Authority before the model runs
The inference call is the last point before an agent acts. KYE™ puts a Policy Enforcement Point there: an OpenAI-compatible inference gateway — NIM, Triton, vLLM, TGI — consults it before running the model, and the answer is admit, block, escalate, or quarantine.
This is what makes Open Access Authority™ enforced rather than merely declared — authority is checked at the physical boundary where the action would happen.
How it works
This is infrastructure you deploy, not an app you open: a thin PEP sits in front of your inference endpoint.
- Extract. From each request, derive the proposed action — invoking a model, or, if the request declares tools, invoking a tool (the consequential case).
- Decide. Consult the central KYE™ admissibility decision for this agent, right now — reusing the same decision engine the rest of the protocol uses.
- Enforce. Map the verdict to a gateway action: proceed, block with a 403, escalate to approval, or quarantine the agent.
- Evidence. Seal the decision into an Evidence Pack™, replay-verifiable from public keys alone.
Why the inference boundary
For a platform or security team, this is the one place enforcement cannot be bypassed.
- It is the last gate before action: every agent path, whatever framework, funnels through inference.
- A request declaring tools — a wire transfer, a database write — tightens the check exactly when it matters.
- The EU AI Act's logging and human-oversight duties bind at runtime; this is where you discharge them.
Boundary: KYE™ governs whether the agent may act; it does not run the model or proxy the tokens — that stays with your inference engine. Part of the KYE Protocol™ platform; pairs with the Weights & Biases provenance integration.