하여 코드를 작성하고, 워크플로를 자동화하며, 더 큰 규모의 프로젝트를 자신 있게 수행하는 방법을 안내합니다. 설정 및 프롬프트 설계부터 실무 엔지니어링 사례에 이르기까지 폭넓은 내용을 다루는 이 책은, 2026년의 현대적인 소프트웨어 개발 방식을 이해하고자 하는 모든 이에게 실용적인 로드맵을 제시합니다.
Learn to build production-ready LLM applications with DSPy through hands-on tutorials, complete runnable examples, and real-world projects. Master DSPy's core abstractions and create AI systems that improve with data instead of endless prompt tweaking.
