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

# Send feedback to Chattermill

To add feedback to Chattermill from your own systems:

1. Call [List projects](/api-reference/projects/get-all-projects) to find the key of the project you need.
2. Call [List data sources](/api-reference/data-sources/get-project-data-sources) and [List data types](/api-reference/data-types/get-project-data-types) to get their keys. If the source or type you need doesn't exist, contact [support@chattermill.com](mailto:support@chattermill.com) and we'll create it.
3. Send each piece of feedback to [Create a response](/api-reference/responses/create-response).

```bash
curl https://api.chattermill.com/v1/YOUR_PROJECT/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "data_type": "review",
    "data_source": "trustpilot",
    "response": {
      "score": 9,
      "comment": "Delivery was quick and the driver was friendly.",
      "user_meta": {
        "country": { "type": "text", "name": "Country", "value": "GB" },
        "order_id": { "type": "text", "name": "Order ID", "value": "A-10293" }
      }
    }
  }'
```

Each key in `user_meta` becomes an attribute you can filter and segment by in Chattermill. Give each one a `type`, a display `name` and a `value`.

Chattermill analyses new responses shortly after you create them. Themes and sentiment appear on the response once processing finishes.