Skip to content
Request a pilot

Sharp Trust

Every transaction scored. Every decision explained.

Risk decisions for payments initiated by AI agents. One API call returns Approve, Ask the customer, Refer or Decline—with reasons—before authorization.

Request pilot accessRead the API specification
What it is
A pre-authorization risk layer
One call in, one decision out: Approve, Ask the customer, Refer or Decline, with the Sharp Score and its reasons. Non-custodial, network-agnostic, and it never touches card data.
Who it's for
Whoever carries the risk
Acceptance-side platforms taking payments initiated by AI agents: merchants, PSPs and micropayment platforms.
What it solves
Fraud tools go blind when an agent pays
No device, no biometrics, no session, and a hijacked agent moves at machine speed. We verify the agent, check the transaction against what the cardholder actually authorized, and score it in real time. Good payments go through; off-mandate spend and impostor agents stop.

Integration

One call in, one decision out

You send the transaction, we return the decision. Send what you have; every field you add makes the answer sharper. You never send a card number, a CVV or any payment credential.

Your request

POST /v2/scoreHost: api.trust.sharp-labs.comAuthorization: Bearer sk_live_...{  "identity_basis": "signature_verified",  "cart": { "total": { "amount_minor": 134000, "currency": "EUR" } },  "consumer_instruction": {    "presented": true,    "max_amount": { "amount_minor": 40000, "currency": "EUR" }  },  "psp_reference": "pi_88213"}

Our response

200 OK{  "decision_id": "dec_9f21c8a4",  "score": 59,  "decision": "review",  "reason_codes": [    "consumer_instruction_amount_exceeded",    "anomalous_velocity"  ],  "mandate": { "verdict": "violated" }}

Four outcomes. You decide when each one fires.

Without a graded decision the acceptance side has two options: take all agent traffic, or refuse it. The output stays small on purpose, because a decision you have to interpret is not one. The work is in being right, and in being able to show why.

  • Approveapprove

    Consistent and safe

    Continue to authorization

  • Ask the customerchallenge

    Plausible, but unconfirmed

    The customer confirms, for example with a passkey

  • Referreview

    Ambiguous or conflicting

    Hold it for a person to decide

  • Declinedecline

    Off-mandate or anomalous

    Stop the transaction

You draw the lines, not us
A platform taking EUR 5 micropayments and one taking EUR 5,000 orders should not put the boundary in the same place. Thresholds are set per platform and versioned, so you can move them and still explain what happened last month.
You decide whether we can stop anything
Advisory means we return the decision and you act on it. Hard block means we can halt the transaction outright. Most pilots start advisory and tighten once the scores have earned enough trust.

Every decision carries

  • A Sharp Score from 0 to 100, higher is riskier
  • A confidence level
  • Machine-readable reason codes
  • An immutable audit record

What we never receive

  • Card numbers
  • CVV or track data
  • Usable cryptograms

The score

Six factors determine the score, and you see all of them

Two are gates: fail them and the transaction is declined regardless of everything else. The other four are weighted signals that grow more accurate as history accrues. Every one of them returns a reason code, so a decision is never a number you have to take on trust.

  • F1Gate

    Identity and authenticity

    Signature validity, replay window and domain binding. A forged or replayed signature is declined outright.

  • F2Gate

    Mandate consistency

    Does the transaction match what the cardholder actually authorized: amount, counterparty, scope. A mismatch is the strongest early fraud signal there is.

  • F3Signal

    Behaviour and velocity

    Frequency, burst detection and amount drift measured against the agent’s own baseline, not a generic one.

  • F4Signal

    Cross-network reputation

    Disputes, refunds and completions aggregated across networks. This is the part no single network can see on its own.

  • F5Signal

    Transaction context

    Does the purchase match the instruction the user gave: the right amount, the right merchant, the right items.

  • F6Signal

    Counterparty risk

    The seller side. New or unverified sellers, dispute history, and prices that do not match the catalogue.

Decision · txn_9f21c8a4Live
Sharp Score · higher is riskier

59 / 100

REFER
Starting score
30
Net adjustment
+29
Confidence
0.86
Enforcement
advisory
Latency
118 ms
Factor contribution
  • Identity & authenticityF1identity_agent_signature_valid−18
  • Mandate consistencyF2consumer_instruction_amount_exceeded+31
  • Behaviour & velocityF3anomalous_velocity+12
  • Cross-network reputationF4counterparty_trust_low+4
Platform thresholdsCardholder mandate cap EUR 400 · attempted EUR 1,340
APPROVEREFERDECLINE

118 ms

Median decision latency, returned before the transaction reaches authorization.

Zero

Card numbers received, stored or transmitted. Token references and metadata only.

Any network

Scheme-agnostic by design. One integration, whatever rails the transaction arrives on.

Sharp Trust

Already seeing agent traffic?

We are running early pilots with acceptance-side platforms. Tell us what you are seeing and we will tell you whether we can help.

Request pilot access