Get Fraud Metrics
paybond_get_fraud_metricsGet tenant-wide fraud backtesting and monitoring metrics over a rolling window: flagged operators, severity counts, review outcomes, precision/false-positive rates, and backtest summary. Requires Signal analytics access.
Instructions
Use this when you need tenant-wide Signal fraud backtesting and monitoring metrics over a rolling window (flagged operators, severity counts, review outcomes, precision/false-positive rates, and backtest_summary). Requires PAYBOND_API_KEY with Signal analytics read access and the private-dashboards feature. Do not use this for one operator's fraud posture—call paybond_get_fraud_assessment instead—or for Harbor intent escrow detail—call paybond_get_intent. Idempotent read with no side effects; omit window to default to 24h; unsupported windows fail with HTTP 400 ("window must be one of 24h, 7d, or 30d").
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| window | No | Rolling metrics window. Allowed values: 24h, 7d, 30d. Omit to use the gateway default 24h. Unsupported values fail with HTTP 400. | |
| score_version | No | Optional Signal score model version to query. Omit to use the gateway default current model (1.0). Example: 1.0. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| window | No | Active metrics window label: 24h, 7d, or 30d. | |
| tenant_id | No | Tenant echoed by the gateway for the authenticated API key (example: tenant-a). | |
| window_ended_at | No | RFC3339 end of the evaluated rolling window. | |
| backtest_summary | No | Human-readable backtest summary derived from the window metrics. | |
| high_signal_count | No | Count of high-severity fraud signals in the window. | |
| review_open_count | No | Operators currently in an open review state. | |
| window_started_at | No | RFC3339 start of the evaluated rolling window. | |
| score_model_version | No | Score model version used for the metrics (echoes the requested score_version or the gateway default 1.0). | |
| confirmed_risk_count | No | Labeled confirmed-risk outcomes in the window. | |
| false_positive_count | No | Labeled false-positive outcomes in the window. | |
| critical_signal_count | No | Count of critical-severity fraud signals in the window. | |
| elevated_signal_count | No | Count of elevated-severity fraud signals in the window. | |
| labeled_outcome_count | No | Review outcomes labeled in the window (confirmed risk, false positive, or needs more evidence). | |
| flagged_operator_count | No | Operators with at least one fraud signal in the window. |