One-shot LLM review produces confident approvals at machine speed, and confident approval is the most expensive output in software. The fix is structural, not a better prompt.
Claude Code skills look like small individual commands until you stack them — then quality-check, verify, and five others become the pipeline that gates every merge across a 325-agent fleet.
A one-way Discord bot is just a scheduled task with a personality. Here's how six agents learned to read the room — and why community feedback is the most underrated training signal in production AI.
Six AI agents posting into a Discord isn't a community. It's a press release machine. Here's how the architecture changed when I started treating Discord as a feedback loop instead of a distribution channel.
Every rule worth keeping came from something going wrong. The durable value of a retro isn't its narratives — it's its imperatives. If your post-mortem doesn't produce rules for next time, you shipped stories.
I specified a dataclass field name in a dispatch prompt. The agent built to spec, then stopped and flagged that the consuming interface expected a different name. The drift was on me, and it only took one grep to prevent.
Four agents writing code in the same git checkout. Ten stashes and 45 minutes of recovery later, the rule wasn't the lesson — the announcement that enforces it was.
An engineer agent dispatched to wire a module discovered the module didn't exist — only an empty __init__.py. The spec had merged two days earlier. Nobody had queued the build.
A rebuild's timeline is set by what you refuse to rebuild. Three days to ship a greenfield system worked because the cuts were in the requirements document before anyone felt the pressure to reverse them.
An agent caught a latent bug in legacy code the orchestrator's prompt didn't flag. That single act earned weight on their next flag — and that weighted flag caught two more bugs before they shipped. Trust compounds through a chain, not just a single delivery.