› Create a Quick Capture solution › Field extraction › Copilot Auto Extract fields › Extract fields using Copilot Auto Extract

Extract fields using Copilot Auto Extract

This method of extraction leverages a large language model alongside natural language instructions to extract data from a document. This means users can provide a simple text description to extract values from a document. There is no need for additional configuration, scripts, or training.

Recognition is only performed on the first 10 pages of a document.

Before extracting the fields using Copilot Auto Extract, you must Enable field extraction.

To configure a field to use Copilot Auto Extract:

  1. Optional. Click Hide suggested fields.

    This option is useful if there are multiple suggested fields that appear within the view.

    You can click Show suggested fields at any time to view the suggested fields.

  2. Click Add Copilot Auto Extract field.

    The Add Copilot Auto Extract field window is displayed.

  3. Enter a Name and Description.

    See the Description best practices for more information on writing useful descriptions.

  4. Optionally, click Advanced Settings to provide more information about the kind of information you require.
  5. Click Save.

    Your new Copilot Auto Extract field is added and if a value is found, it is highlighted on the document.

    If the information is inferred, the highlighted value may not match the content.

  6. Optionally, add additional fields.