Set up a use case for Now Assist in Document Intelligence

Create a use case record to define a document you want to process with Now Assist in Document Intelligence.

Before you begin

• If the Now Assist in Document Intelligence skill has been deactivated, activate the skill. For more information, see Activate a Now Assist in Document Intelligence skill.
• Role required: Admin, DocIntel Admin, DocIntel Manager

About this task

In a use case, you define the information you want Now Assist to get from a document by specifying the type of document to process, the fields to detect, and the location where document processing results are stored.

Once you have defined a use case, users can begin processing documents for it in the related workflows.

For more information on use cases, see Use cases in Now Assist in Document Intelligence.

Procedure

1. Navigate to All > Now Assist Admin > Skills.
2. In the workflow list, select Platform.
3. In the Platform skills list, find the applicable document intelligence skill and select Edit in the options menu ( ).
4. Select New use case.

   The guided use case setup opens.

5. Define the use case.
   1. Enter a name for the use case.
   2. Select a target table to store the document processing results for this use case.
   3. Select the large language model (LLM) that will make predictions for the documents processed with this use case.
   4. Select Save and continue.
6. Define fields or questions.
   1. Select Add a field.

      If you have already defined one or more fields or questions and you want to add another, select New field.

   2. Select the type of information you want to get from the document.

      You can choose one of the following:

      Field

      For document extraction uses cases, fields are used to extract a single piece of information in the document. For example, a document number or a customer name.

      Table

      For document extraction uses cases, tables are used to extract lists or tables of information. A table can have multiple columns. The number of list items or table rows doesn’t have to be known in advance.

      Question

      For document Q&A uses cases, define the question you want to ask about the document.

      A field form displays based on the information type you selected.
   3. On the form, fill in the fields.
      The type of form depends on the type of field.

      • Question form for document Q&A setup
      • Field form for document extraction setup
      • Table form for document extraction setup

      Figure 1. Field form for document extraction

      

   4. Select Save.
      The system adds the new fields or questions to the Fields list associated with the use case.
   5. Select Save and Continue.
7. Test the use case performance with a sample document.
   Select Test a new document.
   1. Select a document.

      Option	Description
      Upload from record	Select Upload from record. Enter search criteria in the search field. Select a record from the list. This option is available when a target table is selected for the use case.
      Upload from this device	Select Upload from this device. Select Add file. Select a file and select Open. Select Upload.

   2. Select Continue.
      The Document Intelligence workspace appears in a frame on the Test output screen.
   3. Review the performance of the skill for the test document.
   4. Select Save and continue.
8. Add integrations.

   Integrate the document intelligence use case with a workflow.

   This option is available when a target table is selected for the use case.

   For more information on Document Intelligence integrations, see Integrate with a custom application or workflow.

   1. Select Add integration.

      If you have already defined one or more integrations and you want to add another, select New integration.

   2. Enter a name for the integration.
   3. Select the type of integration you want to use.

      The Process task type creates an integration point to automatically create and process document tasks based on specific triggers happening in the target table.

      The Extract values type creates an integration point to automatically propagate the extracted values to the target table when extraction has been completed in Now Assist in Document Intelligence.

   4. Use the conditions to select certain fields as specific triggers for the integration.

      Conditions are available if you selected Process task in the previous step. For more information on conditions, see OR conditions.

   5. Optional: Select the Create Flow option to create a flow for this integration in Workflow Studio.
      Tip:

      This option should be selected, unless you are planning to write your own custom script to set up the integration. Be sure the integration is activated on Workflow Studio. For more information, see Building flows.
   6. Select Save.
   7. Select Save and continue.
9. Review and activate.
   1. Review the configuration selections you’ve made for the use case.
   2. Optional: Select Back to return to a previous step and make a change
   3. Select Complete setup.

Related tasks

• Activate a Now Assist in Document Intelligence skill
• Turn on Full automation mode for a document extraction use case
• Change the large language model (LLM) for a use case
• Edit a use case in Now Assist in Document Intelligence
• Make a copy of a use case in Now Assist in Document Intelligence
• Deactivate a use case in Now Assist in Document Intelligence
• Delete a use case in Now Assist in Document Intelligence