Data Handling Rules for Prompts
Define what may be pasted into AI tools and how to mask the rest.
Added October 15, 2026. Written with AI assistance and checked for clarity and placeholders; not reviewed by a lawyer, accountant, clinician or other professional. How these prompts are made
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it (what [VERIFY] means).
Write data handling rules for using AI tools in [TEAM_OR_FUNCTION]. Data categories we hold: [DATA_CATEGORIES]. Tools approved: [APPROVED_TOOLS]. Customers' expectations: [CUSTOMER_EXPECTATIONS]. Create a three-level table: green (may paste), amber (mask first), red (never paste), with examples of each drawn from my categories. Give masking techniques with before and after examples using invented data: replace names with roles, round numbers, remove identifiers, summarise instead of pasting. Add a pre-paste checklist of five questions, instructions for what to do after pasting something by mistake, and a training exercise with six sample snippets to classify. Legal duties on personal data are [VERIFY] for [JURISDICTION]. Also address screenshots, uploaded files and voice recordings, which people often forget are data too, and explain what to do with tool history and shared conversation links, including how to delete them where the tool allows. Close with a short script a team lead can read in a meeting to explain the three levels, followed by a one-line reminder to print or pin beside each person's desk.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Claude, Gemini, ChatGPT or another assistant.