Product design question
You're launching the first version of Glean’s governance layer for AI agents at a Fortune 500 customer using ServiceNow, Zendesk, GitHub, and Microsoft Teams. What specific capabilities would you include in v1 vs. later releases so the customer can safely deploy agents, and how would you justify those scope decisions?
- 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
Whether you can scope a v1 governance launch tightly around what a real enterprise deployment needs across specific connectors, and justify the scope tradeoffs rather than trying to cover everything at once.
How to approach it
- V1 must include: an audit log of agent actions across ServiceNow, Zendesk, GitHub, and Microsoft Teams, and basic role-based permissions controlling which agents can access which connector's data.
- V1 must include: a simple admin view showing what data agents accessed and why, since the customer's core concern is likely visibility before anything more advanced.
- V1 should exclude: fine-grained per-field data masking and advanced anomaly detection, since these require more mature usage data to be built well and are not typically day-one blockers for a first Fortune 500 deployment.
- V1 should exclude: cross-connector policy templates beyond the four named systems, keeping scope tied to the connectors actually in this launch rather than building for hypothetical future ones.
- Justify the cuts by tying each excluded item to insufficient current usage data or lower deal-blocking risk, and commit to a named follow-up release so the customer sees a credible roadmap, not just cuts.
What a strong answer includes
- Scopes v1 tightly to the four named connectors and the customer's likely core concern, visibility and basic control, rather than a generic governance feature list.
- Justifies each exclusion with a specific reason, insufficient data or lower blocking risk, instead of just saying it was deprioritized.
- Commits to a follow-up roadmap for excluded items, which matters for keeping the Fortune 500 customer's confidence.
Common mistakes
- Scopes v1 too broadly, trying to cover advanced controls like anomaly detection before basic auditability is solid.
- Cuts scope without connecting each cut to a specific reason or a follow-up plan.
Likely follow-up questions
- How would you decide if a fifth connector needs to be added to v1 scope.
- What would you do if the customer insists on a control you scoped for v2.
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