---
sourceDocument: Xanadu Enable AI
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/xanadu/intelligent-experiences

 Release :

    - xanadu

ft:locale :

    - en-US

ft:publication_title :

    - Xanadu Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Train a use case

# Train a use case {#ariaid-title1}

* Release version: Xanadu
* 
* Updated August 1, 2024
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read

Train the document classification use case with user input from completed document tasks to improve Document Intelligence recommendations over time.

## Before you begin

* There must be at least one reviewed document task associated with the use case to train it. Across all reviewed tasks, there must be at least two attachments for each type you defined in your use case.

  Begin by [creating a document task](https://servicenow-prod.fluidtopics.net/QYRMV0IcD7HASr1CzSm3fg "Create a document task and upload single or multi-page documents that are in JPEG, PNG, or PDF formats to start extracting text or classifying documents.") and [completing it](https://servicenow-prod.fluidtopics.net/qXtgUtiN41nsOpDrSnbtAg "After the document task processing is finished, complete the task by providing input or review to train the AI.") using the Document Intelligence workspace.  
  Note:  
  You won't be able to process the task until the use case is trained, but you can complete it by completing all the fields and submitting it.
* Role required: sn_docintel.manager
{#train-a-use-case__ul_gtf_kbc_rxb}

## About this task

Document classification use cases don't begin with pre-trained AI models, so it's important to train the models with user input from completed document tasks.  
Note:  
To reduce server load and minimize performance issues, the default limit for training a use case is once every 30 days.

## Procedure

1. Navigate to AllDocument IntelligenceDocument ClassificationUse Cases.
2. Select a use case in the list.
3. Select Train Use Case.  
   DocIntel uses the extracted values from the document tasks in a Done status to train the model.

## Result

The train use case job begins. This job may take several hours to complete.

*[\>]: and then