Information Extraction skill workflow

concept australia Updated Nov 6, 2026 1 min read information-extraction-workflow.md
Raw file servicenow.com

Information Extraction is a skill that analyzes documents to provide values for defined fields, table columns, and questions in a use case. It populates ServiceNow records with extracted data from documents.

Processing stages

When a document enters a workflow, the Information Extraction skill examines its content and retrieves the requested information according to the use case. The use case defines what to extract from a document and where to write the results. After a use case is configured, the skill follows these stages at run time:

  • Stage 1: Document task creation

    A trigger — such as a document upload, an inbound email, or an attachment added to a record — creates a document task.

  • Stage 2: Prediction

    The Information Extraction skill processes the document and returns a prediction for each field, table column, or question in the use case.

  • Stage 3: Review or automation

    In full automation mode, the predictions populate the fields in the target table. In agent review mode, the document task goes to a fulfiller, who validates or corrects the predicted values.

  • Stage 4: Completion

    After the document task is complete, the predictions populate the target fields and the integrated workflow continues.

Related topics

Content Understanding personas

Predictions in Information Extraction skill

Use cases in Information Extraction skill

Automation modes

Keywords information extractiondocument processingskill workflow
Search documentation
Search document titles and file paths on the australia branch