Detection categories
What Northdocs looks for and how to tune it with keywords.
Detection | 1 min read
Northdocs has 30 built-in categories, plus manual boxes, including names, addresses, emails, phone numbers, national IDs (such as CPR), company numbers (CVR), bank/IBAN details, health information, titles, confidential markings, attorney-client privilege, and attorney work product.
How finding works
- Structured data (IDs, emails, card numbers, IBAN, CPR-style numbers) is matched with deterministic patterns. IBAN (mod-97) and card numbers (Luhn) are checksum-validated; CPR numbers are checked for a plausible date of birth, not a checksum.
- Unstructured data (names, organizations, addresses, health narrative, privilege language) uses on-device NER plus optional OVHcloud AI Endpoints after first paint.
Tune what gets flagged
You can enable or disable categories under Settings → Categories, and add keyword lists under Settings → Keywords to always redact (include) or never flag (exclude) specific terms. Magic Redact (available on Pro and above) describes a concept in plain language when a pattern is not enough.
Related articles
- Magic Redact filtersDescribe custom PII in plain language; Northdocs validates and applies AI-assisted filters.
- Fast Track reviewEntity-first triage: accept one person or organization once and every instance follows.
- Policy packs by matter typeAssign versioned detection, pseudonymization, and export defaults to an organization or case.