VEverdun
analytics

Get Agent Agreement

AI-vs-operator agreement: precision/recall of the agent's recommended action (and of the actual auto-dismiss gate) against human dispositions as ground truth. Same tenant scoping as /analytics/summary.

403 for a curated role rather than curated: there is no customer- meaningful reading of "AI vs operator agreement precision" — it is a staff accuracy-monitoring metric, and every input to it (gate-stops, auto-dismissals, what the agent recommended doing) is exactly the internal pipeline detail this feature hides. Unlike the incident-counts/events endpoints, curating this one down to only customer_visible rows would not produce a meaningful "agreement rate" — it would produce a rate over a handful of already-escalated events, which is not what this metric means.

get/analytics/agent-agreement

Request

  • Base URL
    https://api.verdun.ai (the document declares no server; this is the origin it was published from)
  • URL
    https://api.verdun.ai/analytics/agent-agreement
  • Auth
    HTTP bearer

Query parameters

startstring date-time nullable
endstring date-time nullable
parent_idstring[] nullable
site_idstring[] nullable
camera_idstring nullable

Response

Successful Response

range_startstring date-time required

Start of the analyzed range (UTC).

range_endstring date-time required

End of the analyzed range (UTC).

Example response

{
  "totals": {
    "reviewed": 124,
    "with_recommendation": 110,
    "agreement": 96,
    "agreement_rate": 87.3
  },
  "confusion": [
    {
      "recommended": "non_threatening",
      "disposition": "non_threatening",
      "count": 41
    }
  ],
  "classes": [
    {
      "action": "false_alarm",
      "precision": 92.1,
      "recall": 88.4,
      "predicted": 38,
      "support": 40
    }
  ],
  "dismiss_screen": {
    "precision": 97.5,
    "recall": 84,
    "false_dismissals": 2
  },
  "gate_simulation": {
    "would_auto_dismiss": 58,
    "correct": 57,
    "wrong": 1,
    "precision": 98.3,
    "coverage": 46.8,
    "blocked_by_camera_types": 3
  },
  "cameras": [
    {
      "camera_label": "Loading dock",
      "site_name": "Downtown Plaza",
      "reviewed": 31,
      "with_recommendation": 29,
      "agreement_rate": 89.7,
      "gate_would_dismiss": 14,
      "gate_precision": 100,
      "agent_incident_types_count": 12,
      "gate_blocked_by_camera_types": 2
    }
  ]
}

Changes

No recorded changes to this operation across all 2 revisions of this API.