~/writing
Production Incidents
2 posts tagged production-incidents. clear filter
September 2026
- 20Why git revert can't undo an agent's API calls, emails, and chargesday 15 · Software Engineering in the AI Era
A clean git revert made our dashboard look fine — it was the billing charges, duplicate emails, and spent API credits sitting in other people's databases that told the real story.
- 19Why retrying a non-idempotent tool call charges a customer twiceday 15 · Distributed Systems in 30 Days
Your `max_retries=3` wrapper is quietly promising that a tool call is safe to run more than once, and nothing in your dashboards will tell you when that promise is a lie.