Product design question
Design an AI shopping assistant inside Comet.
- Perplexity
- Product design
- Medium
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 combining trust, personalization, and a real commerce workflow inside an AI browser context.
How to approach it
- Clarify the user need: comparing products across many open tabs and reviews is tedious, and the user wants a synthesized recommendation they can trust.
- State the core requirement: the assistant must ground recommendations in the actual pages the user is viewing or has viewed, not generic product knowledge, to feel personalized and credible.
- Propose the flow: the assistant tracks open shopping tabs, extracts price, reviews, and specs, and presents a comparison table with a clear recommendation and reasoning.
- Address trust and bias: disclose clearly if a recommendation involves an affiliate or sponsored link, since undisclosed bias would break user trust quickly.
- Define success: conversion rate on assistant-recommended purchases, and repeat usage of the shopping assistant across multiple sessions.
What a strong answer includes
- Grounds the assistant in the user's actual open tabs and browsing context, making it a genuine comparison tool rather than a generic product chatbot.
- Proposes a concrete, structured output, a comparison table with explicit reasoning, rather than a vague conversational recommendation.
- Names disclosure of affiliate or sponsored relationships as a non-negotiable design requirement, protecting long-term trust over short-term commerce revenue.
- Sets a business-relevant success metric, purchase conversion rate, tied directly to the commerce value of the feature.
Common mistakes
- Designing a generic product-recommendation chatbot disconnected from the user's actual open tabs and browsing context.
- Ignoring the trust risk of undisclosed affiliate incentives influencing recommendations.
Likely follow-up questions
- How would you handle a product category where reviews across sites conflict significantly?
- How would you balance affiliate revenue incentives against giving the genuinely best recommendation?
More product design questions
- How would you improve Perplexity's Comet browser for daily use?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
- 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