Interview Questions › AI Product

AI meeting notes and action items

Design AI-generated meeting notes and action items for Microsoft Teams. How do you define quality and launch it responsibly?

Context

Meetings can include confidential topics. Some participants may not want to be recorded.

Clarifying questions to ask first

• Who triggers it and who sees the notes?
• What about consent from all participants?
• Which languages?

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

• Consent and visibility controls
• Action items with owners, editable
• Quality = faithful, complete, no invented decisions

1. Eval set of meetings with reference notes
2. Score faithfulness (no hallucinated decisions) and coverage
3. Track edit rate and share rate after launch

Opt-in with clear notice to all participants, editable notes and action items with owners. Quality bar: no invented decisions, measured on a reference set. Launch internally first; success is notes shared and action items completed.

What interviewers look for

• Notes viewed and shared
• Action items completed
• Accuracy ratings