--- sourceDocument: Zurich Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/zurich/intelligent-experiences Release : - zurich ft:locale : - en-US ft:publication_title : - Zurich Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Limitations # Limitations in Now Assist in Document Intelligence {#ariaid-title1} Release version: Zurich Updated August 26, 2025 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) 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 Limitations in Now Assist in Document Intelligence This document outlines the important limitations ServiceNow customers should be aware of when using Now Assist in Document Intelligence. Understanding these constraints helps ensure effective setup and use of the platform's capabilities for document processing and AI-driven insights. Show full answer Show less ## Skill Limits for Now Assist in Document Intelligence * **Supported File Formats:** JPEG, PNG, PDF, and DOCX are supported. Encrypted files are not supported. * **File Size Limit:** Maximum file size allowed is 20 MB. * **Page Count Limits:** * If image mode is enabled during use case setup, the limit is 10 pages per file. * If image mode is disabled: * 200 pages per file if no tables are defined in the use case. * 20 pages per file if a table is defined. * **Maximum Fields Per Use Case:** Limited to 50 fields. * **Supported Languages:** * For image files requiring OCR, language support depends on available OCR models. * For text-based files, recognition covers all languages supported by the selected or default large language model (LLM). ## Limits for Document and Visual Insights AI Agent * **Supported File Formats:** JPEG, PNG, PDF, DOCX, XLSX, CSV, TXT, and PPTX. * **File Size Limit:** Maximum 20 MB per file. * **Page Count Limits:** * 200 pages per file for general document tasks. * If extraction involves a use case with tables, the limit is 20 pages per file. * **Supported Languages:** The AI agent supports all languages available in the selected or default LLM for both image and text files. ## Practical Implications ServiceNow customers should design use cases within these constraints to ensure optimal performance. Key considerations include file format compatibility, adherence to size and page limits, and ensuring language support aligns with their document types. For use cases involving tables or image mode, stricter page limits apply, which may affect how documents are processed. These limitations directly impact how much and what type of data can be processed in a single transaction, influencing document ingestion strategies and AI extraction workflows. There are several important limitations to be aware of when you're using Now Assist in Document Intelligence. ## Now Assist in Document Intelligence skill limits {#now-assist-document-intelligence-limitations__section_kpt_3wj_lgc} The following table lists the important limitations for the skills in Now Assist in Document Intelligence.{#now-assist-document-intelligence-limitations__table_uds_5wj_lgc__entry__2} | Limit | Description | |-|-| | File formats | The supported file formats are JPEG, PNG, PDF, and DOCX. Note: Encrypted files are not supported. | | File size limit | The file size limit is 20 MB. | | Page count limit | If image mode is turned on for the use case, the page count limit is 10 pages per file. If image mode is turned off, the page count limit is: * 200 pages per file if no tables are defined for the use case. * 20 pages per file if a table is defined for the use case. {#now-assist-document-intelligence-limitations__ul_ch4_gw3_nhc} Image mode is selected during use case setup. For more information, see [Set up a use case for Now Assist in Document Intelligence](https://www.servicenow.com/docs/iqB4_8Mmo5GNmaBUq187~g "Create a use case record to define a document you want to process with Now Assist in Document Intelligence."). | | Maximum number of fields per use case | The maximum number of fields per use case is 50. | | Supported languages | For image files that need optical character recognition (OCR) to detect the text in them, there are OCR models to support different language groups. For more information, see [Languages supported by Now Assist in Document Intelligence](https://www.servicenow.com/docs/kj0AeCvh6W0iq8dTQCTA4A "Now Assist in Document Intelligence supports text in multiple languages."). For text-based files, the skill recognizes any language supported by the selected or default model, as described in the model card for the LLM. For more information on LLMs, see [Large language models used by Now Assist in Document Intelligence](https://www.servicenow.com/docs/Hsg6o0_gI82K1nRROD6GRw "Now Assist in Document Intelligence uses large language models (LLMs) to perform generative AI and agentic AI capabilities."). | [Table 1. Skill limits for Now Assist in Document Intelligence] {#now-assist-document-intelligence-limitations__table_uds_5wj_lgc} ## Limits for the document and visual insights AI agent {#now-assist-document-intelligence-limitations__section_nqz_3wj_lgc} The following table lists the important limitations for the document and visual insights AI agent.{#now-assist-document-intelligence-limitations__table_lkm_ywj_lgc__entry__2} | Limit | Description | |-|-| | File formats | The supported file formats are JPEG, PNG, PDF, DOCX, XLSX, CSV, TXT, and PPTX. | | File size limit | The file size limit is 20 MB. | | Page count limit | For each document task, the page count limit is 200 pages per file. If the AI agent performs the extraction based on a use case that includes a table, the limit decreases to 20 pages per file. | | Supported languages | For image and text-based files, the AI agent recognizes any language supported by the selected or default model, as described in the model card for the LLM. For more information on LLMs, see [Large language models used by Now Assist in Document Intelligence](https://www.servicenow.com/docs/Hsg6o0_gI82K1nRROD6GRw "Now Assist in Document Intelligence uses large language models (LLMs) to perform generative AI and agentic AI capabilities."). | [Table 2. Document and visual insights AI agent limits] {#now-assist-document-intelligence-limitations__table_lkm_ywj_lgc} **Related reference** * [Components installed with Now Assist in Document Intelligence](https://www.servicenow.com/docs/VOlslvqrnW1A8DfwYEbyjA "Components are installed with the activation of Now Assist in Document Intelligence.") * [Data extraction modes in Now Assist in Document Intelligence](https://www.servicenow.com/docs/r7stJ2D_yCf9T3JbVpEguQ "The extraction mode determines how Now Assist in Document Intelligence processes a document task.") * [Document and visual insights AI agent](https://www.servicenow.com/docs/W1dNFW5UfjMnFV1CXEwW1Q "The document and visual insights AI agent gathers context from user input and document or image attachments, generates the requested information based on the content, and provides the information along with any relevant task details.") * [Document Intelligence tool for AI Skill Kit](https://www.servicenow.com/docs/JlYQ_NSc87LIJXFxoR~ccw "Use the Document Intelligence tool to leverage extraction, question answering, and summarization capabilities for a skill created with AI Skill Kit.") * [Field types in Now Assist in Document Intelligence](https://www.servicenow.com/docs/nBYpeDivzKQk0___TkAi7A "The field type specifies the information that is retrieved from a document with Now Assist in Document Intelligence.") * [Now Assist in Document Intelligence forms](https://www.servicenow.com/docs/~FV_sfdHnQ4sgYb2VKHiiQ "Use forms to view and update Now Assist in Document Intelligence information.") * [Large language models used by Now Assist in Document Intelligence](https://www.servicenow.com/docs/Hsg6o0_gI82K1nRROD6GRw "Now Assist in Document Intelligence uses large language models (LLMs) to perform generative AI and agentic AI capabilities.") * [Languages supported by Now Assist in Document Intelligence](https://www.servicenow.com/docs/kj0AeCvh6W0iq8dTQCTA4A "Now Assist in Document Intelligence supports text in multiple languages.")