33Your RAG system can surface documents a user shouldn't see. How do you enforce authorization in retrieval?▼hardGleanMicrosoftSalesforce2 replies◆ premiumAn enterprise RAG that retrieves across everyone's documents is a breach waiting to happen. The fix lives in the retrieval layer, not the prompt. Here is the design that survives a security review.Open full answer →
49Why is 'the model is not a trust boundary' the core principle of secure RAG, and how do you build on it?▼hardAnthropicMicrosoftGoogle2 replies◆ premiumAsking the model to keep secrets or enforce permissions is asking the wrong component. The signal is enforcing access control before retrieval, in code you trust, and treating the LLM as untrusted compute over already-authorized data.Open full answer →
58Your agent calls tools on behalf of users. How do you design its identity, credentials, and authorization?▼hardNewGleanSierraAnthropic◆ premiumAn agent running on one over-privileged service account is a confused deputy waiting to happen. The signal is per-user delegated credentials, token exchange, per-tool scopes, and an audit trail that names the human. Here is the answer.Open full answer →
