Your mental-health chatbot gave harmful advice to a user in crisis. How do you redesign it?

The root cause is not a weak system prompt. A model trained to be agreeable is dangerous to a user in crisis, because the objective and the safety requirement point in different directions. The fix has to live outside the model. Here is what that architecture looks like.

Updated Sep 2026 · Grounded in real GenAI, LLM, and AI/ML engineering interview loops and written to a senior-engineer editorial bar.