Writing
Notes on Azure & AI architecture
Practical write-ups on cloud migration, AI-enabled systems, and production delivery on the Microsoft stack — from real patterns, not slideware. Looking for a short, direct answer? See Questions.
Governance is code: what an AI engineering playbook actually enforces
A policy no gate enforces is a suggestion. How one playbook governs AI coding agents across five repos, and which rules block versus merely advise.
“A chatbot” and “production enterprise chat” are not the same thing
What production enterprise chat actually looks like on Azure — one public front door, a private network, grounding, state, and the governance around the model.
LLM, agent, MCP — what they actually mean
Three terms that get used interchangeably and shouldn't. What each one is, how they fit together, and the questions to ask before you buy "an AI agent".