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.

KYE™ at the inference boundary (NVIDIA NIM · vLLM), stage by stage

Demo data

You learn: How it works, one stage at a time. You can: Run it end to end.

  1. Extract

    KYE Protocol™

    From each request, derive the proposed action — invoking a model, or, if the request declares tools, invoking a tool (the consequential case).

  2. Decide

    KYE Protocol™

    Consult the central KYE™ admissibility decision for this agent, right now — reusing the same decision engine the rest of the protocol uses.

  3. Enforce

    KYE Protocol™

    Map the verdict to a gateway action: proceed, block with a 403, escalate to approval, or quarantine the agent.

  4. Evidence

    KYE Protocol™

    Seal the decision into an Evidence Pack™ , replay-verifiable from public keys alone.

How this widget is built
Demonstrates
KYE Protocol™
Components
  • The stages this page describes
Flow
Each stage in order, as the page sets it out. Architecture diagram
Used on

This is what makes Open Access Authority™ enforced rather than merely declared — authority is checked at the physical boundary where the action would happen.

Start a governed pilot See Open Access Authority™

How it works

This is infrastructure you deploy, not an app you open: a thin PEP sits in front of your inference endpoint.

  1. Extract. From each request, derive the proposed action — invoking a model, or, if the request declares tools, invoking a tool (the consequential case).
  2. Decide. Consult the central KYE™ admissibility decision for this agent, right now — reusing the same decision engine the rest of the protocol uses.
  3. Enforce. Map the verdict to a gateway action: proceed, block with a 403, escalate to approval, or quarantine the agent.
  4. 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.