KYA— Know Your Agent

Protocol

What is KYA?

KYA is a governance protocol for autonomous agents. It defines identity, ownership, risk, mandates, and audit — the contract every agent must satisfy before acting.

Principles

Why KYA exists.

Five commitments that shape every part of the protocol.

  1. 01

    Identity is the foundation

    An agent without a stable identity is unreviewable, unauditable, and untrustable. KYA binds an agent to a vendor, a model, and a prompt fingerprint that uniquely identifies its behaviour.

  2. 02

    Authority is bounded

    Agents do not hold open authority. They operate under a defined mandate — what they may do, on whose behalf, within what limits — recorded before any action takes place.

  3. 03

    Risk is measured, not assumed

    Every agent carries a risk score derived from its profile, data sources, and history. Risk is visible to operators and feeds into policy decisions automatically.

  4. 04

    Oversight is non-optional

    Sensitive actions require human confirmation. Oversight is a first-class property of the protocol, not an afterthought bolted onto execution.

  5. 05

    Records outlast the agent

    Proposals, approvals, executions, and outcomes are append-only. Even after an agent is revoked, its history remains available for review and audit.

Identity model

What does KYA know about an agent?

Six attributes that make an agent reviewable, attributable, and auditable.

agent_idattribute

Stable identifier

Persistent across re-deployments.

owner_idattribute

Principal link

Every action is attributable.

prompt_hashattribute

Behavioural fingerprint

SHA-256 of the system prompt.

data_sourcesattribute

Declared access

What the agent may read.

human_oversightattribute

Supervision flag

Is a human reviewing actions?

spend_capattribute

Authorised ceiling

Hard limit per window.

Risk model

Three bands, one decision rule per band.

A risk score is computed for every agent. It is used to route proposals automatically and to surface risk to operators.

low0 – 32

Routine actions allowed under standard policy.

medium33 – 65

Approval required above per-action thresholds.

high66 – 100

All actions require explicit owner confirmation.

Lifecycle

Agent states are first-class.

Every transition is recorded; nothing is implicit. Operators see history; owners see authority.

  1. 01
    Draft
    Agent is created locally; KYA profile not yet submitted.
  2. 02
    Pending review
    Submission accepted; compliance review in progress.
  3. 03
    Approved
    KYA decision recorded. Agent may begin authorised actions.
  4. 04
    Active
    Operating under policy limits; every action is audit-logged.
  5. 05
    Frozen / Revoked
    Authority withdrawn. Pending actions are blocked.

Mandates

Authority is granted in writing.

A mandate is a structured grant of authority: scope, caps, categories, expiry. It is the agent's contract with the principal.

  • Spend caps — daily and per-action.
  • Categories — allow-list of permitted purposes.
  • Merchants — optional restriction on counterparties.
  • Expiry — automatic revocation after a set period.
  • Approval default — always-confirm, no exceptions in MVP.
Mandateactive
agent
agt_01HEZ8K3W9XM2
principal
own_01HEZ7Q83T
scope
procurement
spend_cap
5,000 USD / day
categories
compute, saas
expires
2026-12-31
approval
always_confirm

Events

Every state change is an event.

Events are append-only. They are the substrate for audit, reconciliation, and webhook delivery.

event.jsonjson
{
  "event_id": "evt_01HEZ8K3W9XM2",
  "type": "proposal.approved",
  "agent_id": "agt_01HEZ8K3W9XM2",
  "owner_id": "own_01HEZ7Q…",
  "payload": {
    "amount": 24900,
    "currency": "USD",
    "merchant": "API Provider",
    "purpose": "Inference credits"
  },
  "policy": {
    "matched": ["spend_cap.daily", "category.compute"],
    "risk_score": 24
  },
  "ts": "2026-05-22T09:14:08Z"
}

Early access

Build on a protocol, not a hack.

If you're shipping agents, KYA gives you the trust layer you'd otherwise have to invent.