More rules should mean better output. That's the intuition. I spent weeks building a comprehensive CLAUDE.md — 200 lines covering naming conventions, security rules, error handling, architectural patterns, import ordering, type safety requirements, and more. I was proud of it. I'd thought through every scenario. Then I scored the output. 79.0 / 100. My carefully crafted documentation was actively
State that survives a docker compose down is one of those things you don't think about, until your test suite needs it, your local dev needs it, and your CI pipeline absolutely doesn't. LocalStack handles persistence with one switch (PERSISTENCE=1) and it's a Pro-only feature. Floci ships four storage modes, all free, all in core, with per-service overrides. Pick the right tradeoff for the job.
I'm a software engineer in Japan. I've been using AI coding assistants — Claude Code, Cursor, Copilot — for about one years now. At some point I started keeping informal notes on how many prompt revisions it took to get production-quality output. After a few months, a pattern was hard to ignore. For tasks I described in Japanese: 4–6 revisions on average. 1–3. Same AI. Same model. Roughly similar
"Write a function to fetch the list of users." — same prompt, same codebase. Yesterday: getUsers(). Today: fetchUserList(). Tomorrow: loadAllUsers(). Six months of AI-assisted coding and I kept hitting this wall. My initial reaction was "maybe I need to write better prompts." I wrote better prompts. The functions got slightly better. New inconsistencies appeared elsewhere. The problem wasn't the A