Product design question
Pick one target persona, such as a Head of Support or VP of Engineering, and design a v1 dashboard plus recommendation workflow that turns Glean’s cross-tool context into a small set of actions they can take this week. What would you show by default, what would stay behind drill-downs, and how would you prevent the experience from turning into a noisy BI dashboard?
- Glean
- 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 judgment for a specific persona: can you decide what belongs in a default weekly view versus behind a drill-down, and avoid the generic BI trap the question explicitly warns about.
How to approach it
- Pick one persona, for example a Head of Support, and define their actual weekly decision cycle: staffing adjustments, escalation pattern review, and knowledge-base gap triage.
- Default view shows only what maps to that weekly decision cycle: a short list of the top 3-5 flagged issues this week, each with a one-line recommended action and confidence level, not a full metrics dashboard.
- Drill-downs hold everything exploratory: full ticket volume trends, team-by-team breakdowns, and historical comparisons, available but not forced on the default view.
- Design the recommendation workflow so each item has a clear accept, dismiss, or delegate action right in the default view, turning the dashboard into a queue of decisions rather than a report to passively read.
- Prevent the noisy-BI-dashboard trap by capping the default view's item count and refreshing weekly rather than real-time, since real-time noise for a weekly-cadence persona adds anxiety without adding decision value.
What a strong answer includes
- Ties the default view directly to the persona's actual weekly decision cycle instead of a generic set of top metrics.
- Builds the default view as an action queue (accept, dismiss, delegate) rather than a passive report, which is what prevents it from becoming generic BI.
- Caps scope and refresh rate deliberately to match the persona's decision cadence, showing restraint instead of maximizing information density.
Common mistakes
- Shows a broad set of metrics and trends by default with no filtering to the persona's actual weekly decisions.
- Builds a dashboard people view but cannot act on directly, missing the recommendation-workflow half of the question.
Likely follow-up questions
- How would you handle a week with far more flagged issues than the view can show.
- What would you do if this persona wants a daily cadence instead of weekly.
More product design questions
- How would you improve Glean's enterprise search relevance across 100+ connectors?Glean · Product design · Hard
- Design a permissions model so Glean never surfaces documents a user shouldn't see.Glean · Product design · Hard
- Design an onboarding flow that gets a new employee productive with Glean on day one.Glean · Product design · Medium
- How would you let non-technical employees build their own Glean agents?Glean · Product design · Medium
- A Fortune 500 admin wants employees to use Glean agents with GitHub, ServiceNow, and Zendesk, but their security team will only approve launch if they can prevent data leakage, over-permissioning, and unsafe write actions. Design the minimum viable governance controls and the admin/end-user experience you would ship for v1, and explain what you would defer to keep adoption high.Glean · Product design · Hard
- Design Glean’s end-to-end first-run developer experience for a team integrating with its APIs, SDKs, and MCP-based interoperability. Start from sign-up and auth, then walk through sandbox or test data, first successful call, SDK setup, error handling, rate-limit behavior, and documentation. What would you optimize for, and what tradeoffs would you make?Glean · Product design · Hard
More questions from Glean
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