Our AI agent passed its eval. Then it refunded 212 customers twice
This story is from 2026-10-26. It is preserved in the archive; the latest stories are on the live feed.
We added one line to a customer-support agent's prompt: "If a tool call fails, retry once." The offline eval passed at 96%, above our 95% bar, so we shipped it to all traffic. Thirty-eight minutes later, 212 customers had been refunded twice. The eval wasn't wrong. It was blind. Our mocked refund t…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-10-26 05:41 · DEV Community — AI
Our AI agent passed its eval. Then it refunded 212 customers twice