Document Intelligence release notes

  • Release version: Xanadu
  • Updated September 30, 2025
  • 4 minutes to read
  • Summarize
    Summarized using AI
    This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.

    Summary of Document Intelligence release notes

    The ServiceNow® Document Intelligence application leverages artificial intelligence to efficiently categorize and extract data from various documents. The Xanadu release, updated as of September 30, 2025, introduces significant enhancements to automate document processing, improve data extraction accuracy, and expand language support.

    Show full answer Show less

    Key Features

    • Document and Visual Insights AI Agent: Available from Xanadu Patch 9, this AI agent autonomously analyzes documents and images to extract data, enabling full automation without manual review.
    • Integration with Now Assist and Virtual Agent: Users can query document content through Virtual Agent chat, and now extract contract information using generative AI capabilities.
    • Draw Tool Enhancements: Early availability of a tool to select specific document areas for precise single-field data extraction.
    • Data Normalization: Improved interpretation of ambiguous date and number fields, plus the ability to match extracted values against referenced table records for standardization.
    • Multilingual Document Processing: Added support for documents in Simplified Chinese and Japanese to broaden language capabilities.
    • Security Improvements: Patch 10 introduces access control lists (ACLs) for AI agents, allowing execution with defined user privileges to enhance security.
    • Monitoring and Dashboards: Enhanced dashboards allow administrators to monitor Document Intelligence performance at both overall and use case levels.
    • Accessibility Enhancements: The interface supports content reflow and zoom up to 400%, improving usability for users with low vision or varying device constraints.

    Key Outcomes

    • Increased Productivity: Automate routine document tasks and data extraction to accelerate workflows without requiring manual intervention.
    • Improved Accuracy and Consistency: Data normalization and reference matching reduce errors and standardize extracted information.
    • Expanded Use Cases: Enhanced AI agents and language support extend Document Intelligence capabilities across contract management, accounts payable, customer service, financial services, and automation center workflows.
    • Enhanced Security and Compliance: ACLs ensure AI agent activities comply with organizational security policies.
    • Better User Experience: Usability improvements in tools and accessibility features support diverse user needs and environments.

    Activation and Dependencies

    Document Intelligence must be installed from the ServiceNow Store. It depends on the Document Intelligence plugin, Predictive Intelligence plugin, and the Document Intelligence UI component. The Platform Document Intelligence Usage dashboard is deprecated; performance monitoring is now available in the Document Intelligence Admin experience.

    The ServiceNow® Document Intelligence application is an artificial intelligence (AI) solution that quickly and accurately categorizes and extracts information from documents. Document Intelligence was enhanced and updated in the Xanadu release.

    Document Intelligence highlights for the Xanadu release

    Xanadu Patch 9
    • Boost productivity by using the document and visual insights AI agent in Now Assist to autonomously analyze and extract data from documents and images.
    • Streamline document data extraction by automating document tasks.
    • Use Virtual Agent to ask questions about the document content.
    Xanadu Patch 3
    • Extract information from contract documents by using Now Assist in Document Intelligence.
    Early Availability
    • Extract the data from single fields by using the Draw tool to select a document area and extract the information.
    • Standardize the extracted data by determining how to interpret ambiguous field values and by matching extracted values with data in a referenced table.
    • Process documents that are written in Simplified Chinese or Japanese.
    • Monitor your Document Intelligence implementation with improved dashboard charts.

    See Document Intelligence for more information.

    Important:
    Document Intelligence is available in the ServiceNow Store. For details, see the "Activation information" section of these release notes.

    New in the Xanadu release

    Xanadu Patch 10
    Improved security for the document and visual insights AI agent
    Enable access control lists (ACLs) to improve the security for the document and visual insights AI agent. ACLs provide you with the capability to run AI agents and agentic workflow executions either as a dynamic user or an AI user.

    The document and visual insights AI agent and its skills are classified as a worker or helper agent. A worker can act as an AI user with different privileges than the human user. A helper only has the privileges of a human user.

    Xanadu Patch 9
    Document and visual insights AI agent
    Use an AI agent to help process tasks that analyze and extract data from documents and images.
    Full automation for document data extraction
    Automatically extract document data and process the document task without agent review.
    Document chat in Virtual Agent
    Integrate Now Assist for Virtual Agent with Now Assist in Document Intelligence to enable chat responses based on document content.
    Attachment summarization in ITSM
    View the summaries of attachments with the record summary in ITSM.
    Xanadu Patch 3
    Now Assist in Document Intelligence
    Use Now Assist in Document Intelligence to extract information from contract documents with generative AI.
    Early availability
    Draw tool enhancements
    Extract the data from single fields by using the draw tool to select a document area and extract the information.
    Data normalization
    Standardize the data extracted from documents with the following improvements:
    • Determine a default interpretation of the ambiguous values for the date and number fields.
    • Create a Reference field type to match the extracted field values with the fields in a referenced table record.
    Dashboards in the Admin experience
    Monitor the overall performance of Document Intelligence in the Document Intelligence monitoring dashboard. You can monitor the performance at the use case level in the use case performance dashboard.
    Document classification integration workflow
    Integrate document classification use cases with a custom application or workflow.

    UI changes

    Usability enhancements to Draw tool features
    Various Draw tool features are updated to create an effective user experience.

    Removed in this release

    Starting in the Xanadu release, the Platform Document Intelligence Usage dashboard is no longer supported or available through the Document Intelligence application. Performance metrics are available in the Document Intelligence Admin experience. For more information, see Document Intelligence monitoring dashboard.

    Activation information

    Install Document Intelligence by requesting it from the ServiceNow Store. Visit the ServiceNow Store website to view all the available apps and for information about submitting requests to the store. For cumulative release notes information for all released apps, see the ServiceNow Store version history release notes. The Document Intelligence application (sn_docintel) depends on the Document Intelligence plugin (com.glide.platform_ml_di), the Predictive Intelligence plugin (com.glide.platform_ml), and the Document Intelligence UIB component (com.sn_docintel_iframe). For more details, see Install Document Intelligence.

    Accessibility information

    Support for reflow
    The sn-docintel-iframe component was updated to support reflow, which enables pages and content to be zoomed up to 400% through your browser settings without loss of content or functionality. Additionally, content can be enlarged without scrolling in two dimensions at a width equivalent to 320 CSS pixels or a height equivalent to 256 CSS pixels.

    This enhancement helps users with low vision or who have trouble seeing web content in a browser due to monitor size, device type, poor lighting, or other situations. Reflow can be turned off with a system property for instances, experiences, and pages. See Reflow for Configurable Workspace for details.

    Localization information

    Chinese and Japanese language support
    Process documents in additional languages with added support for Simplified Chinese and Japanese.