An AMD/IREE developer quantitatively analyzed Claude Code session logs, demonstrating the correlation between shrinking extended thinking since February and quality degradation. The GitHub Issue drew 87 comments and 790 HN points.
Stripe Minions, Amazon Kiro, Claude Code compaction, and a Replit DB deletion. We synthesize multiple cases to extract the design principles required to operate AI coding agents in production, and organize them alongside CodeRabbit's 470‑repo statistics plus efforts from Google and GitHub.
Kiro autonomously deleted production, causing 13 hours of AWS downtime; Claude Code’s auto-compaction irreversibly erases context; sub-agents silently burn through usage. Three incident reports from the same week.
Stripe’s Minions agent generates 1,300+ PRs per week with zero human effort. Implementation details of the four components: Devbox, Blueprints, Toolshed, and a fork of goose.
