Verify AI agent transactions at the moment of decision

If an AI agent can propose a payment, booking, or order, the system must be able to answer one question in real time: is this agent permitted to perform this action right now, within explicit limits? Verification means returning a transaction-scoped YES/NO decision plus proof you can log.

Run the verification flow.
See a binary decision and proof object, then map it to issuer/merchant integrations.
Try the live verification demo Consent receipts

Proof of permission

Permission must be encoded as an object (delegation/receipt), not implied by a token or session.

Stateless decisioning

Each transaction is evaluated independently from current context. No long-lived “trust me” state.

Replay-safe

Receipts/nonces can’t be reused to “double spend” authorization in agent workflows.

What must be verified (minimum)

Issuer vs merchant verification

Issuer-side (authorization)

Verify before returning an authorization response. Focus on consent, delegated scope, account standing, and risk signals.

Issuer AI agent authorization →

Merchant-side (checkout)

Verify before order creation and value release. Focus on basket policy, agent identity, and permission constraints.

Merchant AI agent verification →

Transaction-time verification flow (reference)

  1. Construct context: action, amount, currency, merchant/category, timestamp, device/runtime signals.
  2. Attach permission object: consent receipt or delegation reference + agent ID.
  3. Verify: signature/provenance, expiry/revocation, scope match, constraint match, policy checks, replay checks.
  4. Decide: return eligible: true|false plus a proof record.
  5. Log: store the proof with the payment/order/authorization record.
{
  "agent_id": "agt_123",
  "permission": { "type": "consent_receipt", "id": "cr_456" },
  "transaction": { "action": "payment.authorise", "amount": 4200, "currency": "GBP", "merchant": "m_789" }
}
→
{ "eligible": true, "proof": "sha256:…", "reason": "in_scope" }

Next: build the page cluster

FAQ

What should I log when verification returns YES?

Log the proof record (hash/ID), the receipt/delegation reference, policy version, and the transaction context used to decide. Don’t rely on UI screenshots.

Where does replay protection live?

Ideally in a nonce ledger that’s checked online. For offline flows, use freshness windows and reconcile nonces on reconnect.