Combined Now Assist in Document Intelligence release notes for upgrades from Yokohama to Zurich

zurich Combined Product Files

Release

zurich

ft:locale

en-US

ft:publication_title

zurich Combined Product Files

ft:clusterId

delta3zy

bundleId

delta3zy

Combined Now Assist in Document Intelligence release notes for upgrades from Yokohama to Zurich

Release version: Zurich

Updated August 11, 2026

10 minutes to read

Summarize

Summarized using AI

Summary of Combined Now Assist in Document Intelligence Release Notes for Upgrades from Yokohama to Zurich

This consolidated release notes document provides ServiceNow customers with a comprehensive summary of Now Assist in Document Intelligence updates and changes from the Yokohama release family through to Zurich. It is designed to assist customers in preparing for upgrades by highlighting new features, changes, removals, and activation requirements relevant to Now Assist in Document Intelligence.

Show full answer Show less

Important pre- and post-upgrade tasks should be reviewed before upgrading to Zurich to ensure a smooth transition.

New Features

LLM Selection and Model Providers: Starting in Yokohama Patch 6, customers can configure different large language models (LLMs) for extraction and Q&A use cases. New AI model providers Google Gemini and AWS Claude are now available alongside Now LLM Service and Azure OpenAI for all Now Assist applications.
Document and Visual Insights AI Agent: Introduced in Yokohama Patch 3 and enhanced in Zurich, this AI agent automates data extraction from documents and images without requiring predefined use cases, supports file uploads, and displays results in a dedicated document view. It also supports access control lists (ACLs) for improved security and can run as either a dynamic AI user or human user with appropriate privileges.
Automation and Integration Enhancements: Full automation for document data extraction, integration with Virtual Agent for document-based chat responses, and extraction from accounts payable invoices were introduced in Yokohama.
Skill Consolidation: In Zurich Patch 1, document data extraction and document Q&A capabilities were merged into a single “Extract information from documents” skill, simplifying setup and task review for agents.
Language and Image Processing Improvements: Language model selection enhances OCR accuracy, image mode optimizes processing of image-based use cases, and multilingual file support (including Simplified Chinese and Japanese) was added.
Operational Sustainability Risk Management: Extract ESG-related data from invoices to support compliance initiatives.
Usability Enhancements: Ability to open test documents in a new browser tab for larger workspace views and image captioning support for accessibility in knowledge base articles.

Changes

Usage Measurement: Transition from a 365-day look-back to a 365-day burn-down usage measurement model with resets at contract anniversaries was implemented starting in Yokohama Patch 5 and continued in Zurich.
Default Skill Activation: New installations automatically enable designated Now Assist skills, and during upgrades, previously unconfigured skills are turned on automatically.
Limitations Updates: Document processing limits were adjusted in Zurich, including a 20-page limit per file for table-based extractions in some patches, support for DOCX files, and varying page limits depending on image mode usage.
AI Agent Functionality: Added tools allow the AI agent to display extracted data and manage use cases based on document content and descriptions.

Removed Features

The standalone Document extraction and Document Q&A skills were removed from the list of Platform skills in the Now Assist Admin console in Zurich, as their capabilities are now combined into a single skill.

Activation and Requirements

Now Assist features require activation of any Now Assist plugin from the ServiceNow Store.
Installation of the Document Intelligence application (sndocintel) and at least one Now Assist product is mandatory for both Yokohama and Zurich releases.
No changes were noted for browser compatibility or accessibility compliance between Yokohama and Zurich.

Localization and Accessibility

Zurich Patch 1 introduced support for processing files containing multiple languages, including Simplified Chinese and Japanese.
No additional accessibility updates were reported.

Practical Benefits for ServiceNow Customers

Enhanced flexibility in AI model selection allows customers to tailor document extraction and Q&A capabilities to their specific needs.
Improved automation with the AI agent reduces manual workload by autonomously processing documents and images.
Consolidated skills simplify administration and usage, enabling agents to efficiently review all extracted information in one place.
Expanded language and file format support broadens applicability across diverse document types and global use cases.
Security improvements via ACLs provide better control over AI agent operations and data access.

Reviewing these updates will help customers maximize the benefits of Now Assist in Document Intelligence during and after their upgrade to Zurich.

Consolidated page of all release notes for Now Assist in Document Intelligence from Yokohama to Zurich.

How to use this page

To help you prepare for your upgrade, we have combined the cross-family Now Assist in Document Intelligence release notes onto one page. Read this summary of the new features, changes, and updated information for your product from Yokohama to Zurich.

Tip:

If there were no updates for a release notes section in a certain family release, we included a short note for your reference. For example, if a product did not have any updates in Tokyo, the row says "No updates for this release."

Important information for upgrading Now Assist in Document Intelligence to Zurich

Before you upgrade to Zurich, review these pre- and post-upgrade tasks and complete the tasks as needed.


Release	Release notes
Yokohama	No updates for this release.
Zurich	No updates for this release.

New features

Between your current release family and Zurich, new features were introduced for Now Assist in Document Intelligence.


Release	Release notes
Yokohama	Yokohama Patch 6 LLM selection for use cases Configure a different LLM to generate predictions for extraction and Q&A use cases. New third-party AI model provider options available for all Now Assist applications Google Gemini and AWS Claude are available for Now Assist skills and AI agents in addition to Now LLM Service and Azure OpenAI. Yokohama Patch 3 Document and visual insights AI agent Use an AI agent to help process the tasks that analyze and extract data from documents and images. Full automation for document data extraction Automatically extract the document data and process the document task without agent review. Data extraction from accounts payable (AP) invoices Extract data from invoices with Now Assist for APO. Document chat in Virtual Agent Integrate Now Assist for Virtual Agent with Now Assist in Document Intelligence to enable the chat responses that are based on the document content. Attachment summarization in ITSM View the summaries of attachments with the record summary in ITSM. Early Availability Document extraction Extract the data from documents by using LLMs to provide the recommended field values. Document Q&A Use generative AI to find the answers to the predefined questions in a document. Setting up use cases for Now Assist in Document Intelligence Set up Document Intelligence use cases to enable agents to use the document extraction and document Q&A skills.
Zurich	Zurich Patch 4 Open document in a new tab View a test document in a larger workspace on a separate browser tab during use case setup. Image captioning in Knowledge Center Extract information from images to support accessibility captioning in knowledge base articles. Document and visual insights AI agent enhancements Leverage features that enable you to use the document and visual insights AI agent with selected LLMs to upload files, extract information without a predefined use case, and display results in a dedicated document view. Select an LLM for the AI agent to use when processing documents and images. Now LLM Service is not an available option for LLM selection. Prompt the AI agent to upload a file to process. View the results of the AI agent actions in a document view screen. Zurich Patch 1 Document Intelligence for Now Assist Skill Kit Use document and visual intelligence to leverage extraction, question answering, and summarization capabilities for a skill created with Now Assist Skill Kit. Language model selection Select the language for a use case to help the optical character recognition (OCR) model to detect text in the document and image files. Image mode selection for use cases Turn on image mode to process images more efficiently for use cases that use a multimodal AI model. Model provider flexibility at the use case level Choose a model provider at the use case level, including a Now Assist default option that uses the instance-level model selected in AI Control Tower. Information extraction for Operational Sustainability Risk Management Extract ESG-related information from invoices to support Operational Sustainability Risk Management initiatives and regulatory compliance. 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. Early Availability New third-party AI model provider options available for all Now Assist applications Google Gemini and AWS Claude are available for Now Assist skills and AI agents in addition to Now LLM Service and Azure OpenAI.

Changes

Between your current release family and Zurich, some changes were made to existing Now Assist in Document Intelligence features.


Release	Release notes
Yokohama	Yokohama Patch 11 Changes to Now Assist usage measurement Starting with Yokohama Patch 5, Now Assist usage measurement is transitioning from a 365-day look-back model to a 365-day burn-down model, with usage resetting at the contract anniversary date. For more information, refer to KB KB2704710: Now Assist Usage - Overview & New Measurement Logic. Some Now Assist skills are turned on by default The new default behavior works as follows: New customers: When you install a Now Assist product, designated skills are turned on automatically. Existing customers who are upgrading (starting with Yokohama Patch 11): Any previously unconfigured skill is turned on automatically (the skill was never configured and turned on, then turned off again). Previously configured skills that were turned on, then off, remain inactive. Yokohama Patch 6 Document and visual insights AI agent enhancements Generate a summary of document and image attachments with the document and visual insights AI agent.
Zurich	Zurich Patch 5 Changes to Now Assist usage measurement Zurich Patch 4 Changes to limitations The page count limit decreases to 20 pages per file for an extraction based on a use case with a table defined. Zurich Patch 1 Merged skills Document data extraction and document Q&A capabilities are available in a single Extract information from documents skill. The Extract information from documents skill is available in the list of Platform skills in the Now Assist Admin console. Data extraction and document Q&A capabilities can be set up for the same use case. Agents can review the AI predictions for the fields, tables, and questions in the same task. Document and visual insights AI agent enhancements Leverage added tools that enable the AI agent to display the extracted data and to look up existing use cases or create use cases based on descriptions and document attachments. Changes to limitations The limitations set for Now Assist in Document Intelligence properties are updated to support processing larger documents. DOCX files are supported for information extraction. The page count limit is 200 pages per file If image mode is turned off for the use case. If image mode is turned on, the page count limit is 10 pages per file. The file size limit is 20 MB.

Removed

Between your current release family and Zurich, some Now Assist in Document Intelligence features or functionality were removed.


Release	Release notes
Yokohama	No updates for this release.
Zurich	The Document extraction skill has been removed from the list of Platform skills in the Now Assist Admin console. The Document Q&A skill has been removed from the list of Platform skills in the Now Assist Admin console.

Deprecations

Between your current release family and Zurich, some Now Assist in Document Intelligence features or functionality were deprecated.


Release	Release notes
Yokohama	No updates for this release.
Zurich	No updates for this release.

Activation information

Review information on how to activate Now Assist in Document Intelligence.


Release	Release notes
Yokohama	Now Assist features are available with activation of any Now Assist plugin from ServiceNow Store. The following plugins are available: For more information, see Configuring Now Assist in Document Intelligence.
Zurich	Now Assist features are available with activation of any Now Assist plugin from ServiceNow Store. The following plugins are available: For more information, see [Placeholder link text to key bundle-platai.docintel-configuring-now-assist].

Additional requirements

If any additional requirements were introduced or changed for Now Assist in Document Intelligence we have noted them here.


Release	Release notes
Yokohama	Now Assist in Document Intelligence requires the installation of the Document Intelligence application (sn_docintel) and at least one Now Assist product.
Zurich	Now Assist in Document Intelligence requires the installation of the Document Intelligence application (sn_docintel) and at least one Now Assist product.

Browser requirements

If any specific browser requirements were introduced or changed for Now Assist in Document Intelligence we have noted them here.


Release	Release notes
Yokohama	No updates for this release.
Zurich	No updates for this release.

Accessibility information

Review details on accessibility information for Now Assist in Document Intelligence, such as specific requirements or compliance levels.


Release	Release notes
Yokohama	No updates for this release.
Zurich

Localization information

If there are specific localization considerations for Now Assist in Document Intelligence we have noted them here.


Release	Release notes
Yokohama	No updates for this release.
Zurich	Zurich Patch 1 Support for files in multiple languages Process files with text in multiple languages, including Simplified Chinese and Japanese.

Highlight information

If there are specific highlight considerations for Now Assist in Document Intelligence we have noted them here.


Release	Release notes
Yokohama	Yokohama Patch 11 Review changes to Now Assist usage measurement. Some Now Assist skills, agents, and agentic workflows are on by default. Additional role configuration is required for agentic workflows and AI agents included with Now Assist applications. Yokohama Patch 6 Summarize the content in document and image attachments with the document and visual insights AI agent. Choose a large language model (LLM) to generate predictions for extraction and Q&A (question & answer) use cases. Use Google Gemini and Anthropic Claude on AWS as AI model providers for Now Assist skills and AI agents in addition to Now LLM Service and Azure OpenAI. Yokohama Patch 3 Boost productivity by using the document and visual insights AI agent 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. Extract the data from invoices with Now Assist for Accounts Payable Operations (APO). Early Availability Speed up your document processing workflows and quickly extract the text and tables from your documents. Save time looking for the information that you need in a document, and quickly find the answers to predefined questions. See Now Assist in Document Intelligence for more information.
Zurich	Zurich Patch 5 Review changes to Now Assist usage measurement. Zurich Patch 4 View a test document in a larger workspace on a separate browser tab during use case setup. Use the document and visual insights AI agent to upload files, extract information without a predefined use case using a selected LLM, and display the results in a dedicated document view. Additional role configuration is required for agentic workflows and AI agents included with Now Assist applications. Zurich Patch 1 Leverage document data extraction and document Q&A capabilities in a single Extract information from documents skill. Create skills with data extraction, question answering, and summarization capabilities by using document and visual intelligence in Now Assist Skill Kit. Choose the language for a use case to help the optical character recognition (OCR) model better detect the text to extract from your files. Extract information from files with text written in Simplified Chinese or Japanese. Extract information from documents for Operational Sustainability Management (Operational Sustainability Risk Management) workflows. Early Availability Use Google Gemini and Anthropic Claude on AWS as AI model providers for Now Assist skills and AI agents in addition to Now LLM Service and Azure OpenAI. See [Placeholder link text to key bundle-platai.docintel-nowassist-landing] for more information.