Filter by access rights before the model
A poorly designed RAG system can show one customer another customer's documents, and that kind of leak is a security incident, not a display bug. The lesson helps a PM specify access control for RAG, place the filtering step in the pipeline, and ask the right questions about how the architecture protects data.
Lesson objective
By the end of this lesson, you will be able to specify a RAG system's access filtering (where rights come from, where the filter applies, how rights stay in sync) and to reject an architecture whose security relies on the prompt.
Questions this lesson answers
- How do you filter access rights in a multi-tenant RAG system?
- Is a prompt instruction enough to secure a RAG system?
- Where should access filtering happen before the model sees passages?
Topics covered
- RAG access control
- RAG security
- multi-tenant isolation
- AI data leakage
Where it fits
Access rights and freshness
How do you guarantee that each user only reads what they are allowed to see, in its current version?
Lessons in this module
- Filter by access rights before the model (this lesson)
- Keep the index up to date
What you will learn in this module
This lesson is part of the course Design a RAG architecture that fits your product
- Specify access filtering before the model reads any passage, and index freshness (resync, deletions, versions).
Related courses
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Build an AI assistant for your product
3 hr
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Evaluate an AI feature: test sets, metrics and LLM judges
3 hr
- AI & ProductExpertAdvanced level: for deeper mastery and specialization.
Ship and monitor an AI feature in production
3 hr