AI actions - Categorize document

Important: 
  • The AI actions feature is available only when the feature is selected in the AI features for the tenant.

  • AI Actions have input limits to ensure safe and predictable results. Each action that analyzes or extracts information from text can process up to 100,000 characters and up to 1,000 repetitive pattern occurrences. Any input that exceeds these limits will not be processed. Some actions that only convert documents or images to text without analyzing the content, do not enforce these limits.

Use the Categorize document action A tool for building the processes, logic, and direction within workflows. Actions are the steps the workflow performs to complete a process. to analyze a document's text, structure, and metadata then assign it to a predefined category. The action follows the category list and descriptions provided and returns the best-matched category, along with a brief reasoning in a variable. Use this output to route documents, trigger follow-up actions, or support automated document processing.

For example, in a healthcare workflow, patients may upload various documents such as lab results, insurance forms, or prescriptions. Use the Categorize document action to identify the type of each uploaded file and categorize it into options such as Lab results, Insurance form, or Prescription. The action returns the matched category and a short explanation, which you can use to send the document to the appropriate team or department.

Jump to:

Configure the Categorize document action

  1. Add the action to the workflow and open the action configuration panel. For more information, see Add an action to the workflow.

  2. Select a variable that contains the document in the File field.

  3. Click Add new category.

  4. Type or insert variables that contain name and description in the Category name and Description field.

    Note: To delete a category, click on the next to the category you want to delete.

  5. Select or create a variable in the Category field to store the result.

AI actions - Categorize document action fields and settings

Section Field Description

Variable
(Unlabeled) File

A variable that contains the document to categorize text from.

  • File limit includes 1 file per action.
  • Maximum supported file size is 25 MB.
  • Supported file types include .pdf, .jpg, .jpeg, .png, .bmp, .tiff, .heif, .docx, .xlsx, .pptx , .html

File
Categories Add new category

Creates a new category entry for the action.

 NA
  Category name Name of the category. Text
  Description Description to identify the category. Text
Output Category

Stores the categorized text as an object with the following variables:

  • Document category: Text variable to store the matched category name.

  • Description: Text variable to store the description of the matched category.

  • Reasoning: Text variable that stores the explanation for why the category was matched.

The output language matches the language of the input document.

Object