> ## Documentation Index
> Fetch the complete documentation index at: https://docs.antonpayments.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Anton Intelligence

> Create normalized risk intelligence evaluations for payees, instruments, payouts, and merchant onboarding.

Anton Intelligence turns payment-risk inputs into one concise evaluation result. You send a strict request with a `use_case`, an `entity`, and optional instrument or payout context. Anton normalizes the request internally, calls independent peer systems, applies deterministic policy and a five-dimension scoring model, and returns a final decision.

The create endpoint is intentionally strict. Unknown fields are rejected, enum values are fixed, and sensitive values are used only in memory. Anton persists redacted decision evidence, not raw PII. Every response includes `contract_version: "intelligence-public-v1"` so clients can pin and generate SDKs against a stable schema.

## Two surfaces, one contract

| Surface                                   | Auth                                                                               | Persistence                                                                                                                                                                                                        |
| ----------------------------------------- | ---------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Authenticated** (production contract)   | OAuth + DPoP with the `intelligence` scope — see [Authentication](/authentication) | Evaluations persist under **your** merchant account; read them back via the scoped [list](/api-reference/intelligence/list-evaluations), get, and evidence endpoints. `Idempotency-Key` is **required** on create. |
| **Anonymous public test** (where enabled) | None                                                                               | Evaluations run under a shared synthetic test merchant — not tied to your account, and not listable.                                                                                                               |

The request and response contract is identical on both surfaces. Intelligence is available on **every** account tier — including [AI-compliance-only accounts](/capabilities) that have no payout surface. Start with the [quickstart](/guides/intelligence/quickstart) for the full authenticated walkthrough.

## Use cases

| Use case               | When to use it                                            | Event type            |
| ---------------------- | --------------------------------------------------------- | --------------------- |
| `payee_registration`   | Registering or screening a person or business payee       | `payee.create`        |
| `instrument_screening` | Adding or screening a bank account, wallet, card, or IBAN | `instrument.create`   |
| `payout_screening`     | Evaluating payment movement context                       | `payout.create`       |
| `merchant_onboarding`  | Evaluating business onboarding data                       | `merchant.onboard`    |
| `monitoring`           | Generic/manual screening                                  | `monitoring.evaluate` |

## Required shape

```json theme={}
{
  "use_case": "payee_registration",
  "entity": {
    "type": "person"
  }
}
```

For a meaningful evaluation, include at least one searchable input: `entity.name`, `entity.vault_token_id`, `instrument.vault_token_id`, or the matching instrument fields.

## Validate before creating

Use validation to test request shape without creating an evaluation:

```bash theme={}
curl -sS -X POST "https://api.antonpayments.dev/v1/intelligence/evaluations/validate" \
  -H "Authorization: DPoP $ANTON_ACCESS_TOKEN" \
  -H "DPoP: $ANTON_DPOP_PROOF" \
  -H "Content-Type: application/json" \
  -d '{
    "use_case": "payee_registration",
    "entity": {
      "type": "person",
      "name": "John Doe",
      "country": "US"
    }
  }' | jq
```

## Field rules

| Field class           | Rule                                                                |
| --------------------- | ------------------------------------------------------------------- |
| Countries             | Uppercase ISO 3166 alpha-2, such as `US` or `CA`                    |
| Dates                 | Real calendar dates in `YYYY-MM-DD` format                          |
| Currencies and assets | Uppercase supported currency or asset codes, such as `USD` or `BTC` |
| Instrument payloads   | The nested payload must match `instrument.type`                     |

## Response summary

The full response carries the decision, a five-dimension `scoring` block (Transaction Risk, Onboarding Risk, Transaction Monitoring, Anomaly Detection, Graph Intelligence — each 0–1000), peer statuses, policy outcome, and an audit hash — see the [quickstart](/guides/intelligence/quickstart) for a complete example. The normalized `summary` block:

```json theme={}
{
  "contract_version": "intelligence-public-v1",
  "decision": "review_auto",
  "next_action": "request_more_information",
  "summary": {
    "screened": ["entity", "instrument"],
    "use_case": "instrument_screening",
    "instrument_type": "crypto_wallet",
    "findings_count": 1,
    "identity_confidence": "possible",
    "missing_fields": ["address", "birth_date", "identifier"]
  }
}
```