Quick answer Prompt redaction advice covers what you type, not what you upload. When a full PDF, a case file, a contract, gets pasted or attached to an AI tool, the names, dates of birth, and account numbers inside it go with it, in one step, with no highlight to catch them. BeeSensible's desktop app opens the PDF first, marks the sensitive fields on the page, and produces a clean copy to share or paste in, before any of it reaches an AI tool.
A caseworker has a ten-page PDF and wants a two-line summary. She opens ChatGPT, uploads the file, and asks for the highlights. Done in ten seconds.
That file had a client's full name, date of birth, national ID number, and a paragraph about a family situation that was never meant to leave the case management system. None of it was typed. It went in as one upload, in one step, with nothing to catch it.
#The advice you have read is about typing, not uploading
Guides on safe AI prompts tell you to remove names, replace identifiers, mask account numbers. Good advice, and BeeSensible's own browser extension is built around exactly that moment: the text field, while you type, before you send.
But a PDF upload does not go through a text field. The whole document goes in at once, formatting and all. Whatever prompt-hygiene habit you have built for typed text does not apply, because there was no typing to catch.
#What is actually in that file
A single case file, contract, or report routinely carries more personal data than a week of typed prompts combined: full names, dates of birth, national ID numbers, medical codes, account numbers, addresses, the names of people who are not even the subject of the file but show up in a paragraph about them.
None of that is unusual. It is what a normal working document looks like. The problem is only that none of it gets a second look before it goes into a tool that was never asked to keep it confidential.
#Redacting the document, not the prompt
BeeSensible's desktop app (macOS and Windows) is built for exactly this moment. Open a PDF, and the sensitive fields on the page are marked, with the most sensitive ones, national ID numbers, financial details, called out more strongly than the rest.
You uncheck anything that should stay, draw a box by hand over anything the detection missed, and export a clean copy. Hidden document metadata is stripped in the same step, so nothing leaks through the file's properties either.
This is PDF only today. Word documents, Excel spreadsheets, images, and scanned PDFs are not supported yet, so a photographed page or a spreadsheet with sensitive columns still needs a human eye. Where the document is processed follows the same on-device or EU-cloud setting as the rest of BeeSensible: on-device, the file never leaves the machine.
A redacted PDF is safer to share regardless of where it ends up. But which AI tool it ends up in is its own question, and organisations increasingly cannot answer it for every tool their people have opened.
A clean document pasted into a tool your organisation has never assessed is a smaller problem than an unredacted one, but it is still a decision worth making on purpose rather than by default.
#Prompt hygiene and document hygiene are the same discipline
Typed text and uploaded files are two different moments with the same underlying risk: personal data reaching a tool before anyone looked at what was actually in it. Treating only one of those moments as the risk leaves the other wide open.
Redact the document. Watch the prompt. Neither one covers what the other does.
ChatGPT
