---
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


---

# Information Extraction skill

# Extract information from documents {#ariaid-title1}

Release version: Australia  
Updated November 5, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read  
The Extract Information from documents skill (Information Extraction skill) uses generative AI to automatically extract content from documents and images, and to respond to questions about that content.

With the Information Extraction skill, you can extract specific fields, tabular data, and answers about documents or images. You can then integrate the extracted data into your workflows. The skill transforms unstructured files,
such as invoices, purchase orders, and contracts, into structured data that populates ServiceNow records, eliminating the need for manual data entry.

You configure this skill in the AI Admin Hub. You can define one or more use cases that specify what to extract from a particular type of document. For example, a use case for purchase order forms extracts date and number, captures an
itemized list with prices, and answers questions about specific terms in the descriptions.{#cu-extract-information-from-document__cu-extract-information-from-document-para-2}  
Important:  
The Extract Information from documents skill can't be cloned. To use the skill, create a new use case or copy an existing one. 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.") or [Copy a use case](https://www.servicenow.com/docs/JMWOGf~Yc23wsrHxpvR~jw "Copy an existing use case to use as a starting point for a similar one. The copy includes the original fields, tables, questions, integrations, and flows.").

## Define the information to extract {#cu-extract-information-from-document__section_wls_5pj_xjc}

Within a single use case, you can define any combination of the following:{#cu-extract-information-from-document__cu-extract-information-from-document-para-3}

* Specific fields to extract, such as a date or a document number.
* A table structure with multiple columns to capture repeating line items.
* Questions for generative AI to answer based on the text and images in a document.
{#cu-extract-information-from-document__ul_xls_5pj_xjc}

## Benefits {#cu-extract-information-from-document__section_zg3_sfz_yjc}

The Extract information from documents skill provides the following benefits:{#cu-extract-information-from-document__cu-extract-information-from-document-para-4}

* Populates ServiceNow records with data extracted from documents.
* Reads both text and images in a document.
* Runs automatically or routes results to a reviewer for validation, depending on the automation mode.

{#cu-extract-information-from-document__ul_tkn_sfz_yjc}  
Note:  
The Extract information from documents skill uses generative AI to process documents. Results may be inaccurate or incomplete. Review extracted data before using it in production workflows.

## Scenarios {#cu-extract-information-from-document__section_qds_qgz_yjc}

The Extract information from documents skill supports the following scenarios:{#cu-extract-information-from-document__cu-extract-information-from-document-para-5}

Field population
:   Extracts values from an uploaded document and writes them to the fields of a record.

Assisted review
:   Presents predicted values to a reviewer for validation before saving them to a record.
**Related concepts**   

* [Use cases in Information Extraction skill](https://www.servicenow.com/docs/y~Jz2L23f5ttfxiuSfS~7Q "Use cases in the Information Extraction skill define what documents to process and what information to extract, so generative AI can accurately retrieve structured data from unstructured documents.")
* [Automation modes](https://www.servicenow.com/docs/i6KzhgYWrc57LJ_LjceWaw "Automation modes in the Information Extraction skill determine whether predictions are accepted automatically or routed to a human agent for review before a document task completes.")

