Review what's new and changed, and the fixes and limitations in Document Automation for the v.37 release.

What's new

Audit log support for Test mode

You can track changes made to learning instances that have the test mode option enabled for audit purposes.

Audit entries Description
Edit learning instance This action is logged when the user performs any of the following actions:
  • Enables test mode
  • Disables test mode
  • Edits learning instance fields when the test mode is enabled
Import learning instance This action is logged when the test mode is enabled and you import an existing learning instance.
Restore learning instance This action is logged when you restore a version of a learning instance

Audit events list
Test mode status

You can now quickly view from the Learning Instances page if the test mode for a learning instance is enabled or disabled without opening the learning instance. Also, when you open a learning instance, a test mode icon is displayed before the learning instance name to indicate that the test mode is enabled for the learning instance.

Test learning instances

What's changed

Test mode enhancements

The following enhancements are included for test mode:
Simplified process to use prompt tags
You can now select prompt tags, instead of manually adding them, to insert them in your prompts. This improved process provides the following benefits:
  • Streamlines the process of allowing to insert only the prompt tags that are supported in prompts.
  • Avoids any error that might occur because of manually inserting incorrect prompt tags in prompts.

Also, the AdvancedExtraction prompt tag is now renamed to GenAIVisionPlus.

Using prompt tags in generative AI prompts
Support for adding more custom aliases (Service Cloud Case ID: 02182397)

You can now add more custom aliases for a field to define all the different aliases that defines the field for improving data extraction.

Considerations when creating learning instance in Document Automation

Fixes

You can now view the rule values in the field and document rules for check box fields in Standard Forms learning instances after updating to the v.37 release.

Previously, the field and document rules were not displayed in such a scenario.

Data extraction will no longer fail for a learning instance that has its extraction bot checked out or when cloned copies of the learning instance are in the private repository.

Previously, data extraction failed in such a scenario.

Service Cloud Case ID: 02179111, 02180406, 02181013, 02188560
You will now be able to edit document rules in a learning instance when the number of document rules used in the learning instance is more (for example, 20 or more rules), and a field rule contains a check box field.

Service Cloud Case ID: 02173183, 02180260, 02184419
In the Extract data action of the Document Automation package, the text displayed in the Additional settings options now supports the default languages supported in the Control Room.
When you point to the cross (x) button on the Learning Instances or Select a model page to clear the search options, you will now see the Remove text to clear the options.

Previously, incorrect text was displayed in such a scenario.
When you update settings on the Administrator > Settings > Document Automation pane, the changes are now updated correctly.

Previously, the changes were being saved even after users canceled their request.

Service Cloud Case ID: 02197300
You will no longer be able to view the delete button for the a single action added to a field or document rule.

Previously, you were able to view the delete button in such a scenario.
The Validate documents count option displays the total number of documents that are in the validation queue and require validation.

Previously, if the test mode option was enabled for a learning instance, the validator count increased when documents were processed to test different versions of the learning instance.
You will now be able to view PDFs uploaded to your Standard Forms models.

Previously, the PDFs were not displayed in such a scenario.

Service Cloud Case ID: 02189025
When you are using a language other than English for the Control Room, the Document Automation settings pane now displays the text as per the language selected.

Previously, the language was displayed in English in such a scenario.

Limitations

When you try to check in a process without having the required permissions, the audit log entry for this event will include Source as Control Room instead of Document Workspace and Item name as Unknown instead of <learning-instance-name>.
If you are using the set value action in the field or documentation rules in your existing learning instances, the rules will be removed after you update the Control Room.

Workaround: Apply the rules again after your update your Control Room.
Incorrect audit logs are logged when users without permissions to checkin process try to checkin the process.
Limitations from previous releases
When you restore a learning instance to any previous version from version history and reprocess a document, the document upload count is increased.
When you process documents with file names greater than or equal to 75 characters in test mode, you might not see improvements in the reprocessing time for such documents.
If you have disabled the OCR provider in the administrator settings and if you are using a language other than English for your Control Room, you will see an error to enable the OCR provider settings in English in the following scenarios:
  • When you create a learning instance that is using an OCR provider
  • When you change the OCR provider for an existing learning instance
When you use the Document Classifier actions (Classify, Classify documents, and Train Classifier) and Extract Data action in the Document Extraction package together in a bot, the bot will fail to execute.

Workaround: Ensure that you create separate bots when using any of the actions from the Document Classifier package and the Extract Data action of the Document Extraction package. If you need to execute these bots in a sequence, include these bots in an Automation Co-Pilot process.
If you copy a learning instance that is using a third-party parser configured in Document Automation and process documents using the copied learning instance, data extraction will fail.
When a user processes a document on a custom process learning instance, the validate document count is not updated post extraction. Also, if the user submits the document, the validate document count is updated with a negative value.
A user with the Automation Co-Pilot administrator permissions is unable to view the Document Automation tasks that are assigned or requested and are in pending or complete status.
When you are using the IQ Bot Pre-processor package actions and if the Output folder path contains Japanese characters, you will see an error when processing documents.

Workaround: Create an output folder in a folder path that does not contain any Japanese characters and provide the path in the output folder path field.

IQ Bot

You will no longer see a 100% spike in CPU when you install IQ Bot and log in to your Control Room.

Previously, you were seeing a 100% spike in CPU in such a scenario.

Completed deprecations

Standard Forms support in IQ Bot is deprecated

You will not be able to use Standard Formsin IQ Bot as of June 2025. We recommend that such customers evaluate the transition plan for moving from IQ Bot to Document Automation. See IQ Bot to Document Automation: Transition plan.

Completed feature deprecations

Updates to the interface

Document Automation
You can now select prompt tags instead of adding them manually to your prompts:

Interface showing prompt tag selection for generative AI model queries

Simplified process to use prompt tags