AI Audit Console

Reproducibility + decision guardrail verification

Run Detail

Run ID: 662bcf15-c51f-47dc-8337-43ddf028ce84

App: fraud-evaluator

Provider: openai

Provider Model ID: gpt-4.1-mini

Model Version: 2026-01-15

Model: gpt-4.1-mini

Config Snapshot: 1a9e98d1-5c3f-4730-affe-8dd5fcf26cd2

Created: 2026-04-19T02:53:06.386Z

Fingerprint: 0da811f6164b6caf997988be380694a5d4866ec839047927f82d6873d3417fe1

Guardrail Evaluations

  • default-guardrails: PASS
    []

Reproducibility Checks

As Baseline: 0

As Candidate: 0

Replay Execution

Run deterministic replay against the external provider and auto-check reproducibility.

Run Configuration Snapshot

{
  "id": "1a9e98d1-5c3f-4730-affe-8dd5fcf26cd2",
  "provider": "openai",
  "providerModelId": "gpt-4.1-mini",
  "providerModelVersion": "2026-01-15",
  "endpoint": "https://reti-backend-prod-54gd5jq6aq-du.a.run.app/api/analyze/query",
  "region": "global",
  "sdkVersion": "openai-node-4.x",
  "systemPrompt": null,
  "toolsSchemaHash": null,
  "environmentHash": null,
  "requestConfig": {
    "seed": 42,
    "topP": 1,
    "maxTokens": 400,
    "temperature": 0.2
  },
  "createdAt": "2026-04-19T02:53:06.371Z"
}

Audit Events

[
  {
    "id": "37bd1a2a-0fb3-4642-aee3-200688508b69",
    "runId": "662bcf15-c51f-47dc-8337-43ddf028ce84",
    "eventType": "RUN_INTAKE_COMPLETED",
    "payload": {
      "fingerprintId": "576f7301-e21b-448a-868c-a5c1ceaa99a1",
      "guardrailStatus": "PASS",
      "configSnapshotId": "1a9e98d1-5c3f-4730-affe-8dd5fcf26cd2"
    },
    "createdAt": "2026-04-19T02:53:06.450Z"
  }
]