# Using AI safely with customer data: what to leave out and who checks > A free one-page cheat sheet on AI and customer data: what never to paste, how to redact, data controls, Temporary Chat and human review. Source: https://learn.ynteractive.com/content/cheat-sheets/ai-customer-data-safety · Updated 2026-10-01 · Free from Stepthrough (https://learn.ynteractive.com) [Topic cheat sheet](https://learn.ynteractive.com/content/cheat-sheets#kind-topic) · One page · US letter · [ChatGPT](https://learn.ynteractive.com/content/tool/chatgpt) · [n8n](https://learn.ynteractive.com/content/tool/n8n) By [Robert Breen](https://learn.ynteractive.com/content/about) · Published October 1, 2026 · From the free lesson [Reply Faster: Turn a Messy Customer Email Thread into a Clear, Friendly Reply](https://learn.ynteractive.com/content/chatgpt-reply-to-customer-emails) A free one-page cheat sheet on AI and customer data: what never to paste, how to redact, data controls, Temporary Chat and human review. [Download the free PDF (72 KB)](https://learn.ynteractive.com/content/cheat-sheets/ai-customer-data-safety.pdf)Print this sheet Free, no sign-up and no email needed. It prints on one letter-size page; the whole sheet is below. *▶*StepthroughFree printable cheat sheet · learn.ynteractive.com Using AI safely with customer data: what to leave out and who checks Most AI tasks don't need the private parts of a customer's email, and leaving them out costs nothing in quality. ## Leave it out before you paste - **PII** is information that can identify a specific person, alone or combined with other details. - Never paste account and card numbers, Social Security and tax IDs, dates of birth, license numbers or health details. - Drop full names or addresses the reply doesn't need. The test is not "no personal details ever", it is "only the details this reply needs". - Write a short facts list yourself instead of pasting whole records. ## Redact in three steps 1. Search the text for long numbers and @ signs before you paste. 2. Swap what you remove for clear placeholders like `[CLIENT]` or `[ACCOUNT]`, so the AI knows something was removed. 3. Put the real details back in yourself, in your email app, after the AI step. ## Settings that help, and their limits **Data controls** In ChatGPT's Settings, turn off **Improve the model for everyone** so chats on a personal account aren't used for training. **Training off** Doesn't mean private. Chats are still processed and stored to run the service. **Temporary Chat** Skips history and memory and isn't used for training. Turn it on before you paste. The data still goes to OpenAI. ## People stay in charge **Human in the loop** A person reviews AI work before it reaches a customer. Make it structural, like an n8n Gmail tool set to **Draft** only. **AI use policy** Approved tools and plans, data that never goes in, allowed uses, and the review step before anything goes out. **Hiring notes** Score against job-related must-haves with a quote as evidence. Tell the AI: "Don't guess at age, family, health, religion or anything else that isn't job-related." **Remember:** Send the AI only what the task needs, and have a person check the result before it reaches anyone. Your company's policy and industry rules come first. **Have a professional review it.** This prompt helps you draft, not decide. AI can get the law wrong and doesn’t know your jurisdiction or your facts, so have a licensed attorney review anything legal before you send or sign it. Practice it free: [Reply Faster: Turn a Messy Customer Email Thread into a Clear, Friendly Reply](https://learn.ynteractive.com/modules/chatgpt-reply-faster) at learn.ynteractive.com/modules/chatgpt-reply-faster. This sheet: learn.ynteractive.com/content/cheat-sheets/ai-customer-data-safety. Businesses in the lesson examples are made up. By Robert Breen, October 1, 2026. ## Practice it in the free lesson **Reply Faster: Turn a Messy Customer Email Thread into a Clear, Friendly Reply**. Turn a messy customer email thread into a clear, friendly reply: give ChatGPT the thread and your facts, check every promise, fix the tone, and send it from Gmail. You do every step yourself in a practice copy of ChatGPT, it checks your work as you go, and “Do it for me” finishes any step you get stuck on. Free, and nothing touches your real accounts. [Start the free lesson](https://learn.ynteractive.com/modules/chatgpt-reply-faster) [Or read the full step-by-step guide](https://learn.ynteractive.com/content/chatgpt-reply-to-customer-emails) ## Lessons on this sheet - [Reply Faster: Turn a Messy Customer Email Thread into a Clear, Friendly Reply](https://learn.ynteractive.com/content/chatgpt-reply-to-customer-emails): Turn a messy customer email thread into a clear, friendly reply: give ChatGPT the thread and your facts, check every promise, fix the tone, and send it from Gmail. - [AI Email Responder: Draft Gmail Replies Automatically with n8n](https://learn.ynteractive.com/content/ai-email-responder-gmail-drafts-n8n): Build an n8n agent that watches your Gmail, reads each new customer email, and writes a reply as a draft in the same thread, ready for you to check and send. - [Turn an Interview Debrief into a Scorecard and a Candidate Follow-Up (Recruiting & HR)](https://learn.ynteractive.com/content/chatgpt-interview-debrief-scorecard): Turn the transcript of an interview panel's debrief into a scorecard against the role's must-haves, the decisions, action items with owners and dates, and a follow-up… ## Related terms Plain-English definitions, each with an example from a free lesson. [Personally identifiable information (PII)](https://learn.ynteractive.com/content/glossary/pii) · [Redaction (masking private details)](https://learn.ynteractive.com/content/glossary/redaction) · [ChatGPT data controls](https://learn.ynteractive.com/content/glossary/chatgpt-data-controls) · [Temporary Chat](https://learn.ynteractive.com/content/glossary/temporary-chat) · [AI acceptable use policy](https://learn.ynteractive.com/content/glossary/ai-acceptable-use-policy) · [AI bias](https://learn.ynteractive.com/content/glossary/ai-bias) · [Human in the loop](https://learn.ynteractive.com/content/glossary/human-in-the-loop) · [Action](https://learn.ynteractive.com/content/glossary/action) [The full AI glossary](https://learn.ynteractive.com/content/glossary) ## Related prompts - [Staff AI use policy prompt](https://learn.ynteractive.com/content/prompts/ai-use-policy-draft-prompt): Draft a short staff policy for AI tools at work: approved tools, what never goes in, what a person must check and who to ask… - [AI agent system message prompt](https://learn.ynteractive.com/content/prompts/agent-system-message-draft-prompt): Draft the system message for an n8n AI Agent: who it is, what it knows, its rules and how it writes, including a rule never to… - [Billing question reply prompt](https://learn.ynteractive.com/content/prompts/billing-question-reply-prompt): A ChatGPT prompt for "why was I charged this?" emails: the charge, the correct amount, the reason, the fix as simple math, and… - [Check reply promises prompt](https://learn.ynteractive.com/content/prompts/check-reply-promises-prompt): A ChatGPT prompt that checks a draft before you send it: a table of every promise, the fact behind each, and safer wording for… [All free prompt templates](https://learn.ynteractive.com/content/prompts) ## More cheat sheets - [AI Email Responder in n8n Cheat Sheet](https://learn.ynteractive.com/content/cheat-sheets/ai-email-responder-n8n): A free one-page cheat sheet: n8n watches Gmail, an AI agent reads each customer email and saves a reply as a draft in the same thread. - [Interview Debrief Scorecard Cheat Sheet](https://learn.ynteractive.com/content/cheat-sheets/interview-debrief-scorecard): A free one-page cheat sheet: score a candidate on each must-have with a quote as evidence, keep it job-related and write the follow-up email. - [AI Email Drafts Safety Cheat Sheet](https://learn.ynteractive.com/content/cheat-sheets/ai-email-drafts-safety): A free one-page cheat sheet: let AI write email drafts, not sends. Give it facts and rules, keep private data out and check every promise. [All free cheat sheets](https://learn.ynteractive.com/content/cheat-sheets) · [All free tutorials](https://learn.ynteractive.com/content)