Hi, I'm Colin.

I care about writing clean, maintainable code and designing systems that scale gracefully — from the API boundary down to the way a single function reads on the page.

Lately most of my work sits at the AI frontier: agent runtimes, evaluation pipelines, developer tooling. I'm drawn to the problems where the model isn't the answer on its own — the hard part is the system around it.

This is where I think out loud — mostly about software engineering, machine learning, and the craft of building useful things. I write because the best way to understand something is to put it in your own words.

Posts range from short notes on a habit I'm trying, to longer pieces unpacking a system I've been working on. Nothing here is meant to be a final answer — just where I am today.

When I'm not coding, you'll usually find me reading, running, or experimenting with new tools and ideas.