Interview Questions › AI Product

Should a health app add an AI symptom checker?

Practo is considering an AI symptom checker that tells users what might be wrong and whether to see a doctor. Should they build it, and if so, how?

Context

Wrong advice could harm people. The business earns from doctor consultations. Regulation of medical advice is tightening.

Clarifying questions to ask first

• Is the goal triage or diagnosis?
• Who is liable?
• Which conditions are in scope?

How to approach it

1. Start from the user problem, not the model: is AI the right tool here?
2. Describe the experience and where the model fits in it
3. Define what "good output" means and how you would evaluate it before and after launch
4. Name the failure modes (wrong answers, bias, privacy, cost) and how you contain them
5. Close with a launch plan and success metrics

Framework: User and problem -> Is AI the right tool? -> Experience design and human-in-the-loop -> Quality bar and evaluation -> Risks, cost and latency -> Staged launch and metrics

Sample answer

• Triage (urgency and specialty), not diagnosis
• Emergency symptoms routed by rules, not the model
• Clinician-reviewed evaluation set

1. Clinician-labelled cases to measure triage accuracy
2. Under-triage of emergencies as a zero-tolerance gate
3. Staged launch with clinician review of samples

Build a triage tool, not a diagnosis tool: hard rules for red-flag symptoms, clinician-validated evaluation with under-triage as a launch gate, and clear routing to doctors. Measure correct triage and safe consultations booked, not engagement.

What interviewers look for

• Correct triage rate
• Under-triage of emergencies
• Consultations booked