---
schema_version: "1"
id: 6cd5e574d634722b07d35487d964f405437d8f893da6cc4d2a3882cfc9e257e0
title: Configure a Document Schema for Licenses and Permits
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/ind/264-0-0/aps_agentic_application_intake_document_schema.md
canonical_url: https://help.salesforce.com/s/articleView?id=ind.aps_agentic_application_intake_document_schema.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: f58ac06cb8f683a63db94e1db039375f0fc1620f2829f869eff1ff807065f726
description: Define which fields Unstructured Document Processing extracts from documents that license and permit applicants upload.
products:
  - Public Sector
release: "264"
---
# Configure a Document Schema for Licenses and Permits

Define which fields Unstructured Document Processing extracts from documents that license and permit applicants upload.

### Required Editions

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small edition"><colgroup><col></colgroup><tbody><tr class=""><td class="slds-cell-wrap" style="vertical-align:top;"><a href="https://help.salesforce.com/s/articleView?id=ind.psc_supported_editions.htm&amp;release=264.0.0&amp;type=5" title="Learn about the editions, user interfaces, and add-ons that support Public Sector.">View supported product editions</a>.</td></tr></tbody></table>

Complete the steps in [Set Up Unstructured Document Processing](https://help.salesforce.com/s/articleView?id=ind.psc_recruitment_enable_unstructured_document_processing.htm&release=264.0.0&type=5 "Enable Unstructured Document Processing, then configure the permissions that users need to upload documents and extract data.") first.

Your agency defines its own document schema. The fields that you extract depend on the documents that your applicants submit, so the product doesn't predefine them. Extracted values land on the Application Form object. A schema supports a maximum of 50 fields per root object or table, and 100 fields in total.

Give each field the same API name as the matching field in your intake flow so that extracted values reach the right fields. Field Type doesn't include a date option, so use String for dates. Prompt Instructions are optional and guide the extraction.

1. From the App Launcher, find and open **Data Cloud**.
2. Locate the **More** dropdown, and select **Process Content**, and then select **Document AI**.
3. Click **New**.
4. Select **Without a Source Object**, select **Create Manually**, and then click **Next**.
5. On the Fields tab, click **Add Field** for each field that you want to extract.
    
    Enter a name and an API name, select a field type, and optionally enter prompt instructions.
6. On the Tables tab, click **Add Table** for each group of repeating information, and then add the columns for each table.
7. Click **Save**, enter a name for the document schema configuration, and then click **Save Draft**.
    
    Give the configuration the same name as the `idpConfigApiName` value in the upload component.