Use the Categorize AI task in an automation

This feature is available to AppSheet Enterprise Plus accounts only. See What features are supported with each subscription?

Categorize information based on a predefined set of categories using AI by adding the  Categorize AI task in an automation.

Examples of categorizing information using AI:
  • Analyze the description in employee expense submissions and automatically categorize them by type (Travel, Meals, Software, or Training).
  • Read incoming facility maintenance requests and categorize them by urgency (High, Medium, or Low) or equipment type (HVAC, Plumbing, or Electrical).
  • Classify customer survey responses or feedback form submissions into types like Bug Report, Feature Request, Positive Feedback, or Billing Inquiry.

Categorize information using AI as described in the following sections.

See also:

Get started

To get started using the Categorize AI task, step through a quick start or explore an app template .

Add and configure the Categorize AI task

To categorize information based on a set of predefined categories, add and configure the Categorize AI task by performing the following steps.

  1. Add the Categorize AI  task to a bot, as described in Add a task to a bot .
  2. Configure the Categorize AI task by using the settings described in the following table. 
  3. Save the app.

Setting

Description

Task type

Select AI task.

Table

Table defined in the event and used by the task.  See Tables: The Essentials for more information about tables.

AI task 

Type of AI task . Select Categorize.

Input columns

Add one or more columns to use as input to the AI task, up to a maximum of 10. Click Addand select a column from the drop-down.

Basic column data types and virtual columns are supported. 

The following data types are not supported:

Note: List  columns are not supported at this time.

Output

Select one of the following:

  • Save to tableto save the extracted information to the table in your data source.
  • Return valueto guide AI responses without storing the results in your data source. Use the returned values in later steps, as follows:  [ AI-step ].[ column ]

For best practices when saving content, see  Manage updates to row data by multiple bots .

Then, select the column that defines the allowed category values. Must be an Enum or Ref column. 

Note: If you select a  Ref column, it only works with existing values and there must be at least one row. AppSheet won't create a new entry in the referenced table. 

For example, you might have a column called How expensive?  that is an Enum  column with the following values:  Inexpensive , Moderately expensive , Expensive,Other

Additional instructions

Recommended. Do the following:
  • Describe in more detail the requirements for each category value.
  • Indicate what values to set if results are not known.
  • Ensure that any recommended values match the type and format of the column, for best results. 

Supports up to 1000 characters. 

For example:

Inexpensive: Less than 10 dollars
Moderately expensive: Between 10 and 50 dollars
Expensive: Over 50 dollars
Other: Not sure of value

Note: Specifying a value that is not defined in the Enum  or Ref column selected for the Output setting may cause unexpected behavior unless you  allow other values  when configuring the Enum column properties.

Was this helpful?

How can we improve it?

Need more help?

Try these next steps:

Search
Clear search
Close search
Google apps
Main menu
3193932189569093298
true
Search Help Center
true
true
true
false
false
false
false
Create a Mobile Website
View Site in Mobile | Classic
Share by: