Librería Samer Atenea
Kálamo Books
Librería Elías (Asturias)
Librería Kolima (Madrid)
Librería Proteo (Málaga)
Agentic AI and LLM orchestration are transforming modern software. It lets AI plan a task, use tools, and carry it through to completion on its own, making autonomous workflows the new standard for complex enterprise systems. This book provides a practical, step-by-step roadmap for software engineers and architects looking to design, deploy, and scale intelligent AI agents into real, everyday business systems where they must work reliably, safely, and at scale.This comprehensive book guides you sequentially through the entire lifecycle of agentic AI engineering using dual-stack Python and JavaScript implementations. It walks through the full journey: understanding how these systems think, making them safe and trustworthy, and finally running them in a real company setting where things need to work every single day without breaking. By the end of this book, readers will be able to design, build, and run production-ready AI agent systems on their own, from planning the workflow to keeping it secure, tested, and cost-efficient. They will walk away with real, job-ready skills: orchestrating multi-agent workflows, connecting AI safely to tools and data using MCP, handling errors and scaling issues like a professional engineer.WHAT YOU WILL LEARN● Build multi-agent AI workflows using LangGraph step by step.● Connect AI agents securely to tools and data using MCP.● Test and monitor agent performance to catch problems early.● Deploy and scale agentic apps in the cloud.● Apply these skills to real business use cases.● Prevent operational risks like agent loops, drift, and tool abuse.● Design production scaffolds with backpressure handling and CI/CD tests.WHO THIS BOOK IS FORThis book is designed for software engineers, ML engineers, data engineers, and AI architects and also students wanting to build production agentic systems. Solution architects, DevOps, SREs, and security professionals will also benefit. Readers should possess basic Python or JavaScript programming experience.