Quality control
You have the following quality-control options for your extracted document data:
notes | ||
---|---|---|
Custom validation logic | Validating extractions | Throw extraction errors and warnings based on your custom rules. For example, use a regex expression to throw azip code is invalid error for a field customer_zip_code . |
Monitor in real time | Monitoring extraction metrics | Real-time dashboard in the Sensible app. Track your document extraction metrics in one place, in real time. Aggregate performance summaries, monitor configuration success, track usage at the document type level, and view historic performance data for all production deployments. |
Manual review and correction | Human review | Set criteria based on metrics and validations for flagging extractions for review. A reviewer can then use the Sensible app to manually correct errors in flagged extractions and approve or reject extractions. |
Updated 1 day ago