Product design question
Design a 'Deep Research' feature that produces trustworthy, citable reports.
- 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
Product design for a high-stakes AI output where trust and verifiability matter more than speed or breadth.
How to approach it
- Clarify the user: someone making a decision, like an investment or a purchase, based on the report, who needs to verify claims, not just read a summary.
- State the core requirement: every substantive claim in the report must be traceable to a specific, checkable source, not a vague aggregate citation at the end.
- Propose the design: inline citations next to each claim, with source credibility indicators, and a visible confidence level when sources conflict.
- Propose a review step for high-stakes reports: a structured summary of source diversity and any detected disagreement between sources, surfaced explicitly rather than silently resolved.
- Define success: user-reported trust score for the report and, more concretely, the rate at which users click through to verify at least one cited source.
What a strong answer includes
- Requires inline, per-claim citations rather than a general source list, since the latter does not let users verify specific claims efficiently.
- Explicitly surfaces disagreement between sources instead of silently picking one answer, which is a realistic and important trust-building design choice.
- Proposes a concrete verification-behavior metric, source click-through rate, as a better trust signal than a self-reported satisfaction score alone.
- Addresses source credibility directly, since not all cited sources are equally reliable and the design should reflect that difference visibly.
Common mistakes
- Proposing only a general source list at the end of the report instead of per-claim inline citations.
- Ignoring cases where sources genuinely disagree, silently picking one answer rather than surfacing the conflict.
Likely follow-up questions
- How would you handle a topic where reliable sources are scarce or low quality?
- How would you measure whether users actually trust the report more after these changes?
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
- 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
- Perplexity notices that many users start a research task on web, ask several follow-ups, but do not return to that work on another platform later. How would you identify the single highest-leverage friction point in the begin → continue → return journey, and decide whether to invest first in context carryover, navigation, or collaboration?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: Discovery and strategy for AI products
- Chapter 7: AI UX and human oversight: design for a system that is wrong sometimes
- Chapter 14: Get the job: the AI PM interview loop