The KYE™ Decision Engine — decisions over meaning + state.
Step 5 holds the live instance graph. Step 6 is the engine that walks it. The Decision Engine (KYE Decision Engine™) consumes a candidate request, traverses the Authority Graph™, evaluates ontology-bound predicates, runs continuity + discoverability checks, and returns a signed verdict with reason code.
Walks the chain. Signs the verdict.
For every candidate decision the Decision Engine resolves the actor / principal / capability / scope context, evaluates it against the bound authority graph, ontology, continuity and discoverability inputs, and returns a verdict with a reason code. The verdict is bound into a signed Decision Map™ and chain-linked into the audit ledger.
The specific check ordering, the inter-check short-circuit rules, the verdict alphabet, and the per-verdict obligation set are proprietary and are not disclosed in this repository. Conformant runtimes consume the canonical contract via the private decision-engine binding.
One authorize call.
POST /v1/runtime/authorize
Content-Type: application/json
{
"actor_entity_id": "kye:agent:finance_agent_001",
"principal_entity_id": "kye:user:finance_owner_001",
"capability_id": "kye:capability:payment.prepare",
"scope": { "amount": { "value": 240, "currency": "GBP" } },
"delegation_id": "kye:delegation:0xabc"
}Bespoke per-vendor gates are replaced by one signed verdict + one signed Decision Map™, replayable offline by any third party with the published JWKS.
Continue the stack →
Every claim here is backed by the open KYE Protocol™ contracts and verifiable end-to-end from the publisher's JWKS — you check it yourself, you don't take our word for it.
Ready to see your AI agents flagged?
Start in shadow mode. We’ll deliver your first Evidence Pack™ in 4–8 weeks.