Extract named datapoints from a company site by domain

Define the fields you want — name, description, type and an example each — and get them extracted from the company's own website, with the URLs used Request one bounded result or page using the documented fields. Pagination is explicit: follow-up pages require another run. The catalog price is the maximum per request; the upfront quote reflects the selected limits. Completed requests cost that quote, including valid empty pages and no-match answers. Supplier waivers do not change the customer price. Failed requests are uncharged. Results contain reviewed business data and available pagination. The worked example shows selected fields from a recorded response, with at most the first item of each list.

Inspect returns this reviewed example, its estimated cost and the current input schema. Run calculates the estimate for your actual input.

{
  "tool_id": "brand-dev.brand-ai-query",
  "input": {
    "domain": "stripe.com",
    "data_to_extract": [
      {
        "datapoint_name": "pricing_model",
        "datapoint_type": "text",
        "datapoint_example": "per-transaction percentage fee",
        "datapoint_description": "How the company charges customers"
      }
    ]
  }
}

{
  "data": {
    "domain": "stripe.com",
    "status": "ok",
    "data_extracted": [
      {
        "datapoint_name": "pricing_model",
        "datapoint_value": "Integrated per-transaction pricing with no hidden fees"
      }
    ]
  }
}

• invalid_input: The lookup fields or limits are invalid.example: {"domain":"stripe.com","data_to_extract":[{"datapoint_name":"pricing_model","datapoint_description":"How the company charges customers","datapoint_example":"per-transaction percentage fee","datapoint_type":"text"}]}
• upstream_error: The provider could not complete a verified result; the wallet was not charged.Check the documented fields and contact Scrollport support with the run ID if needed.