90 data types. 8 categories. One model.
BeeSensible recognises personal, financial, medical, and credential data across the apps your team uses. English and Dutch, processed in the EU, configurable per team.
Hi team, Sarah Martinez will be joining the project. Her contact is NL91 ABNA 0417 1643 00.
Every type of sensitive data your team touches.
Detection profiles let admins toggle categories on and off per app. A healthcare profile enables medical codes; a finance profile enables IBAN and card data. All off by default until you turn them on.
- · Full name
- · Email address
- · Phone number
- · Date of birth
- · Age
- · Street address
- · Postal code
- · City / Region
- · GPS coordinates
- · IBAN
- · Credit card number
- · BIC / SWIFT
- · Bank account number
- · BSN (NL)
- · Passport number
- · Driver's licence
- · Tax ID / VAT
- · Medical code (ICD-10)
- · Diagnosis
- · Prescription
- · Health insurer ID
- · API key
- · Password
- · OAuth token
- · SSH private key
- · Contract reference
- · Case number
- · Legal entity ID
- · Chamber of Commerce
- · Customer ID
- · Employee number
- · Project code
- · Internal reference
The severity shown above is just an example. You fine-tune exactly what counts as critical or warning to match your organisation's policy.
Configure exactly what counts as sensitive, per team, per app.
Every entity type has an on/off toggle and a severity level. Admins build profiles for each workflow and assign them to the relevant apps. Finance sees IBAN warnings; everyone else doesn't.
- · Toggle individual entity types without rebuilding a profile from scratch.
- · Preview a sample match in the editor before saving.
- · Assign one profile per app, or reuse across your full stack.
Detection Profiles
Manage which PII entities are detected and how they are masked.
Balanced detection for everyday Dutch workplace use.
Strict profile for finance and treasury teams.
Detection built for live typing, not batch scanning.
BeeSensible analyses text in the browser session as the user writes. Text is sent to BeeSensible's EU servers, processed in working memory, and discarded. No content log, no clipboard access.
In-session, not in-flight
Text is processed when typed, not intercepted mid-flight.
Text is sent to BeeSensible's EU servers, processed in working memory, and discarded. Nothing is stored or logged. Only counts reach the dashboard.
Profile-scoped
Active entity types follow the detection profile.
Admins configure which types are active per app. A finance team's IBAN profile doesn't apply to the support team's Intercom window, unless the admin enables it.
Per-severity actions
Critical and warning map to different defaults.
Critical detections (IBANs, API keys, government IDs) prompt stronger defaults. Warning-level types (names, emails) are highlighted but less interruptive.
Accurate enough to trust. Quiet enough to use daily.
Accuracy
Measured per entity type, not as a single average.
The detection is evaluated across every category and severity level. A strong overall result can't hide a weak class because each entity type is checked on its own.
Low noise
Built to avoid interrupting people unnecessarily.
Precision is tuned for each entity type. Common words like 'name' or generic numbers don't trigger warnings. Patterns need to match structure and context.
English and Dutch
Both languages, held to the same standard.
Dutch-specific types like BSN, DigiD, and Dutch IBANs are validated against Dutch-language samples. English entity types are validated against English-language samples. Neither is treated as a second-class case.
Continuously improved
Updated by BeeSensible, never trained on your text.
The detection model is built and refined by the BeeSensible team. Text typed by your users is processed in memory and discarded, so it never reaches a training dataset.
Roll detection out per app.
Pick the AI tools and email apps your team uses most, assign a profile to each one, then add the rest when you're ready.