Document processing
Separation, extraction, and getting clean data out of Paige.
Getting Paige document separation right
Pick the right separation method for each scan job, write AI guidance that describes real boundary cues, and prove the setup on a small test set before trusting large batches.
Outbound IP ranges for firewall allow-lists
The two subnets Paige connects from, the firewall rules that let its FTP and Content Central exports through — including the passive-FTP port range most setups miss — and how to verify from the right side of your network.
Paige extracted a blank or wrong field
Trace a missing or wrong field value through Paige's pipeline — grouping, recognized text, field guidance, confidence filtering, and export mapping — and fix the stage that dropped it.
Set up Folder Monitor
Install the Paige Folder Monitor desktop app, connect it with an API key, and create monitoring rules so files dropped in a Windows folder upload themselves to a scan job — with the completed-folder guarantee explained.
Set up scan jobs
Create a scan job with the five-step Scan Job Setup wizard — name, capture sources, separation, document types, and people — then connect an export destination so processed documents flow out automatically.
Teach Paige to identify document types
The three ways to add document types — preconfigured library, custom, or detected from samples — and the AI Document Type Identification description that decides whether each document gets classified as the right one.
Write extraction guidance the AI can follow
The per-field instructions that turn wrong or blank extractions into right ones — where the AI Extraction Guidance box lives, what good guidance sounds like, and the format guide and value lists that back it up.