TL;DR
Generative AI is everywhere, but most agents run with way too many privileges—think “admin access” on your entire data lake. Traditional access control can’t enforce the kind of context- and document-level rules you need, leaving your AI copilots prone to data leaks and compliance headaches.
In this talk, Ashish Jha makes the case for Fine-Grained Authorization to lock down RAG and agentic AI systems. You’ll see real-world demos with OpenFGA and LangChain, covering multi-tenant isolation, leakage prevention, audit trails—and how to scale to billions of access checks without slowing down your app.
Watch on YouTube
Top comments (0)