For the complete documentation index, see llms.txt. This page is also available as Markdown.

Key concepts

Learn how document types, jobs, confidence, access, credits, and webhooks work.

Document AI turns files into structured, reviewable outputs.

Core workflow: Upload → Classify when needed → Extract → Validate → Deliver.

Start with the right document type

A document type defines the fields Document AI extracts from a file.

Select it when you submit an extraction. It also determines the fraud checks that run.

Use the same document type across your workflow.

Classification categories and extraction document types are different. Classify unknown files first, then select the closest document type.

Jobs run in the background

Extraction, classification, and generation each create a background job.

Track each job until it is processed or failed. Each file has its own job.

Use confidence to route review

Every extracted field includes a confidence score. Use it to prioritize human review.

High-confidence values can move forward automatically. Lower-confidence values should be reviewed.

Manage credits and access

Document AI uses prepaid credits for processed pages. Check your balance in Settings → Usage.

Account roles control access to workspace settings. Collection roles control access within each collection.

Deliver results with webhooks

Webhooks notify your systems when a background job completes.

Document AI sends the complete result to your configured URL. Verify each request before processing it.

Last updated