Validators let you define rules that check whether extracted fields meet your requirements — so you only review documents that actually need attention. This helps you reduce manual work and improve data quality at scale.Documentation Index
Fetch the complete documentation index at: https://docs.cradl.ai/llms.txt
Use this file to discover all available pages before exploring further.
Available Validators
Here’s a quick overview of the validators you can use to automatically flag documents for review:- Confidence threshold
Triggers a review if the model’s confidence in a field is below a specified percentage. Useful for catching uncertain predictions. - Logical expression
Validates a field using custom logic (e.g.total_amount > 0). Ideal for numeric checks, date comparisons, and other business rules. - RegEx
Ensures that a field matches a specific pattern using regular expressions. Great for validating formats like postal codes, VAT numbers, or phone numbers. - Cannot be empty
Flags the document if a required field is missing or empty. Use this to make sure essential information is always extracted.