See sensitive data before you send it.
BeeSensible marks names, IBANs, BSNs and 65 data types while you type, in AI tools, email, and chat. You decide what to do with each one. It never changes your text on its own and never blocks sending.
ClaudeThe method
The same four steps, now for sensitive data.
Every BeeSensible module follows this cycle. Here is what it looks like for the data your people type and paste.
Where sensitive data shows up
Which kinds of data pass by, in which apps, and how often. Aggregated, never the text itself and never per person.
What counts as how sensitive
Per detection profile you set which of the 65 data types are recognised, and whether something is standard or critical. You attach that profile to the apps where it applies.
A marking while you type
What is sensitive gets a marking as someone types. Replace, mask, or remove, in one click. The text never changes by itself.
What happens to the markings
How much gets fixed before anything leaves, and what is sent anyway. The figures you substantiate your policy with.
and again How the cycle works
See where sensitive data shows up.
Aggregated, never individual. Which platforms create the most exposure, how much your team handles before sending, and when it happens.
Adjusted, or sent anyway.
Every marking is counted with its outcome: replaced, masked, removed, or sent despite the warning. That last figure is the honest one: it shows where the advice is not followed, per app and per data type. It is what substantiates data minimisation at the moment of input, and it shows where a profile should be stricter or can be calmer.
Replace, mask, or remove. One click.
Each marking becomes a choice in the panel. Replace a name with a realistic stand-in so the prompt still reads naturally, mask it behind a placeholder, or remove it entirely. Apply it once, or to every match in the field.
Gemini
Bombus, our best engine yet.
Since July 2026, Bombus 2.1 is the standard engine behind BeeSensible, on-device and in the EU cloud alike. A smart combination of fast AI techniques and hard rules, working as one judgement. It builds on Osmia 3.3, our earlier detection engine, and reads sharper: higher recall and stronger on structured data like IBANs and medical codes. On our internal benchmark it scores roughly 96% F1, across all 65 data types, in Dutch and English.
How it works
On your own device. Or in the EU.
With the desktop app, the detection runs on the machine itself, so the text never leaves it. Prefer no install? Detection runs in EU working memory and is discarded right away.
Dear Eva Eriksson,
Someone types
in ChatGPT, email or a document
On device or in the EU cloud
the engine runs on the machine, or in EU memory wiped right after
Check your policy
aggregated numbers for analysis and compliance
Across the apps you already use
AI tools like ChatGPT and Claude, email in Gmail and Outlook, chat in Slack: 18 apps in the browser. The desktop app adds Outlook, ChatGPT, Claude, and Copilot as native apps on macOS and Windows.
Three actions, always yours
Replace with a realistic stand-in, mask with a placeholder, or remove it. One click, or apply to every match in the field.
Nothing is stored
Detection runs on the user's own machine or in the EU, in working memory. The text itself is never stored either way.
Try it on your own text.
Install the extension, open ChatGPT or Gmail, and see what gets marked before anything is sent.