AI prompt to use ChatGPT safely at work

Good results from AI depend on clear prompts, the right tool for the job and protecting client data. These guides help agents and staff use AI safely and effectively.

Below is a ready-to-copy prompt to use ChatGPT safely at work, a detailed version that asks you clarifying questions first, and tips for using it. It works in any AI assistant: ChatGPT, Claude, Gemini or Copilot.

Try it in the search box ›

The prompt

List 10 rules for using AI assistants safely at an insurance agency (no client PII, verify facts, compliance review for marketing, don't rely on AI for coverage decisions) and explain each in one sentence.

Detailed version (asks clarifying questions first)

Act as an experienced assistant to a licensed insurance agent. Before answering, ask me up to 3 clarifying questions (your role, the AI tool you use and what you want to achieve). Then complete this task, and finish with a short checklist of statements I should verify with my compliance team.

Task: List 10 rules for using AI assistants safely at an insurance agency (no client PII, verify facts, compliance review for marketing, don't rely on AI for coverage decisions) and explain each in one sentence.

What a good result looks like

Good rules are short, specific and easy to remember: never paste client personal information, check facts before using them, send marketing through compliance review, and don't let AI make coverage decisions. Each rule gets one sentence explaining why.

Common mistakes and watch-outs

Don't treat the AI's list as your agency's policy; check it against your carrier contracts, privacy obligations and any broker-dealer rules. Settings matter too: business versions of AI tools may handle data differently from free personal accounts, so check before you choose one.

How to adapt the prompt

Add rules for the tools you actually use, such as AI note takers or receptionist bots. Turn the list into a one-page poster for the office, and pair it with your AI use policy and the protect-client-data page.

EXAMPLE output (placeholder data, not a real client)

10 rules for using AI safely at [Agency Name]

1. Never paste client personal information. Use placeholders.
2. Verify every fact, number and date before using it.
3. AI doesn't decide coverage; licensed staff do.
4. Marketing content goes through compliance review.
5. Use only agency-approved AI tools.
6. Don't upload policy documents with personal details.
7. Be clear with clients when they're talking to an automated system, where required.
8. Save prompts that work; share them with the team.
9. Report mistakes so we can fix the process.
10. When unsure, ask [Policy Owner].

How to use it

Copy the prompt. Copy the short prompt above, or the detailed version if you want the AI to ask clarifying questions first.
Add your details. Add the details for your situation (line of business, audience, tone). Keep it de-identified; never paste client personal information.
Run it in the right tool. Paste it into any AI assistant: ChatGPT, Claude, Gemini or Copilot.
Review before you use it. Have compliance or legal review the final policy before you roll it out. Check every fact, name and number yourself.
Take the next step. Next, see: Protect client data when using AI.

Which AI tool to use

Any AI assistant

ChatGPT Claude Google Gemini Microsoft Copilot

Paste the prompt above (short or detailed) into any of these.

Before you use it

Have compliance or legal review the final policy before you roll it out.
Check what each AI tool does with your data (training, retention) before staff use it.
Never paste client personal information (names, policy numbers, health or financial details) into AI tools your agency hasn't approved.
Review every AI output for accuracy and compliance before you use it.

Was this page helpful?