Running Clinical ReAct Agent 🩺 Answer clinical questions using patient charts and reference lookup
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
Running Order the Lab: a tool-calling trace, and what the model said with no tools 🩺 Show LLM tool-call trace and compare with no‑tool answer
Running Speak the Patient's Language: semantic search vs keyword search 🩺 Find similar patient statements with semantic search
Running GP versus the Specialist: a measured model-tier scorecard 📊 Compare AI model answers to clinical questions