AI & Technical question
Design the next version of Glean’s Indexing API and custom connector platform for large enterprises that need to bring proprietary data sources online quickly. What core capabilities would you prioritize, such as schema/modeling, auth and permissions, incremental sync, observability, and governance, and what principles would you use to keep the platform flexible without creating an inconsistent product experience?
- Glean
- AI & Technical
- 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 designing a next-generation platform API for custom enterprise connectors, prioritizing schema, auth, sync, observability, and governance while keeping the platform consistent, not fragmented.
How to approach it
- Prioritize incremental sync and schema modeling first, since large enterprises with proprietary sources need fast, reliable updates and a way to describe custom document types without a full re-index.
- Prioritize auth and permissions next, supporting flexible source-system auth models while mapping into Glean's canonical permission model, so governance stays consistent with existing connectors.
- Add observability, sync status, error rates, and freshness lag, visible to the customer building the connector, so they can self-diagnose issues instead of filing tickets.
- Bake governance in from the start, requiring every custom connector to declare its permission granularity, rather than treating it as a bolt-on for regulated customers later.
- Keep the platform consistent by enforcing a small set of required interface contracts, schema declaration, auth handshake, sync protocol, while leaving implementation details flexible for the customer's source system.
- Pilot the v2 API with one enterprise building a genuinely custom, high-complexity source before general release.
What a strong answer includes
- Sequences schema and incremental sync before auth polish, since without reliable sync the connector isn't useful regardless of governance quality.
- Requires permission granularity declaration as a mandatory part of the API contract, keeping the earlier unified governance design consistent for custom connectors too.
- Gives developers self-serve observability, reducing support burden while building trust that the connector is actually working.
- Enforces a small, required interface contract to prevent platform fragmentation, while leaving real implementation flexibility elsewhere.
Common mistakes
- Treating governance as an add-on for later instead of a required part of the connector contract from day one.
- Making the API so flexible that every custom connector behaves inconsistently with the rest of the platform.
- Skipping observability tooling, leaving customers unable to self-diagnose sync or freshness issues.
Likely follow-up questions
- How would you version this API as customer needs evolve?
- What's the minimum governance declaration you'd require even for a low-risk connector?
More ai & technical questions
- How would you measure whether Glean's AI answers are accurate and well-cited?Glean · AI & Technical · Medium
- How would you design a governance model that behaves consistently across Glean's UI, public APIs, and heterogeneous enterprise connectors, for example, a shared policy layer for permissions, action scopes, audit logging, and redaction, even when source systems expose different authentication models and data granularity?Glean · AI & Technical · Hard
- A Fortune 500 customer asks for an audit trail for every AI-agent answer: which data sources were accessed, which permissions were applied, why the response was generated, and whether sensitive content was filtered or redacted. Design the admin and end-user experience, and the core APIs/data model needed to support this without overwhelming either audience.Glean · AI & Technical · Hard
- Several enterprise customers report that the ServiceNow and GitHub connectors are ingesting data successfully, but search results and assistant answers still feel incomplete or low quality. How would you diagnose where the breakdown is across crawl freshness, permissions sync, metadata extraction, entity mapping, ranking, and UX, and how would you decide which fixes to ship first?Glean · AI & Technical · Hard
- Glean Model Hub lets enterprise customers choose among LLMs for search, assistant, and agent workflows. How would you build a model-provider evaluation framework to decide which new providers to add, including the gating criteria, offline/online evals, and the tradeoffs you would make across answer quality, latency, security, cost, and enterprise-specific requirements?Glean · AI & Technical · Hard
- Suppose Glean wants to launch a new answer-generation experience in core search. How would you define the MVP and rollout plan given enterprise constraints around permissions, citations, latency, model choice, and admin controls? What would need to be true before you scaled it broadly?Glean · AI & Technical · Hard
More questions from Glean
Learn the skill behind it
Chapters of the AI PM course that teach what this question tests.
- Chapter 1: Foundations: the model and the decisions it forces on you
- Chapter 8: Evals: define good and make the number defensible
- Chapter 6: Agents and agentic architecture