Voice intelligence - Verify Group

Scenarios

Scenario	Use case
`customerSupportComplaint`	FNOL / intake calls (default)
`fraudSignalDetection`	SIU / fraud investigation
`debtCollection`	Collections calls

Trigger analysis

POST /api/v1/voice/sessions/{sessionId}/analyze

{"forceReanalysis": false}

Result structure

{
  "analysisResults": {
    "primaryScore": 62,
    "recommendedDecision": "MANUAL_REVIEW",
    "headline": "Moderate stress detected",
    "keyScores": {"stress": 68, "deception": 45, "coaching": 31},
    "importantCallSignals": [{"type": "elevated_stress", "confidence": 0.78}]
  }
}

Composite fraud score

POST /api/v1/forensics/poi-fraud-check

{"claimId": "claim-uuid"}

Returns per-participant composite scores combining voice, KYC, and evidence signals.

When a SCENARIO_MISMATCH_NOT_SCORED warning is returned, the backend retries automatically with the suggested scenario.