---
sourceDocument: Australia Enable AI
sourceDocumentLink: https://www.servicenow.com/docs/r/australia/intelligent-experiences

 Release :

    - australia

ft:locale :

    - en-US

ft:publication_title :

    - Australia Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Limitations

# Limitations in Content Understanding {#ariaid-title1}

Release version: Australia  
Updated March 12, 2026  
![](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 Content Understanding

This document outlines the key limitations that ServiceNow customers should be aware of when using Content Understanding skills and AI agents, specifically focusing on file formats, sizes, page counts, and language support.
Understanding these constraints helps optimize document processing and ensures successful data extraction and analysis within your workflows.
Show full answer Show less  

## Information Extraction Skill Limits

* **Supported File Formats:** JPEG, PNG, PDF, and DOCX. Note that encrypted files are not supported.
* **File Size:** Maximum file size allowed is 20 MB.
* **Page Count:**
  * If *image mode* is enabled, the suggested upper limit is 50 pages per file, with a minimum of 10 pages. However, actual limits depend on model constraints, file complexity, and platform payload limits (max 32 MB per request). It is recommended to test incrementally to find effective limits.
  * When image mode is enabled, the hard page count limit is 10 pages per file.
  * When image mode is inactive:
    * 200 pages per file if no tables are involved in the use case.
    * 20 pages per file if the use case includes tables.
* **Maximum Fields per Use Case:** Up to 50 fields can be defined for each use case.
* **Supported Languages:**
  * For images requiring OCR, supported languages depend on the OCR model used.
  * For text-based files, any language supported by the selected or default large language model (LLM) applies.

## Content Insights AI Agent Limits

* **Supported File Formats:** JPEG, PNG, PDF, DOCX, XLSX, CSV, TXT, and PPTX.
* **File Size:** Maximum file size is 20 MB.
* **Page Count:**
  * 200 pages per file per document task.
  * If the use case includes tables, the limit reduces to 20 pages per file.
* **Supported Languages:** The AI agent supports any language recognized by the selected or default LLM for both image and text-based files.

## Practical Considerations for ServiceNow Customers

To ensure optimal performance when using Content Understanding capabilities, customers should:

* Confirm that input files comply with supported formats and size limits.
* Be mindful of page count limits that vary based on mode (image or text) and presence of tables in use cases.
* Test documents incrementally when working near limits to identify specific constraints based on document complexity and model capacity.
* Choose appropriate language models and OCR configurations aligned with the language content of files.
* Limit use cases to 50 fields or fewer to maintain compatibility with the extraction skill.  
Review the file format, size, page count, and language limitations that apply to skills and AI agents in Content Understanding.

## Information extraction skill limitations {#cu-limitations__section_kpt_3wj_lgc}

The following table lists the limitations for the Information Extraction skill in Content Understanding.{#cu-limitations__section_kpt_3wj_lgc-para-1}
{#cu-limitations__table_uds_5wj_lgc__entry__2}

| Limit | Description |
|-|-|
| File formats | The supported file formats are JPEG, PNG, PDF, and DOCX. Note: Encrypted files aren't supported. |
| File size limit | The file size limit is 20 MB. |
| Page count limit | When image mode is enabled, the suggested upper boundary is 50 pages per file, with a minimum of 10 pages. Actual performance varies based on the following factors: * Model constraints: Some models limit the number of images per request. For example, some models allow a maximum of 20 images per request. * File complexity and size: Documents with dense text or large images consume more tokens and memory, which can affect processing time and efficiency. * Platform payload limits: The upper limit for data passed to the language model is 32 MB. Because image sizes vary, the exact page count that fits within this limit varies by document. {#cu-limitations__ul_nb1_3st_bjc} Because these constraints depend on your configuration, document characteristics, and the model used, test your documents by gradually increasing the page count to identify the effective limits for your use case. If image mode is enabled, the page count limit is 10 pages per file. If image mode is inactive, 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. {#cu-limitations__ul_ch4_gw3_nhc} Image mode is selected during use case setup. For more information, see [Set up a use case](https://www.servicenow.com/docs/7i2Se9AZ5Ls1TvXR7fZJPA "Create a use case to define the information to extract from a document for processing."). |
| Maximum number of fields per use case | The maximum number of fields per use case is 50. |
| Supported languages | For image files that require OCR (optical character recognition) to detect text, OCR models support different language groups. For more information, see [Languages supported by Content Understanding](https://www.servicenow.com/docs/XzBFQ0xuQo7nGb4mSL3wuA "Use this reference to identify which languages the Content Understanding application supports for text-based and image-based files, and which optical character recognition (OCR) model applies to each language group."). 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 Content Understanding](https://www.servicenow.com/docs/Qcu_7obrQJaaZ6iPQwVq_g "The Content Understanding application uses large language models (LLMs) to support generative AI and agentic AI capabilities."). |
[Table 1. Information extraction skill limits]

{#cu-limitations__table_uds_5wj_lgc}

## Limits for the Content insights AI agent {#cu-limitations__section_nqz_3wj_lgc}

The following table lists the limitations for the Content insights AI agent.{#cu-limitations__section_nqz_3wj_lgc-para-1}
{#cu-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 extracts data 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 Content Understanding](https://www.servicenow.com/docs/Qcu_7obrQJaaZ6iPQwVq_g "The Content Understanding application uses large language models (LLMs) to support generative AI and agentic AI capabilities."). |
[Table 2. Content insights AI agent limits]

{#cu-limitations__table_lkm_ywj_lgc}