Ideas

A run produces data. A loop produces decisions.

Notes on AI operations, agentic systems, and RevOps — the thinking behind the systems I build.

The signature thesis: the data you scrape should plan the next scrape. Loops beat runs.

A working definition — from someone who designs, codes, and operates the systems.

Why the Model Context Protocol turns every product and dataset into a callable tool.

Custom Postgres + RLS, a custom MCP server, and 2,500+ prompts — one operator.

How generative-AI engineering connects to conversion, CAC, and revenue.

Prompt engineering at scale: 200+ libraries as reusable, versioned infrastructure.