Product design question
Design the core mobile interaction model for an agentic AI answer that may be slow, uncertain, or partially wrong. On a phone screen, how would you communicate progress, uncertainty, sources, editability, and next-step actions so users can move quickly without over-trusting the system?
- Perplexity
- Product design
- Hard
Practice this question out loud. An AI interviewer asks it, follows up like a real interviewer would, and scores your answer. Type or speak.
Start a mock interview on this question · Mock interview from a job description
What this question tests
Tests core mobile interaction design for an uncertain, possibly slow AI answer, balancing speed, trust, and user control on a small screen.
How to approach it
- Design a progress indicator that communicates what the agent is doing, not a generic spinner, so waiting feels informative rather than opaque.
- Surface uncertainty explicitly when confidence is low, a visible flag or caveat on the answer, rather than presenting every answer with equal confidence.
- Show sources compactly, a tappable citation chip rather than a full source list, to respect limited mobile screen space while preserving verifiability.
- Make the answer editable inline, letting users correct or refine a partially wrong answer without restarting the whole query.
- Surface next-step actions as a short row of suggested actions below the answer, so users can act quickly without composing a new prompt.
- Test the design specifically for whether users can distinguish a confident answer from an uncertain one at a glance, avoiding over-trust.
What a strong answer includes
- Designs an explicit uncertainty signal distinct from a confident answer, directly addressing the over-trust risk named in the prompt.
- Uses a compact citation chip to preserve verifiability without consuming scarce mobile screen space.
- Makes the answer editable inline, respecting that mobile users need fast correction paths, not a full restart.
Common mistakes
- Using a generic spinner that gives no insight into what the agent is doing.
- Presenting all answers with the same visual confidence regardless of actual certainty.
Likely follow-up questions
- How would you test that users correctly perceive the uncertainty signal?
- What would you cut first if screen space forced you to drop one element?
More product design questions
- How would you improve Perplexity's Comet browser for daily use?Perplexity · Product design · Medium
- Design an AI shopping assistant inside Comet.Perplexity · Product design · Medium
- Design a 'Deep Research' feature that produces trustworthy, citable reports.Perplexity · Product design · Hard
- How would you design Comet Assistant to safely act on tasks like booking flights and managing email?Perplexity · Product design · Hard
- Design the core interaction model for a Project where a human and multiple agents collaborate on ongoing work. How would you handle delegation, approvals, edit history, permissions, and recovery from bad agent actions so the experience feels powerful but dependable?Perplexity · Product design · Hard
- Users of Perplexity Computer say they do not understand why the agent clicked, searched, or changed course, and they hesitate to let it continue. Design a core interaction model that makes the agent’s intent, current state, and next actions understandable and controllable without turning the product into a complex dashboard.Perplexity · Product design · Hard
More questions from Perplexity
Learn the skill behind it
Chapters of the AI PM course that teach what this question tests.
- Chapter 4: Discovering and Sizing AI Opportunities
- Chapter 7: Designing AI UX and Oversight
- Chapter 14: Interviewing for AI PM Roles