Wants AI access to follow existing authorisations, not bypass them.
Platform · Role-based access
Policy, documentation and internal knowledge are routed by role, with end-to-end RBAC over both retrieval and inference. No one sees more through the AI than they are allowed to see.
Wants AI access to follow existing authorisations, not bypass them.
Wants certainty that sensitive documents do not end up in an answer via a detour.
Wants to reuse roles from its own IdP, not maintain a separate access model.
The problem
RAG systems sitting on one big knowledge source give everyone access to everything the model has ingested — regardless of what that person is allowed to see.
Numaga applies role-based access across the whole chain: what is retrieved and what is inferred both stay within the user’s permissions.
How it works
RBAC is not a filter at the end — it applies at every step.
Access maps to the roles and groups you already manage via SSO — no second authorisation model.
The knowledge base returns only documents the user is entitled to; the rest is never retrieved.
The model, too, works only with context the user is allowed to see — no leakage via a detour.
Who saw which context sits in the audit trail — traceable at every review.
We show how RBAC over retrieval and inference works in your environment.
Get demo access