Vision
FR EN

Zero-Trust · Distributed PEPs → Central PDP

A zero-trust architecture for enterprise AI

A navigable reference framework: never trust, always verify, assume breach — applied to AI agents and applications.

The three principles

Never trust, always verify

Every request is authenticated and authorized, regardless of origin.

Assume breach

Design expecting compromise: limit blast radius, segment by identity.

Least privilege & least agency

Grant only what is needed — and constrain what each agent tool can do.

The architecture planes