A tech publication for people building with AI.
Tutorials and reviews. No coding background needed.
Latest
Claude Code ran 4 hours unsupervised. What I reverted
I let Claude Code refactor a real repo for four hours with no review. Half the diff stayed. Here is what it broke and why.
Stop AI agents committing to main: a 2-line git hook
Branch protection blocks the push, not the local commit. A pre-commit hook stops any agent from landing work on main, with a one-line escape.
Claude Code agent loop: 3 causes and the fix
Claude Code looping on the same edit means one of three things: lost context, a failing command, or a vague task. Here is the fix for each.
Run two Claude Code sessions in one repo with worktrees
Claude Code has a native -w flag for git worktrees. Run a refactor and a feature in parallel, each in its own files, with no merge pain.
Claude Code sub-agents: when to spawn one (3 cases)
A sub-agent runs in its own context window and hands back a summary. Here is the one rule for when to spawn one, with three worked examples.
Get Claude Code to write tests you'll keep
Claude Code writes tests that pass without checking anything. Write them before the code, lock the assertions, and keep the tests worth running.
Newsletter
A short weekly email about AI tools and what's worth trying.
Free. No spam. Unsubscribe anytime.
Start here
For beginners. No code required.
Codex CLI review: what beats Claude Code after 2 months
Two months of daily Codex CLI use. The three things that stuck, where it beats Claude Code, and where Claude Code still wins.
Claude Code ran 4 hours unsupervised. What I reverted
I let Claude Code refactor a real repo for four hours with no review. Half the diff stayed. Here is what it broke and why.
Claude Code sub-agents: when to spawn one (3 cases)
A sub-agent runs in its own context window and hands back a summary. Here is the one rule for when to spawn one, with three worked examples.