Agentic Engineering

45% do código gerado por IA tem vulnerabilidades. Este livro cobre prompt injection, vazamento de dados, codificação segura com ferramentas de IA, hardening de servidores MCP, sandboxing de agentes e compliance OWASP LLM. 14 capítulos com demonstrações de ataque e código de defesa.

Guia prático para desenvolvimento agêntico com Claude Code, MCP, Claude API e Agent SDK. De modelos mentais a arquiteturas de produção — tudo que um dev experiente precisa para trabalhar de forma agêntica, não apenas usar ferramentas de IA.

A hands-on guide to building with Claude Code, MCP, the Claude API, and the Agent SDK. From mental models to production architectures — everything an experienced developer needs to work agentically, not just use AI tools.

As the author, I (Anshuman Mishra) have written this book with the spirit of mentorship — not just to explain how chatbots work, but to help you build one confidently and ethically. I have taught AI, programming, and computer science for nearly two decades, and I have seen countless students struggle to bridge the gap between theory and implementation.This book closes that gap. It teaches you what to do, why to do it, and how to do it right. It’s not just a manual — it’s a journey from curiosity to mastery.You are not just learning to build a chatbot; you are learning to create intelligence — responsibly, creatively, and with purpose.

As the author, I (Anshuman Mishra) have written this book with the spirit of mentorship — not just to explain how chatbots work, but to help you build one confidently and ethically. I have taught AI, programming, and computer science for nearly two decades, and I have seen countless students struggle to bridge the gap between theory and implementation.This book closes that gap. It teaches you what to do, why to do it, and how to do it right. It’s not just a manual — it’s a journey from curiosity to mastery.You are not just learning to build a chatbot; you are learning to create intelligence — responsibly, creatively, and with purpose.

«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.

Build MCP servers from scratch — from protocol to production deployment. Learn Tools, Resources, Prompts, HTTP transport, authentication, testing, and server composition. 14 chapters, one real project, complete TypeScript code.

Construa servidores MCP do zero — do protocolo ao deploy em produção. Aprenda Tools, Resources, Prompts, transporte HTTP, autenticação, testes e composição de servidores. 14 capítulos, um projeto real, código TypeScript completo.

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.

Build a complete AI agent from scratch — from a simple API call to a production multi-agent system with memory, planning, RAG, security, and deployment. 15 chapters, one real project, complete Python code.

Construa um AI agent completo do zero — de uma chamada simples à API até um sistema multi-agente em produção com memória, planejamento, RAG, segurança e deploy. 15 capítulos, um projeto real, código Python completo.

What if agentic AI was less about hype and more about work you can actually inspect?OpenClaw and Hermes for Agentic AI is a practical field guide to building with local agents, memory, tools, sessions, cron jobs, and ACP bridges. It shows how to turn fuzzy ideas into reliable workflows with clear boundaries, real artifacts, and human review where it matters most.If you want a grounded look at how agent systems really operate, this book starts there.

Most senior engineers don't fail AI systems interviews from lack of ability—they fail because they sound like builders when they need to sound like staff. This book gives you the answer flow, the system deep dives (RAG at billion-doc scale, agentic pipelines, token-cost tradeoffs), and the behavioral stories that earn L5/L6 offers at AI-first companies. Built for senior engineers targeting Staff AI Systems roles in the next 8 to 12 weeks.

Master AI integration on Apple platforms by bridging Swift 6 with OpenAI, LangChain, and autonomous agents. Build high-performance RAG pipelines using hardware-accelerated vector math and persistent local semantic memory. Architect thread-safe, real-time apps with strict concurrency, intelligent function calling, and efficient token streaming. Move from basic API calls to production-grade intelligence with the definitive guide for modern Apple developers.