For AI agents: a documentation index is available at /llms.txt. Every page also has a Markdown version at its URL plus .md.
~/what-i-do
The areas I work in, and the rules I work by in each. Every rule comes from real projects, and most link to the one where I applied it.
Developers are fastest when the right thing is also the easy thing. I look for the friction that quietly eats a team’s week (slow feedback, flaky setup, manual steps) and remove it with tooling, not more documentation.
A pipeline is a promise about quality that runs on every change. I build ones that are deterministic, fast, cheap to run and hard to quietly weaken, including by AI agents.
Most of a product lives in its backend: the APIs, the data and the services behind them. I build those around the domain, so the business rules are easy to find, the data can be trusted and a slow dependency never takes the product down.
Good platforms are paved roads: the safe, observable, repeatable way is also the quickest way to ship. I build the plumbing that makes that true, from pinned toolchains and scaffolding to config and policy as code.
AI earns its place when it removes real, repetitive work and you can trust what it does. I build AI features and agent workflows with structure, measurement and humans on the uncertain cases.