Every network engineer knows the moment. Your finger hovers over Enter. The change looks right. You've checked it twice. But somewhere in the back of your mind, a voice asks: What if I'm wrong?

How I built a 16-device, 4-vendor lab for network automation, and what broke along the way.

I've been building network automation for a couple of years. Ansible playbooks, Python scripts, REST APIs. They all work. But when Anthropic released the Model Context Protocol (MCP), I saw something different: a way to make AI understand network operations natively.

I built a RAG system that lets an AI answer network automation questions using my actual documentation—and query live devices when the answer isn't in a PDF. The result: fewer hallucinations, accurate config syntax, and real-time troubleshooting that knows my topology.

Here's what I learned about chunking, embeddings, and making retrieval actually work for technical content.

Five months, 142 MCP tools, and the journey from "what if I could talk to my network?" to enterprise-grade automation