Problem
Scenario
You're working on a patient-facing AI agent that helps users ask questions, share symptoms, and get guided next steps in a healthcare setting. The model needs to sound clear and supportive, stay within policy, avoid unsafe medical advice, and know when to hand off to staff or ask for clarification.
Question
How would you handle prompt engineering for a patient-facing AI agent?
What this tests
- Prompt design for patient-facing conversations
- Safety handling for hallucination and unsafe advice
- Agent behavior with routing and escalation
- Evaluation strategy for prompt quality and policy adherence
You are practicing as a guest. Sign up free to get your answer graded with AI feedback. Your draft stays right here.
