How do I automate document triage before data extraction?

Direct answer

Document triage should happen before extraction when one channel receives many different file types, business documents, attachments, or supporting materials.

The workflow should determine what arrived, whether it is processable, which extractor should handle it, and whether any file needs review before extraction.

What triage should include

A strong triage layer captures sender, subject, folder, file type, case identifier, document class, and rejection or review reason for files that should not move forward.

This prevents operations teams from manually sorting documents before the extraction workflow can even begin.

How Lido helps

Lido supports document classification and workflow routing so mixed inbound files can be directed to the right extraction setup or exception queue.

That makes the workflow more resilient when documents arrive through email, shared folders, APIs, or other channels.

Example workflow

1. Define which documents should be processed, ignored, split, or reviewed.
2. Capture intake metadata and classify the document type.
3. Route each document class to the right extractor and validation rules.
4. Track unclassified or rejected documents so triage improves over time.