Case studies, and the thinking behind them.

The bot on this site got used more than I expected — and usage is just a stress test you didn't schedule. One visitor talked it into dropping the assistant role and performing a celebrity-style monologue. The next tried to make it read its own instructions out loud. This is the whole arc: how I caught the first one, why a careful model fell for it, the layered fix, the prompt-extraction hole I found next, and the moment I got tired of patching by hand and taught the thing to heal itself.

My site's chatbot makes two AI calls for every message — one to answer, one to grade the answer. For weeks I ran that pipeline half-blind. Langfuse is the open-source tool that let me finally see inside it.