Data Handling Rules for Assistants: What Goes In, What Stays Out
Write plain rules about the data an assistant may process.
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 staff and assistants at [ORGANISATION]. Types of data held: [DATA_TYPES]. Assistants and tools in use: [TOOLS_IN_USE]. Where data is processed and stored (as far as known): [DATA_LOCATIONS]. Obligations I know of: [KNOWN_OBLIGATIONS]. Create a three-level classification (can paste freely, paste only with approval, never paste) with examples from my data types, and what to do instead (summarise, anonymise, use synthetic data). Write a short policy in plain language (under 400 words) and a one-page quick guide for staff. Include an anonymisation checklist, rules for uploading files, rules for sharing outputs, and a procedure if someone pastes something by mistake (who to tell, what to record). Add training questions with answers. Highlight the questions I should put to each vendor about retention and training use of my data. Mark all legal and contractual points as [VERIFY] with legal or privacy counsel; this is not legal advice.
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.