> ## Documentation Index
> Fetch the complete documentation index at: https://koreai.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Auto QA Reporting API
[Back to API List](/ai-for-service/apis/quality-ai/api-list)
The Auto QA Score Reporting API returns interaction-level evaluation data, including Auto QA scores, metric results, duration-based eligibility, disposition, and audit details. Audit data includes audit status, audit date, auditor, and audit responses by metric, enabling AutoQA vs. ManualQA analysis and audit-level reporting.
The API supports contact direction (inbound/outbound), uses `duration_status` to indicate evaluation eligibility, supports date-range and pagination filters, and can include below-threshold interactions when requested. Direction-specific evaluation logic enables directional segmentation and reporting.
| **METHOD** | **POST** |
| :------------ | :-------------------------------------------------------------------------------------------------------------------------------- |
| Endpoint | `https://{{host}}/qualityai/api/v1/public/qualitymanagement/app/{{streamId}}/scorereporting` |
| Content Type | `application/json` |
| Authorization | `auth: {{JWT}}` — See [How to generate the JWT Token](/ai-for-service/apis/automation/api-introduction#generating-the-jwt-token). |
| API Scope | Quality Management Analytics. |
## Header Parameters
| Parameter | Description | Type |
| :------------- | :----------------------------------------------------------------- | :--------------- |
| `Content-Type` | `application/json` | string, required |
| `accountId` | Unique account identifier. For example, `67a9ca06cf0e510a8632xxxx` | string, required |
| `orgId` | Unique identifier of the organization. | string, required |
| `auth` | JWT token used for authentication. | string, required |
## Path Parameters
| Parameter | Description | Type |
| :--------- | :--------------------------------------------------------------- | :--------------- |
| `host` | Environment URL. For example, `https://platform.kore.ai/` | string, required |
| `streamId` | `botId` or `streamId`. Retrieve this from the App Settings page. | string, required |
## Sample Request
```bash theme={null}
curl --location 'https://{{host}}/qualityai/api/v1/public/qualitymanagement/app/{{streamId}}/scorereporting' \
--header 'accountId: {{accountId}}' \
--header 'auth: {{JWT_TOKEN}}' \
--header 'Content-Type: application/json' \
--header 'orgId: o-da5be4e0-8fbb-5229-ac20-9b1384ebxxxx' \
--data '{
"offset": 0,
"startDate": "2026-03-23 10:17:54",
"endDate": "2026-03-23 23:36:35",
"include_below_threshold": true,
"contact_direction": "inbound"
"limit": 100
}'
```
## Body Parameters
| Parameter | Description | Type |
| :------------------------ | :------------------------------------------------------------------------------------------------------------------------------- | :---------------- |
| `offset` | Number of records to skip for pagination. | integer, optional |
| `startDate` | The start date from which records are retrieved. Use UTC format: `YYYY-MM-DDTHH:MM:SS.NNNZ`. For example, `2026-03-23 10:17:54`. | string, required |
| `endDate` | The end date to include records. Use UTC format: `YYYY-MM-DDTHH:MM:SS.NNNZ`. For example, `2026-03-23 23:00:35`. | string, required |
| `include_below_threshold` | When `true`, includes contacts marked Below Threshold in the response. Default: `false`. | string, required |
| `limit` | Number of records to retrieve per page (maximum `100`). | integer, optional |
| `contact_direction` | Filters results by `inbound` or `outbound`. | string, optional |
APIs exclude contacts below the threshold by default. An `include_below_threshold=true` parameter allows explicit inclusion for ad hoc analysis.
## Sample Response
```json theme={null}
{
"results": [
{
"conversationId": "c-0179c0cc********60dbed",
"Queues": [
{
"Queue ID": "qu-8ebc557-57c********698cd5",
"Queue Name": "Inbound Q"
}
],
"Agents": [
{
"Agent ID": "a-647043a-dac********6b688",
"Agent Name": "xxxxx admin"
}
],
"koreEvalutionScore": 0,
"fatalErrorCount": 1,
"Language": "English",
"duration_status": "evaluated",
"Disposition": [
{
"setId": "dst-57b825e-cea1-4643-9b3c-4d24538bxxxx",
"setName": "Resolution",
"code": [
{
"id": "ds-e73c46c-c826-4294-b326-ae94429axxxxx",
"name": "Requires Supervisor Attention",
"colour": "#800080"
}
]
},
{
"setId": "dst-d8863d8-9cb2-4a3d-a132-79983c49xxxx",
"setName": "set2",
"code": []
},
{
"setId": "dst-a06a346-aed9-4b53-8433-5999b70dxxxxx",
"setName": "test set",
"code": [
{
"id": "ds-939696c-c33c-42b8-a749-e3312767xxxxx",
"name": "code2",
"colour": "#FB3199"
}
]
}
],
"Metrics": [
{
"Metric ID": "em-5a2e735a-5cc********61847",
"Metric Name": "AU",
"Metric Weight": 5,
"Metric Negative Weight": 11,
"Qualification": "NA",
"isFatalError": false,
"Auditor Response": null
},
{
"Metric ID": "em-0b1ca817-c********6afa1",
"Metric Name": "AU Dyn Gen ai+ deter",
"Metric Weight": 10,
"Metric Negative Weight": 12,
"Qualification": "NA",
"isFatalError": false,
"Auditor Response": null
},
{
"Metric ID": "em-69bc23c********6dc2a2",
"Metric Name": "Booking playbook",
"Metric Weight": 7,
"Metric Negative Weight": 0,
"Qualification": "YES",
"isFatalError": false,
"Auditor Response": null
},
{
"Metric ID": "em-0a7f9c8cc********6db3b",
"Metric Name": "End_Gen ai",
"Metric Weight": 20,
"Metric Negative Weight": 31,
"Qualification": "NO",
"isFatalError": true,
"Auditor Response": null
}
],
"contactDirection": "inbound",
"AuditStatus": "Unassigned",
"AuditDate": null,
"AuditorName": null,
"custom_fields": {}
}
]
}
```
## Response Body Parameters
| Parameter | Description | Type |
| :----------------------- | :-------------------------------------------------------------------------------------------------------------------------------- | ----------------- |
| `results` | List of conversation objects returned for the request. | array |
| `conversationId` | Unique system-generated identifier for the conversation. | string |
| `customConversationId` | Custom identifier provided at ingestion time; present only when set during upload. | string |
| `queues` | List of queue objects associated with the conversation. | array |
| `queueId` | Unique identifier for the queue. | string |
| `queueName` | Name of the queue. | string |
| `agents` | List of agents who participated in the conversation; multiple agents may exist per conversation. | array |
| `agentId` | Unique identifier for the agent. | string |
| `agentName` | Name of the agent. | string |
| `koreEvaluationScore` | Auto QA score (-100 to 100); returns `null` for `below-threshold` or `unavailable duration`. | number or null |
| `fatalErrorCount` | Number of fatal metric failures; returns `0` when none are present. If a fatal error occurs, `koreEvaluationScore` is set to `0`. | integer |
| `language` | Conversation language. | string |
| `metrics` | List of evaluation metric objects applied to the conversation. | array |
| `metricId` | Unique identifier for the evaluation metric. | string |
| `metricName` | Name of the evaluation metric as configured in the evaluation form. | string |
| `metricWeight` | Positive weight assigned to the metric. | number |
| `metricNegativeWeight` | Negative weight assigned; returns `0` when not configured. | number |
| `qualification` | Agent outcome for the metric (`YES`, `NO`, `NA`); present only when `duration_status` is `evaluated`. | string (enum) |
| `isFatalError` | Indicates whether the metric is fatal and not met; if `true`, `koreEvaluationScore` is set to `0`. | boolean |
| `duration_status` | Evaluation eligibility status (`evaluated`, `below_threshold`, `duration_unavailable`). | string (enum) |
| `disposition ` | List of disposition sets associated with the conversation. | array |
| `evaluation_status` | Overall evaluation result (`pass`, `fail`, `not_evaluated`). | string (enum) |
| `audit_status` | Status of audit assignment or completion; returns `null` if unavailable. | string or null |
| `contact_direction` | Resolved interaction direction (`inbound` or `outbound`). | string (enum) |
| `is_direction_defaulted` | Indicates whether direction was system-inferred (`true`) or provided at ingestion (`false`). | boolean or null |
| `channel` | Interaction channel (`voice` or `chat`). | string |
| `auditor` | Name of the auditor. | string or null |
| `AuditStatus` | Audit workflow status (`Audited`, `Assigned`, `Not Assigned`). | string |
| `AuditScore` | Score assigned during audit evaluation; returned only when completed. | number (optional) |
| `audit_date` | Timestamp of audit completion. | DateTime or null |
| `evaluatedAt` | Timestamp when Auto QA evaluation was completed. | DateTime or null |
| `totalResults` | Total number of conversation records matching the request. | integer |
| `totalPages` | Total number of pages based on page size. | integer |
| `hasMore` | Indicates whether additional pages exist. | boolean |
| `results` | A list of conversation objects. | array |
Contacts ingested before the minimum duration threshold feature is enabled return `null` for `duration_status`.