Overview

Extraction Configurations on Document Verification Templates define how Documents AI identifies and extracts textual information from documents. Extracted data can be automatically compared against Inquiry fields when a Document Verification is run within an Inquiry. For example, if the name of an individual is known and stored on an Inquiry field, then you can configure a Document Verification Template's extraction configurations to compare extracted name(s) from a Document against those Inquiry fields while a user is going through an Inquiry.

These configurations enable you to standardize extraction logic, apply automated comparison checks, and enrich verification results with structured data for further analysis across Persona products like Workflows, Cases, and API responses.

Configure Extraction Configurations

1. Navigate to the Dashboard, and click on Inquiries > Templates (or Verifications > Templates).
2. Find and select an Inquiry template with Document AI, or Create a new template.
3. In the top right, click Configure.

4. In the left navigation, click Document AI.

5. Scroll down to Extractions, or click Extractions in the left navigation.

6. To add a new extraction, click the Add extraction button.

7. In the right toolbar, under Add extraction:

   

   1. Label (required): A descriptive label or name for the extraction that can provide context to the Document AI instructions.
   2. Key (required): Auto-generated from the label. Used in API responses and across Persona products.
   3. Required extraction: When selected, the verification will fail if this extraction cannot be found in the document.

8. Under Extraction method, choose an Extractor type:

   1. Inquiry Comparison: Use this method to extract data from a document and compares it against Inquiry field values. See the Configure Inquiry comparison section below for details on how to set up comparison fields.
   2. AI: Use this method to extract text directly from the document using Documents AI.
      1. Extraction preference:
         1. Best Match: Returns the single extraction that meets the specified criteria, based on the highest confidence score among all extracted results.
         2. All Matches: Returns all unique extractions that meet the specified criteria, providing a wider range of potential results.
      2. Additional Instructions (Optional): Provide context or formatting guidance to refine Document AI extraction results.

9. Under Advanced, choose if you want to “Save analysis output to a Document Field.”

10. Click Add button to save the new field, or Cancel to discard it.

11. To remove a document click the … button then click Remove.

12. Click Save on the top right.

Configure Inquiry comparison

If you selected Inquiry Comparison as your extractor type, you will need to configure how extracted extract data will be compared against Inquiry field values.

1. Inquiry field for comparison: Choose the Inquiry field you want the extracted data to be compared against.
   1. Composite Inquiry Fields: Use these to compare extracted data to specific Inquiry fields that may be a hash data type or have multiple components. This is also useful if you'd like to have custom mappings of what fields to compare. Examples:
      1. Address: Map Document extracted data to the desired address fields on the associated Inquiry template (such as Street 1, Street 2, City, Subdivision, Postal Code) that you'd like to holistically compare document extracted values to.
      2. Name: Map Document extracted data to the desired fields on the associated Inquiry template (such as First Name, Last Name) that you'd like to holistically compare document extracted values to..
   2. Single Inquiry Fields: Use these to compare extracted data to one specific Inquiry field. This is useful is useful if you'd like to have strict 1-to-1 comparisons or for documents that may have less complex data. Examples:
      1. Name First: Compare the extracted first name from the document to the Inquiry’s first name field.
      2. Name Middle: Compare the extracted middle name to the Inquiry’s middle name field, when applicable.
      3. Name Last: Compare the extracted last name to the Inquiry’s last name field.
2. Match requirement: Define how closely the extracted data must match the Inquiry field value.
   1. Loose: Uses AI-based text matching to account for common formatting or spelling variations. (e.g., “St” vs “Street”).
   2. Strict: Requires higher precision in matching specific field components.
3. Address/Name extraction details (if applicable):

When you select a Composite Inquiry Field, an additional section will appear where you can specify which components of the field should be extracted and compared. 1. Address extraction details: Map extracted values to the address schema that include Street 1, Street 2, City, Subdivision, Postal Code. 2. Name extraction details: Map extracted values to the name schema that include First Name, Last Name.

Save Extraction output to a Document Field

Under the Advanced section, you can optionally store the AI-generated extraction as a Document Field. This is recommended.

Use an existing Document Field

1. Click the check box to “Save analysis output to a Document Field.”
2. By default Existing field is selected.
3. Under Document fields the click the selection box to choose an existing document field. The field must be compatible with the prompt template and response type for the extraction. For a String response type, you will only be able to select document fields that are strings. Incompatible fields are disabled.
4. Click Add button to save the new extraction, or Cancel to discard it.

Create a new Document Field

1. Click the check box to “Save analysis output to a Document Field.”
2. Select New Field, fill out the following fields:
   1. New document field label: A name for this document that provides context to the AI instructions.
   2. Document field key: Auto-generated from the label. Used in API responses and across Persona products.
   3. Type: Choose String or Array. Extractions can be saved to String or Array of String document fields. Incompatible fields are disabled.
3. Click Add & Create New Field button to save the new field, or Cancel to discard it.

Why Extraction Configurations are important

Extraction Configurations enable you to automate how Documents AI identifies and interprets document data. By configuring extractions, you can ensure that key details, like names, dates, and addresses, are consistently captured and later validated against trusted sources using the rest of the Persona platform or the Inquiry field comparison sub-configuration.

They’re especially useful when you need to:

• Automate comparisons between submitted documents and Inquiry fields.
• Capture and standardize text values for use across Workflows, Cases, and APIs.
• Enrich your Verification data with structured, machine-readable fields

Access by plan

We're here to chat through your specific needs. Feel free to reach out to your Customer Success Manager or contact the Persona support team.