Posts tagged “lessons-learned”
~/blog ❯ ls -lt tag/lessons-learned/
total 5
How Claude spawned 100 agents to audit my backend
Three audits of Horsemate in two weeks: five agents, then ten, then a Claude Code workflow with 100. What each layer of agents added, the one serious hole it found and fixed before I'd read the report, 29 PRs in 26 hours, and what it all would have cost on the API.
How to train your (AI)pony
Horsemate got a chatbot named after my old Gotland pony. The same evening it went live, I built a 61-question test battery, let Claude Opus grade every answer, and found that most of what was wrong was in how I measured, not in the pony.
What Horsemate shipped since February, and the database I'd build differently
482 commits, three silent months and one very busy September. What shipped in Horsemate from February to September 2026, and an honest look at the database design mistakes that most of that work was spent cleaning up.
I spent a week optimizing the wrong thing (a 100-second sync story)
How I parallelized GitHub API calls for a 23% speedup when the real bottleneck was database writes. The fix that actually worked took an afternoon.
AI doesn't write perfect code (and that's fine, if you're paying attention)
Real examples from my codebase where AI-generated code looked correct but wasn't. The bugs were subtle, the lessons were obvious in hindsight.
~/blog ❯ cd .. # all posts