AI Agents in Practice — Read from the beginning

This article is a practical, production-oriented guide to building AI agents, focusing on engineering patterns rather than hype or specific products. It explains why agent demos often fail in production, defines an agent as a control loop with tools, state, and boundaries, and introduces three core primitives: MCP for acting, RAG for knowing, and Skills for reusable procedures. The series is actively maintained and also includes companion guides on the Model Context Protocol (MCP) and Retrieval-Augmented Generation (RAG).

A practical, production-oriented guide to building AI agents — patterns over products, anti-hype, vendor-neutral. Part 1: The Demo Worked. Production Didn't. Priya's refund went through on a shipped order. The model was right. The system around it wasn't. Why agent demos break the moment they meet production — and what the demo hid that production reveals. Part 2: What Makes Something an Agent Define what an agent actually is in engineering terms — a control loop with tools, state, and boundaries. The three primitives an agent composes MCP for acting, RAG for knowing, Skills for following reusable procedures . The bridge from manual ReAct to native tool calling. Part 3: How the Loop Actually Works Coming soon. What happens turn by turn when the agent runs. State that carries across turns, stopping conditions as real decisions, and context as a finite engineering resource — not just a bigger window. This series is actively maintained. New parts will be linked here as they publish. MCP in Practice — Read from the beginning The Model Context Protocol from first principles — what MCP is, why it exists, and how to build production-grade tool servers and clients. RAG in Practice — Read from the beginning Retrieval-augmented generation from first principles — why AI gets things wrong, what RAG fixes, and how the full pipeline works.