Running Make It Say No: three validation layers, measured in both directions 🛡 Validate pharmacy counseling requests with multi‑layer checks
Running Answer the Patient: what a reranker changes, measured 🩺 Answer clinical questions using a reranked document search
Running Catch the AI Lying: an audited pass/fail harness for one small free model 🩺 Assess AI model answers with exact, fuzzy, and judge scoring