Masking when you paste, attach or send, and Keep context
What you see when BeeSensible masks for you as you paste, attach or send, which choice you have at that point, and how you still read the answer with the real values.
You can always mask a highlighted value yourself. In ChatGPT, Claude, Gemini and Copilot (copilot.com), BeeSensible can also do it for you at three moments: when you paste text, when you attach a file and when you send your message. With Keep context, you then read the real values in the answer while the AI tool only sees the placeholders. This article describes, for each moment, which AI tools it works in, what you see on your screen and which choice you have. Your settings show which of these features are on for you.
When pasting
If you paste text in which BeeSensible finds sensitive data, Masking what you paste appears above the text field. It shows, on each value found, the placeholder that will take its place, such as [NAME1]. You choose Paste masked, Paste original or Cancel. To skip this step from now on, tick From now on paste masked right away. If your organisation has chosen to always paste masked right away, you do not see the Paste original button.
If the check fails, for example because detection does not respond, BeeSensible does not paste anything by itself. You then choose between Paste anyway and Cancel.
Transcript
On screen: Heading: "Sensitive data in pasted text". A browser window with ChatGPT at chatgpt.com; the BeeSensible extension icon sits on the right of the address bar. In the conversation the user asks: "I have notes from a customer call. Can you summarize them?" ChatGPT replies: "Sure. Paste the notes below." Next to it a document "Customer call notes" appears with the text: "Lucía Ortega called about her refund to DE89370400440532013000. Her passport number is NV4837291. She can be reached at +31 6 12345678." The text is selected and the label "Copied" appears.
Sensitive data often ends up in an AI tool because you paste text into it, such as part of an email or a customer file.
On screen: Heading: "When an AI tool receives the text", with the label "The risk". The text is pasted into the ChatGPT text field. The name and the phone number get a yellow line underneath, the IBAN and the passport number a red one. At the same time the four details fly from the text field to the address bar, with the label "Already on its way to the AI tool". Next to the send button it says "Send not clicked yet".
Some AI tools already send what is in the text field before you click send, so masking it afterwards comes too late.
On screen: Heading: "Checking before pasting", with the label "When to mask". The same text is pasted again. The text field stays empty and a BeeSensible panel appears above it: "BeeSensible is checking what you paste", with "Esc to cancel". The panel then shows "4 sensitive details found in what you paste" and "Nothing is in the text field yet. This is how it goes in when you paste masked." Below that is the text with placeholders: "[NAME1] called about her refund to [IBAN1]. Her passport number is [PASSPORT1]. She can be reached at [PHONE1]."
With masking when pasting, BeeSensible first checks what you paste, and only then does the text go into the text field.
On screen: Heading: "Pasting masked or the original", with the label "When pasting". The view zooms in on the panel. At the bottom are the buttons "Paste masked", "Paste original" and "Cancel", and a checkbox "From now on paste masked right away". The pointer moves over "Paste masked" and "Paste original".
Above the text field you see what was found, with a placeholder in place of each detail, and you choose whether to paste the masked text or the original.
On screen: Heading: "Pasting masked straight away", with the label "Paste right away". The checkbox "From now on paste masked right away" is ticked, and then "Paste masked" is clicked. The panel closes and the text field now holds the text with the placeholders.
If you do not need that step, tick the box to paste masked text straight away from now on.
On screen: Heading: "What the AI tool receives", with the label "What it changes". The send button is clicked. The four placeholders fly to the address bar, with the label "This is what the AI tool gets". The new message in the conversation shows [NAME1], [IBAN1], [PASSPORT1] and [PHONE1] instead of the details.
When you send the message, only the placeholders go to the AI tool.
On screen: End card: the BeeSensible logo with the title "Masking when you paste".
When attaching
When you add a file in ChatGPT, Claude or Copilot (copilot.com), BeeSensible holds it back first and you see File held by BeeSensible. You then choose Check and mask, Add the original or Cancel. With Check and mask, BeeSensible opens the file under Documents in the sidebar. There you review the values found, and afterwards you add the anonymised copy to your message (see Redact a document). File types BeeSensible cannot check pass through unchecked.
Transcript
On screen: Heading: "A file is held first", with the label "When attaching". A browser window at chatgpt.com. The file "Student meeting report.pdf" is added to the text field and stays half transparent. A notice appears above it: "File held by BeeSensible. This PDF has not been added to the conversation yet. BeeSensible has not checked it."
When masking when attaching is on for you, BeeSensible first holds a file that you add to an AI tool such as ChatGPT.
On screen: Heading: "Three options", with the label "Your choice". Below the notice are the buttons "Check and mask", "Add the original" and "Cancel". The button "Check and mask" lights up and is clicked.
You then choose Check and mask, Add the original or Cancel.
On screen: Heading: "Anonymising the file", with the label "Documents". The BeeSensible side panel slides open on the right, on the "Documents" tab. It shows "Review before anonymizing" for Student meeting report.pdf, with three ticked findings: Esmee van der Wal, Femke Brouwer and 111222333, the last one with the label "Critical". "Anonymize (3)" is clicked.
Check and mask opens the file under Documents in the side panel. You see what was found, and you anonymise the file.
On screen: Heading: "Adding the anonymised copy", with the label "The copy". The side panel shows "Anonymized documents" with the file "Student meeting report_anonymized.pdf" and "3 items anonymized". Under "Add to chat as" are the buttons "File" and "Text". "File" lights up, and the anonymised copy then appears by the ChatGPT text field.
You then add the anonymised copy to the conversation. File types BeeSensible cannot check pass through unchecked.
On screen: End card: the BeeSensible logo with the title "Masking when you attach".
When sending
When you send a message in ChatGPT, Claude, Gemini or Copilot (copilot.com), BeeSensible turns everything still highlighted into a placeholder before the message goes, so you see those values as placeholders in your message. If the check of your last few words is still running, BeeSensible waits for at most two and a half seconds. If no result arrives in that time, your message goes through as it is.
Transcript
On screen: Heading: "Highlights as you type". A browser window with ChatGPT. In the conversation the user asks: "Can you help me with a customer email?" ChatGPT replies: "Of course. What should it say?" Someone types in the text field: "Rewrite this as a customer email: Lucía Ortega, passport NV4837291, gets her allowance from next month. Questions? Call +31 6 12345678." The name and the phone number get a yellow line underneath, the passport number a red double line. The BeeSensible tab on the right edge of the window shows the number of highlights, 3.
BeeSensible marks sensitive data as you type. Masking every detail yourself takes time, and it is easy to press Enter before you have checked everything.
On screen: Heading: "Turning on When sending", with the label "When to mask". The text field is cleared. The BeeSensible tab is clicked and the side panel opens on the "Privacy" tab, showing "No sensitive items detected". Then the gear icon is clicked and "Settings" opens. The panel scrolls to the section "When to mask": "You can always mask by hand. Below you choose when BeeSensible does it for you." Below that are the switches "When pasting" and "When sending". Under "When sending" it says: "Everything still detected becomes a placeholder the moment you send. After that your message goes through." That switch is turned on and the panel is closed.
You can leave the masking to BeeSensible instead. In the settings of the side panel, under When to mask, turn on When sending.
On screen: Heading: "What happens when you send", with the label "When sending". The same message is typed again and Enter is pressed. Above the text field "BeeSensible is checking your message" appears briefly. Then the field shows [NAME1], [PASSPORT1] and [PHONE1] in place of the details, with a dotted line underneath, and the message is sent.
You then type as usual. When you press Enter, BeeSensible checks your message and turns everything it finds into a placeholder before the message is sent.
On screen: Heading: "What was masked", with the label "What it changes". The view zooms in on the sent message with the placeholders, with the label "3 details masked" above it. ChatGPT replies: "Dear [NAME1], Good news: your allowance starts next month. Any questions? Call us on [PHONE1]."
The sent message shows which details were masked.
On screen: End card: the BeeSensible logo with the title "Masking when you send".
Keep context
When you mask a name, the AI tool sees a placeholder instead of the name and uses that placeholder in its answer as well. If Keep context is on, BeeSensible puts the real name back in the answer on your screen, with a dotted underline. The placeholder then gets a code for the conversation added to it, for example [NAME1-K7]. BeeSensible remembers on your device which value belongs to that placeholder, and the same value keeps the same placeholder throughout the conversation, so the AI tool can keep track of who or what it is about. The AI tool itself only ever sees the placeholder. Keep context works in ChatGPT, Claude, Gemini and Copilot (copilot.com), and under Works in you choose for each AI tool whether it is on.
Transcript
On screen: Heading: "Placeholders in the answer". A browser window with a ChatGPT conversation. The user asks: "Summarise the note about [NAME1] for the mentor meeting." ChatGPT replies: "[NAME1] was late four times in the past three weeks and missed two tests. Mother [NAME2] can be reached on [PHONE1]."
Sensitive details often give an AI tool the context it needs, such as the names in a report about a student. If you mask them, the answer is full of placeholders.
On screen: Heading: "Turning on Keep context", with the label "Settings". The window darkens and an enlarged setting from the extension appears: the switch "Keep context" with the label "Beta". Below it: "Masked details are back in place in the answer, on your screen only. When you mask something in a prompt, BeeSensible remembers which placeholder stands for which value, on this device only. The AI tool only ever sees the placeholders." The switch is turned on. A line "Works in" appears with ticks next to ChatGPT, Claude, Gemini and Copilot, followed by the note: "Restored details are marked with a dotted line. Conversations you share or export from the AI tool keep the placeholders."
With Keep context, BeeSensible puts the real details back in the answer. You turn it on once in the settings.
On screen: Heading: "The real details in the answer", with the label "In the answer". Someone types in the text field: "Email Femke Brouwer: the mentor meeting about Esmee van der Wal moves to Thursday. Call her on +31 6 12345678." The two names and the phone number get a line underneath. After Enter they become [NAME1-K7], [NAME2-K7] and [PHONE1-K7] and the message is sent. The sent message and the ChatGPT answer show the real names and number, underlined with a dotted line: "Dear Femke Brouwer, The mentor meeting about Esmee van der Wal moves to Thursday. If that does not suit you, we will call you on +31 6 12345678." Next to it a card "What ChatGPT gets" shows the same answer with the placeholders, with the label "On this device only".
You mask as you normally would, and the AI tool only receives the placeholders. In the answer you read the real names, underlined with a dotted line. BeeSensible keeps track of which placeholder belongs to which detail on your device only.
On screen: Heading: "Switching and copying", with the label "Conversations". The ChatGPT sidebar opens with the chats "Mentor meeting email", "Lisbon day plan", "Quarterly figures summary" and "Team outing ideas". The view switches to "Lisbon day plan" and then back to "Mentor meeting email"; the real details are still there. The answer is copied, and a card "Pasted into your email" shows the text with the real names and phone number.
The real details stay in place when you switch to another conversation and come back, and when you copy the answer.
On screen: Heading: "The AI tools it works in", with the label "Works in". The window darkens and the logos of ChatGPT, Claude, Gemini and Copilot appear side by side.
Keep context works in ChatGPT, Claude, Gemini and Copilot on copilot.com, and you choose for each tool whether it is on.
On screen: End card: the BeeSensible logo with the title "Keep context".
Good to know about Keep context
- The memory holding the real values is kept on your device only. By default it is cleared when you close the browser or sign out, or after a day. If your organisation has chosen a retention period of 30 days, it is cleared when you sign out or have not used it for 30 days.
- If you copy text from the answer, you take the real values with you. If you share or export the conversation from the AI tool, it contains placeholders.
- Keep context does not work in Microsoft 365 Copilot or in the desktop app.
What an AI tool cannot do with placeholders
- An AI tool cannot calculate with a placeholder. If you ask how old
[AGE1]will be in three years, the answer is[AGE1] + 3. With an ID number, IBAN or email address you lose nothing as a result, but with an age, amount, date or place the answer can become less useful. - An AI tool does not know who
[NAME1]is. It therefore avoids words such as "he" and "she", which can make the answer read a little stiffly. - An AI tool does not always leave placeholders intact when translating. Copilot sometimes translates them too, and BeeSensible does not restore a translated placeholder.
Where to find the switches
Open the side panel and go to Settings. Under When to mask you find the switches When pasting, When attaching and When sending, with Keep context below them. A switch that is off and not locked is one you can turn on yourself.
Why can't I see this switch?
Your organisation decides for each feature whether you see the switch and whether you can change it yourself:
| What you see | What it means |
|---|---|
| No switch | Your organisation has turned the feature off. |
| The switch is off | You can turn the feature on yourself if you want to. This is the default for masking. |
| The switch is on | Your organisation has turned the feature on for you, and you can turn it off. If you have changed it yourself before, your choice is kept. |
| The switch is on and locked | Below it you see "Set by your organisation". Your organisation wants the feature to be on at all times. |
For ChatGPT, Claude and Gemini, your organisation can choose a different setting for each tool than for the rest. A feature can therefore be on in one AI tool and off in another. Masking when you attach also only works if your organisation uses document anonymisation. If you would like to use a feature you cannot see, ask your admin.
Masking for admins explains what your admin sets for these features.
Last updated:
