Your AI Agents Are Overprivileged: The Case for Fine-Grained Authorization

Generative AI is everywhere, but what if your bots are snooping where they shouldn’t? Ashish Jha’s NDC Copenhagen talk dives into why traditional access control just can’t keep up with contextual, document-level permissions in AI systems.

You’ll learn how Fine-Grained Authorization (FGA) with tools like OpenFGA and LangChain can lock down RAG and agentic AI—think multi-tenant isolation, leakage prevention, audit trails, and billions of checks at scale without slowing things down. Whether you’re building an internal copilot or a customer-facing AI, securing your data boundaries is a must-win battle.

Watch on YouTube