Redacting customer data before it reaches your CRM
A quick look at how PII Detect finds names, emails, and card numbers in free text.
Support tickets, call notes, and web forms all tend to collect more personal data than anyone asked for. PII Detect runs incoming text through our managed entity recognition model and hands back both the entity list and a redacted copy — the same request the tool page itself makes.
The categories that matter most in practice are the boring ones: email addresses, phone numbers, and card numbers. Names and addresses are useful too, but they carry more false positives, so we surface a confidence score alongside every match rather than silently dropping anything.
If you're wiring this into an intake pipeline, the redacted text field is safe to store or forward as-is. The entity list is there so a human reviewer can double-check edge cases before anything ships downstream.