> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.resemble.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.resemble.ai/_mcp/server.

# Intelligence Queries

After a transcript completes, ask follow-up questions to extract summaries, action items, sentiment, and more.

## Submit a Question

`POST https://app.resemble.ai/api/v2/speech-to-text/{uuid}/ask`

```bash
curl --request POST 'https://app.resemble.ai/api/v2/speech-to-text/550e8400-e29b-41d4-a716-446655440000/ask' \
  -H 'Authorization: Bearer YOUR_API_TOKEN' \
  -H 'Content-Type: application/json' \
  --data '{"query": "What action items were mentioned?"}'
```

Response:

```json
{
  "success": true,
  "item": {
    "uuid": "650e8400-e29b-41d4-a716-446655440001",
    "transcript_uuid": "550e8400-e29b-41d4-a716-446655440000",
    "query": "What action items were mentioned?",
    "status": "pending",
    "created_at": "2024-01-15T10:35:00Z"
  }
}
```

## Check Question Status

`GET https://app.resemble.ai/api/v2/speech-to-text/{uuid}/questions/{question_uuid}`

Response:

```json
{
  "success": true,
  "item": {
    "uuid": "650e8400-e29b-41d4-a716-446655440001",
    "transcript_uuid": "550e8400-e29b-41d4-a716-446655440000",
    "query": "What action items were mentioned?",
    "answer": "The following action items were identified...",
    "status": "completed",
    "created_at": "2024-01-15T10:35:00Z",
    "updated_at": "2024-01-15T10:35:30Z"
  }
}
```

## List Questions

`GET https://app.resemble.ai/api/v2/speech-to-text/{uuid}/questions`

Supports `page` and `per_page` query parameters (default `25`, max `50`).

```json
{
  "success": true,
  "items": [
    {
      "uuid": "650e8400-e29b-41d4-a716-446655440001",
      "query": "What action items were mentioned?",
      "answer": "The following action items were identified...",
      "status": "completed",
      "created_at": "2024-01-15T10:35:00Z"
    }
  ],
  "meta": {
    "page": 1,
    "per_page": 25,
    "total_pages": 1,
    "total_items": 3
  }
}
```

## Common Questions

* **Action items** – "What action items were mentioned and who owns them?"
* **Decisions** – "What decisions were made?"
* **Summaries** – "Provide a 3-sentence executive summary."
* **Sentiment** – "What is the overall sentiment of this conversation?"
* **Entities** – "List all people and companies referenced."
* **Data extraction** – "Extract all statistics and numerical data mentioned."

## Workflow

1. Ensure the transcript status is `completed`.
2. Submit a question using the `ask` endpoint.
3. Store the returned question UUID.
4. Poll the status endpoint until `completed`.
5. Retrieve the answer (and cache it if you will reuse it).

Use exponential backoff when polling to avoid hitting rate limits.

## Error Handling

Failures return standard error objects, for example:

```json
{
  "success": false,
  "error": "Transcript must be completed before asking questions"
}
```

Other common errors include missing `query` values, invalid transcript UUIDs, or authorization failures.

**Zero-retention transcripts:** once a transcript created with `zero_retention_mode` has been delivered and purged, Intelligence questions are no longer available:

```json
{
  "success": false,
  "error": "Questions are not available for zero-retention transcripts; content has been purged."
}
```