32Design a doc-QA system for a healthcare customer that reliably says 'I don't know' instead of guessing.▼hardAnthropicOpenAIGoogle2 replies◆ premiumIn high-stakes domains a wrong answer is worse than no answer, but a system that always abstains is useless. The selective-prediction design, the layered abstention triggers, and the two metrics that govern the tradeoff.Open full answer →
13Build doc-QA for healthcare where a wrong answer is worse than no answer. How do you make it reliably say 'I don't know'?▼mediumAnthropicHarveyOpenAI1 replies○ sign inCalibrated abstention is a system property, not a prompt line. Learn the four abstention signals, the precision-at-coverage framing, and why 'just tell it to say I don't know' fails the interview.Open full answer →