Protect sensitive data while your team works with AI.
BeeSensible highlights details such as a customer name, ID number or account number in the text. People can mask them before sharing anything, in the tools they already use. That way, help arrives at the very moment they put their training into practice.
Prefer to try it yourself? 14 days free, no credit card.
ChatGPTHighlights in ChatGPT. Demonstration with fictional data; click a highlight.
The AI tool gets the question, not the person.
What the employee types
Write a reply to Ingrid Hansen, SSN 078-05-1120. The refund to card 4532 1234 5678 9010 is on its way.
What the AI tool receives
Write a reply to [NAME1], SSN [SSN1]. The refund to card [CARD1] is on its way.
Product example with fictional data, not a test result.
In our own testing, BeeSensible recognised 95 out of every 100 sensitive details.
People no longer have to strip sensitive details out of their text by hand. BeeSensible finds them: names, ID numbers, account numbers, addresses and medical details, in Dutch and English. One click masks them, or masking happens automatically when someone pastes or sends. Your team can use AI to the full and sees straight away what is sensitive.
How we measure this
Measured with Bombus, BeeSensible's detection engine, on 824 synthetic test documents covering all 65 data types, in Dutch and English. The test set is fixed and was not used for tuning. The F1 score is 0.96. Without BeeSensible, nothing is recognised automatically. The figure shows what the detection finds, not how many data breaches are prevented. How we test the detection
Help right in the text, while people work.
Someone pastes a customer email into ChatGPT to draft a polite reply. The ID number and account number in it are easy to miss.
BeeSensible recognises 65 types of sensitive data and your own terms, such as project and client names, as people type or paste: yellow for standard, red for critical. People can mask a detail with a placeholder such as [SSN1], remove it or leave it as it is. This works in AI tools such as ChatGPT, Claude, Gemini and Copilot, and in email and chat.
The AI tool gets what it needs to answer, without the person behind it. You decide how warnings and masking are set up; the documentation describes the options.
When pasting
Pasted text is checked before it appears in the field. People see what was found and choose to paste it masked, paste the original or cancel.
When sending
If something is still highlighted when someone presses Enter, it can be swapped for a placeholder as the message is sent.
Keep context
The AI tool only sees placeholders. The real details reappear in the answer, and only on the employee's own screen.
Custom terms
Names that only mean something inside your organisation, such as projects and clients, are highlighted like any other sensitive detail.
Share files with an AI tool or outside the organisation, without the sensitive details.
Not everything sensitive is typed. An intake report, a CV or a contract gets attached to a chat as a file, or forwarded.
Open the file in the dashboard or the extension: PDF (including scans), Word, Excel, PowerPoint, images and plain text. Everything found is ticked; the employee reviews it, draws an extra box where needed and exports an anonymised copy in the same format. Comments, tracked changes and metadata are checked and cleaned as well. With Mask on attach switched on, BeeSensible holds back a file you add in ChatGPT or Claude first. You can then check and mask it, attach the original or cancel.
The document that goes out contains only what belongs in it. After anonymising, BeeSensible reads the result back and warns you if anything was missed. In the desktop app, this works for PDF.
Documents in the dashboard. Demonstration with fictional data.
A file held back in ChatGPT. Demonstration.
Anyone who opens an AI tool sees what the organisation has decided.
In the middle of a task, a policy on the intranet isn't always to hand.
When someone opens a tool you've made a decision on, that decision appears in the browser. For DeepSeek: not allowed, with a button to Microsoft 365 Copilot as the first option. For a tool with limited use: the condition, in your own words. For a tool with no decision yet: a low-key note, if you want one.
The decision reaches people when it matters, with the alternative one click away. Whether someone can still continue is up to you. BeeSensible doesn't block anything by itself.
DeepSeek is not allowed here
Your organisation does not allow this tool for work. Use an allowed alternative.
Try the three notices. Demonstration with fictional data.
Building on training
What people learn in training comes back to them while they work.
Training lays the groundwork: what counts as sensitive, which tools are allowed and why. BeeSensible brings that knowledge back when people need it, right in the text they're working on.
In the text itself
Highlights appear where people work: in the AI tool, their email or their chat.
People choose what to do
Mask it, remove it or leave it, within your organisation's settings. A highlight is a reminder, not a ban.
See what sticks
In totals: how often sensitive details are adjusted before sending, and what happens after a notice. Useful for fine-tuning your training.
Trust and getting started
Your data stays safe, and getting started is quick.
What happens to your data
- Text is checked on our own servers, hosted by the European companies Scaleway and Hetzner, and deleted straight away.
- The dashboard shows totals for the whole organisation, never a breakdown by employee. Figures only appear once five or more users are active.
- You get a data processing agreement (DPA). The product DPIA and security information are available on request.
How to get started
- Install the extension on a few workstations, or have IT roll it out centrally through Intune or Group Policy, on any plan.
- Employees get an explanation and short videos about what they'll see and what they can do.
Try it on your own AI tools.
Your team keeps working as usual and sees highlights from day one. Prefer to see it in your own tools first? Book a demo.
14 days free, no credit card. Rolled out across your organisation within an hour.
