Spell-check for privacy
Documentation Changelog
Realtime Privacy

How Realtime Privacy works

What the coloured highlights mean and what you can do about them.

Draft message

Hi team, Ingrid Lindqvist will be joining the project. Her contact is NL91 ABNA 0417 1643 00.

Warning
Names, emails, phone numbers
Critical
IBANs, BSNs, credit cards, API keys
Yellow marks a warning-level finding. Red marks a critical one. Both are yours to handle.

Realtime Privacy is the part of BeeSensible you see every day. As you type or paste in an AI tool, email, or chat, it underlines sensitive data before you send it, so you can decide what to do.

What you see

A coloured underline appears under sensitive data as you write:

  • Yellow is a warning, for regular data like a name or an email address.
  • Red is critical, for data like an IBAN or a national ID.

BeeSensible never blocks sending and never changes your text on its own. The choice is always yours. See Yellow and red highlights for what each colour covers.

What you can do

Click a highlight and pick one of three actions:

  • Replace the value with a realistic placeholder.
  • Mask it with a label like [NAME].
  • Remove it.

You can also apply your choice to everything at once. See Review detections and replace, mask, or delete for the full walkthrough.

Where it works

BeeSensible works in Chrome and Edge across AI tools, email, chat, and other supported sites. If your organisation uses the desktop app, the same highlights also appear in native apps like Outlook desktop.

Your text stays private

Through the desktop app, detection runs on your own device. For browser-only use, the text is checked in EU memory and discarded straight after. Nothing you type is stored.