---
sourceDocument: Brazil Enable AI
sourceDocumentLink: https://www.servicenow.com/docs/r/intelligent-experiences

 Release :

    - brazil

ft:locale :

    - en-US

ft:publication_title :

    - Brazil Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Set up a use case

# Set up a use case {#ariaid-title1}

Release version: Brazil  
Updated March 12, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read  
Create a use case to define the information to extract from a document for processing.

## Before you begin

Several predefined use cases are available within their defined workflow areas. Check whether the available use cases meet your requirements before creating a new one. For more information, see [Content Understanding integrations](https://www.servicenow.com/docs/UFghQPiWii7u_PNGg1Ssxg "Content Understanding integrates with ServiceNow solutions to extract, analyze, and summarize information documents.").

Activate the Information Extraction skill. For more information, see [Activate the Extract Information from documents skill](https://www.servicenow.com/docs/BPpz1PW0mbSUZlCFvwukPg "Activate the Information Extraction skill, so AI agents can analyze and extract information from documents using generative AI.").

Role required: DocIntel Admin \[sn_docintel.admin\] or DocIntel Manager \[sn_docintel.manager\]

## About this task

In a use case, specify the document type to process, the fields and tables to detect, the questions to ask, and where to store the results.

After you define a use case, you can begin processing documents for it in the related workflows.

## Procedure

1. Navigate to AllAI Admin HubSkills.
2. In the workflow list, select Platform.
3. From the Platform skills list, search for Extract information from documents skill.
4. Select the options menu (![Options menu icon]()), and then select Edit.
5. Select New use case.
6. Define a use case.  

   <br />

   1. Enter a name for the use case.
   2. Select a target table to store the document processing results for the use case.
   3. Select the language of the files to process for the use case.  
      If the files contain multiple languages, select the primary language.

      For more information, see [Languages supported by Content Understanding](https://www.servicenow.com/docs/KcRjYyPN4dkVUVl6L1YOaA "Use this reference to identify which languages the Content Understanding application supports for text-based and image-based files, and which optical character recognition (OCR) model applies to each language group.").
   4. Select a large language model (LLM) that will make predictions for the documents processed with this use case.  
      For more information, see [Large language models used by Content Understanding](https://www.servicenow.com/docs/uJlb11QMZ0ws7a5yrxkGbg "The Content Understanding application uses large language models (LLMs) to support generative AI and agentic AI capabilities.").
   5. **Optional:** Turn on image mode to process images more efficiently.  
      Image mode sends pages to the LLM as images to use the visual capability of the multimodal LLM and any of the languages supported by it.  
      Note:  
      Selecting image mode reduces the page count limit to 10 pages per file.

      The image mode option is available when a multimodal LLM is selected.  
      Note:  
      Now LLM Service is a text-only model and doesn't support image mode.
   6. Select Save and continue.
   {#set-up-use-case__substeps_g3k_vg2_b2c}
7. Define information fields, questions, or tables.  

   <br />

   1. Select Add a field.
   2. Select the type of information to extract from the document.  
      You can choose one of the following:

      Field
      :   Fields are used to extract a single piece of information in the document. For example, a document number or a customer name.

      Question
      :   Define a question to ask about the document.

      Table
      : 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.  
      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:
      * [Field form fields](https://www.servicenow.com/docs/C2Le0UKJkB6Yoz_v~VHYBw "The field form defines the information to extract from a document, including the field name, type, and target table.")
      * [Question form fields](https://www.servicenow.com/docs/Y0TrJdDllIuncY_MvGo5hQ "The Question form contains fields that define a question and how its answer is extracted from a document in a use case.")
      * [Table form fields](https://www.servicenow.com/docs/reFI4PT3aReVHzfeXV8qHw "The Table form contains fields for defining a table and its columns for document extraction in a use case.")
      {#set-up-use-case__ul_xzx_yh2_b2c}
   4. Select Save.  
      The field, question, or table is added to the Information list for the use case.
   5. Select Save and Continue.
   {#set-up-use-case__substeps_fvf_1h2_b2c}
{#set-up-use-case__steps_hzl_51b_ckc}

## What to do next

1. [Test a use case](https://www.servicenow.com/docs/b9nbweTPDDs7m0FCoFsJmw "Test a use case with a sample document to verify how well it extracts and processes information. Upload a document from a record or your device, then review the test outputs before saving your results.")
2. [Add integration](https://www.servicenow.com/docs/GPXvW8DbhiZ9e~I5ckLtUA "Connect a use case to a workflow by adding an integration. Integrations automate document task creation or value extraction based on triggers in the target table.")
3. [Review and activate](https://www.servicenow.com/docs/9WnGSyrBENR4FnRcqT1KpQ "Review your configuration selections before completing the setup for a use case. Return to any previous step to make changes before finalizing.")

*[\>]: and then