> This page is for version v8.3.0 (default).
> For other versions, use one of these documentation indexes:
> - v8.3.0 (default): https://docs.workflows.com/v-8-3-0/llms.txt

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

# create_snapshot

CREATE

# create_snapshot

Starts

AI training

to analyze

transcript data

and learn communication patterns, decision-making style, tone, vocabulary, and personality traits. This is an

asynchronous operation

that typically takes 5-15 minutes.

> **Info**
>
> The `create_snapshot` tool processes uploaded transcript data into a trained AI model. The result is a snapshot—a point-in-time representation of how a person thinks and communicates.

## Parameters

### mindId

<table>
  <tr>
    <td>
      **Type**
    </td>

    <td>
      string
    </td>
  </tr>

  <tr>
    <td>
      **Required**
    </td>

    <td>
      Yes
    </td>
  </tr>

  <tr>
    <td>
      **Description**
    </td>

    <td>
      The mind ID from the 

      `create_mind`

       response
    </td>
  </tr>
</table>

### digitalTwinId

<table>
  <tr>
    <td>
      **Type**
    </td>

    <td>
      string
    </td>
  </tr>

  <tr>
    <td>
      **Required**
    </td>

    <td>
      Yes
    </td>
  </tr>

  <tr>
    <td>
      **Description**
    </td>

    <td>
      The digital twin ID from the 

      `create_mind`

       response
    </td>
  </tr>
</table>

### artifactId

<table>
  <tr>
    <td>
      **Type**
    </td>

    <td>
      string
    </td>
  </tr>

  <tr>
    <td>
      **Required**
    </td>

    <td>
      Yes
    </td>
  </tr>

  <tr>
    <td>
      **Description**
    </td>

    <td>
      The artifact ID from the 

      `get_signed_upload_url`

       response
    </td>
  </tr>
</table>

## Request

```json
{
  "mindId": "abc-123-def-456",
  "digitalTwinId": "xyz-789-uvw-012",
  "artifactId": "artifact-456-def-789"
}
```

## Response

```json
{
  "message": "Memory bank snapshot processing initiated",
  "mindAssessmentId": "123e4567-e89b-12d3-a456-426614174003",
  "artifactId": "123e4567-e89b-12d3-a456-426614174004"
}
```

### Response Properties

| Property           | Type   | Description                                                                   |
| ------------------ | ------ | ----------------------------------------------------------------------------- |
| `message`          | string | Status message confirming processing has started                              |
| `mindAssessmentId` | string | **Required for status checks** - Snapshot identifier (also called snapshotId) |
| `artifactId`       | string | Associated artifact identifier (matches input parameter)                      |

> **Success**
>
> Your AI model is now training in the background. Use `get_snapshot_status` to check when it's ready for simulations.

## Processing Time Estimates

| File Size | Conversations | Typical Time  |
| --------- | ------------- | ------------- |
| \< 1 MB   | 10-20         | 3-5 minutes   |
| 1-10 MB   | 30-100        | 5-15 minutes  |
| 10-50 MB  | 100-500       | 15-30 minutes |
| 50-100 MB | 500+          | 30-45 minutes |

> **Note**
>
> Factors affecting processing time include file size, number of unique speakers, conversation complexity, and current system load.

## What the AI Learns

During processing, Mind Reasoner's AI analyzes your transcript to extract:

#### Communication Style

* Vocabulary and phrasing
* Sentence structure
* Formality level
* Speech patterns

#### Emotional Patterns

* Tone and mood
* Empathy expression
* Confidence levels
* Reaction patterns

#### Decision-Making

* Problem-solving approach
* Question handling
* Prioritization style
* Reasoning patterns

## Error Responses

#### 404 Not Found

```json
{
  "error": "Not Found",
  "message": "Artifact with ID 'artifact-456' does not exist"
}
```

**Solution:** Verify the `artifactId` is correct and ensure the file upload completed successfully.

#### 400 Bad Request

```json
{
  "error": "Bad Request",
  "message": "Invalid file format or corrupted data"
}
```

**Solution:** Verify the file is a valid .vtt, .pdf, or .docx format and ensure the file contains actual conversation data. Try re-uploading if needed.

#### 409 Conflict

```json
{
  "error": "Conflict",
  "message": "A snapshot is already processing for this mind"
}
```

**Solution:** Wait for the current snapshot to complete. Check status with `get_snapshot_status`. You can only process one snapshot at a time per mind.

## Next Steps

#### Check Status

[get_snapshot_status](/mcp-tool-get-snapshot-status) - Poll to check when training is complete

> **Tip**
>
> Your AI assistant can continue other work while the snapshot processes. It will automatically check the status and notify you when training is complete.

## See Also

#### [upload_file_to_signed_url](/mcp-tool-upload-file)

Previous step: Upload your file

#### [get_snapshot_status](/mcp-tool-get-snapshot-status)

Next step: Check training status