> ## Documentation Index
> Fetch the complete documentation index at: https://docs.teli.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Get SMS Extraction

> Retrieve extracted data from an SMS conversation

# Get SMS Extraction

Retrieve AI-extracted data from an SMS conversation thread.

<Note>
  Extraction happens automatically when the AI analyzes conversations. Configure extraction fields on your SMS agent to specify what data to extract.
</Note>

## Endpoint

```
GET /v1/sms/extractions/{thread_id}
```

## Authentication

<ParamField header="X-API-Key" type="string" required>
  Your API key
</ParamField>

## Path Parameters

<ParamField path="thread_id" type="string" required>
  The conversation thread ID. Format: `{phone_number}_{campaign_id}`

  Example: `+15551234567_camp_abc123`
</ParamField>

## Response

<ResponseField name="success" type="boolean">
  Whether the request was successful
</ResponseField>

<ResponseField name="extraction" type="object">
  The extraction data (null if no extraction found)

  <Expandable title="extraction properties">
    <ResponseField name="thread_id" type="string">
      Conversation thread identifier
    </ResponseField>

    <ResponseField name="phone_number" type="string">
      Contact's phone number in E.164 format
    </ResponseField>

    <ResponseField name="extracted_fields" type="object">
      Key-value pairs of extracted data. Keys match your configured extraction\_fields.

      Example:

      ```json theme={null}
      {
        "credit_score": "730",
        "loan_amount": "250000",
        "interested": "yes",
        "timeline": "3 months"
      }
      ```
    </ResponseField>

    <ResponseField name="lead_outcome" type="string">
      AI-determined lead classification:

      * `qualified` - Lead expressed interest and met criteria
      * `not_interested` - Lead declined
      * `dnc` - Added to Do Not Contact list
      * `transferred` - Lead was transferred to a live agent
      * `pending` - Still in conversation
    </ResponseField>

    <ResponseField name="objective_met" type="boolean">
      Whether the campaign objective was achieved
    </ResponseField>

    <ResponseField name="do_not_message" type="boolean">
      Whether the contact should not receive further messages
    </ResponseField>

    <ResponseField name="call_transferred" type="boolean">
      Whether the conversation was transferred to a live agent
    </ResponseField>

    <ResponseField name="call_scheduled" type="boolean">
      Whether a call was scheduled
    </ResponseField>

    <ResponseField name="call_scheduled_time" type="string">
      ISO 8601 timestamp of scheduled call (if applicable)
    </ResponseField>

    <ResponseField name="extracted_at" type="string">
      ISO 8601 timestamp when extraction occurred
    </ResponseField>

    <ResponseField name="campaign_id" type="string">
      Campaign identifier
    </ResponseField>
  </Expandable>
</ResponseField>

## Example Request

```bash theme={null}
curl -X GET "https://partner.teli.ai/api/proxy/v1/sms/extractions/%2B15551234567_camp_abc123" \
  -H "X-API-Key: your-api-key"
```

## Example Response

### Extraction Found

```json theme={null}
{
  "success": true,
  "extraction": {
    "thread_id": "+15551234567_camp_abc123",
    "phone_number": "+15551234567",
    "extracted_fields": {
      "credit_score": "730",
      "loan_amount": "250000",
      "interested": "yes",
      "timeline": "3 months"
    },
    "lead_outcome": "qualified",
    "objective_met": true,
    "do_not_message": false,
    "call_transferred": false,
    "call_scheduled": true,
    "call_scheduled_time": "2026-01-25T14:00:00Z",
    "extracted_at": "2026-01-23T19:30:00Z",
    "campaign_id": "camp_abc123"
  },
  "powered_by": "Teli"
}
```

### No Extraction Found

```json theme={null}
{
  "success": true,
  "extraction": null,
  "message": "No extraction found for this thread",
  "powered_by": "Teli"
}
```

## Configuring Extraction Fields

Extraction fields are configured on your SMS Agent. When creating or updating an SMS agent, specify the fields you want to extract:

```bash theme={null}
curl -X POST "https://partner.teli.ai/api/proxy/v1/agents" \
  -H "X-API-Key: your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_type": "sms",
    "agent_name": "Mortgage Lead Qualifier",
    "prompt": "You are a mortgage specialist...",
    "extraction_fields": [
      "credit_score",
      "loan_amount", 
      "property_value",
      "annual_income",
      "interested",
      "timeline"
    ],
    "organization_id": "org_xxx",
    "user_id": "user_xxx"
  }'
```

The AI will automatically extract these fields from the conversation and store them for retrieval.

## Best Practices

1. **Use descriptive field names**: `credit_score` is better than `cs`
2. **Keep fields focused**: Extract specific data points, not entire paragraphs
3. **Configure relevant fields**: Only extract what you need for your workflow
4. **Check lead\_outcome**: Use this to prioritize follow-ups

## Related Endpoints

* [Create SMS Agent](/partner-api/agents/create-sms) - Configure extraction fields
* [Update SMS Agent](/partner-api/agents/update-sms) - Modify extraction fields
* [List SMS Campaigns](/partner-api/campaigns/list-sms) - View campaigns