Glean's signature design question. The two traps: post-filtering that drains your top-k, and the leak through generated answers. The winning architecture filters at retrieval, and here is how, at scale.
more free answers with an account · no card
hardGleanMicrosoftOpenAI
Design RAG over 10M documents with per-user permissions: a user must never see data they can't access
Glean's signature design question. The two traps: post-filtering that drains your top-k, and the leak through generated answers. The winning architecture filters at retrieval, and here is how, at scale.
Updated Aug 2026 · Grounded in real Forward Deployed Engineer interview loops and written to a senior-engineer editorial bar.
Related course lessons
- Specify the ownership, trust, network and meaning at each boundary →
28 min · Free
Foundations of Forward Deployed Engineering · syllabus - Carry the caller’s permissions through every data and action boundary →
28 min · Free with sign-in
The FDE Engagement · syllabus - Give business definitions an executable home →
28 min · Free with sign-in
The FDE Engagement · syllabus
Keep practising
Learners often go here nextGive an agent memory across sessions without blowing up the context window or leaking between usersPremiumLearners often go here nextWalk me through a RAG pipeline end-to-end, and tell me where it usually breaksFreeNext in this trackYour agent fails 5% of the time mid-workflow, after executing real side effects. Make it safe.Premium
DISCUSSION · 0
No comments yet — be the first to share your approach.