Blog
Notes.
Short write-ups on the things we run into building cix — bugs, decisions, and the occasional opinion. Newest first.
August 11, 2026
Why We Run Coding Agents in a Loop
An AI coding agent that runs for an hour fails differently than one that runs for a minute. The short session either works or visibly doesn't.
Read →August 10, 2026
Why Your AI Assistant Stops at the Repo Boundary
The questions that decide whether a change is safe are rarely contained in the repository you're standing in. The client renders a field the API stopped…
Read →August 10, 2026
Why Your AI Assistant Rewrites Code You Already Have
You ask for a helper to format prices. You get a clean, well-tested formatMoney(). It works. It also sits fourteen files away from the formatCurrency() you…
Read →August 10, 2026
What Breaks When Your Code Index Goes Stale
You rarely catch a stale index directly. You catch its symptoms, and they look like this: If you're seeing any of those, the picture and the code have…
Read →August 10, 2026
What a Code Index Is, and When You Need One
A code index is a structural map of your repository: every function, class, component and type, where each one is defined, what calls it, which routes reach…
Read →June 6, 2026
Why AI Struggles With Large Codebases
A few months ago, I found myself chasing a feature that I was convinced didn't exist. The task seemed straightforward.
Read →June 6, 2026
AI Doesn't Struggle With Programming. It Struggles With Your Code.
Modern models can explain algorithms, design APIs, write tests, and reason about systems they have never seen.
Read →