How would you answer an interview scenario involving Metadata filtering?

For an interview scenario involving Metadata filtering, I would first clarify the business goal, scale, constraints, and the failure or quality attribute the interviewer wants to explore. Metadata filtering restricts retrieval using attributes such as tenant, document type, product, region, language, date, or access level. In this scenario, for a multi-tenant RAG application, explain how you would ensure one customer can never retrieve another customer’s documents. I would then explain the main alternatives and tradeoffs, identify likely failure modes, and describe how I would validate the solution through testing, observability, security controls, and recovery or rollback planning.