AI Coding
Coding agents and assistants used on a real repository: briefs, reviews, cost, and the edits you still make yourself.
- Oct- 2026 -14 October
Requirements for an Agent Loop That Runs Until Tests Pass
An agent loop that runs until tests pass is a deceptively simple thing to describe and a genuinely hard thing to build.
Read More » - Oct- 2026 -3 October
How to Write a Task Brief an Agent Can Finish
A task brief that an agent can finish fits on one screen. That is the first test, and it eliminates most of what gets handed over as instructions.
Read More » - Jul- 2026 -30 July
When Generated Tests Are Worth Keeping
A generated test suite can look impressive in a pull request. Fifty files, a thousand assertions, a coverage number that climbs from 61 to 88 percent.
Read More » - Jul- 2026 -27 July
How Context Limits Show Up on a Real Repository
The repository had 412 files. That number matters, because the assistant had been told to read the whole thing before answering a question about where authentication was configured.
Read More » - Jul- 2026 -22 July
A Daily AI Coding Setup for an Indie Hacker
The terminal opens at 6:40 a.m. and the first thing it shows is a diff.
Read More » - Jul- 2026 -4 July
IDE Assistant vs Terminal Agent for a One-File Bugfix
A single-file bugfix is the smallest unit of real programming work, and it has become the sharpest test of two different ideas about what an assistant should be.
Read More »