# A delivery chatbot wrote a poem about how bad its own company was > Source: > Published: 2026-10-28 19:52:01+00:00 DPD disabled part of its chatbot after a customer got it to write a poem criticising the company and to swear. The company said the issue came from a system update, and it switched off the AI element immediately. The chatbot had run for years. The update broke it. The lesson: every release is a new agent that needs grading. → Re-run your full eval suite on every prompt, model, or tool change → Include adversarial “make it insult us” cases as permanent regression tests → Block the release when scores drop Do your evals run before every release or only before launch?