AI prompt to protect client data when using AI

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 protect client data when using AI, 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

Explain how to de-identify information before using AI tools (remove names, addresses, policy numbers, DOBs), with 3 before/after examples, and when not to use AI at all. Follow your agency's data policy.

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: Explain how to de-identify information before using AI tools (remove names, addresses, policy numbers, DOBs), with 3 before/after examples, and when not to use AI at all. Follow your agency's data policy.

What a good result looks like

A good result gives you a simple, repeatable way to de-identify information before it goes into an AI tool: replace names with roles or initials, remove contact details and policy numbers, round or generalize sensitive numbers, and keep the facts the AI actually needs. It should end with a short checklist you can follow every time.

Common mistakes and watch-outs

The biggest mistake is assuming a tool is private because it requires a login. Check whether your AI tool stores or trains on what you enter, and use only tools your agency has approved. Health information, Social Security numbers and financial account details should never go into a general AI tool, even with names removed.

How to adapt the prompt

Add the data types you handle most (for example medical details for life and health, or driver records for auto) and the tools your agency approves. Turn the checklist into a one-page reference for staff and pair it with your AI use policy.

EXAMPLE output (placeholder data, not a real client)

De-identification checklist (before pasting into AI)

- Replace names: "Jane Smith" -> "Client A"
- Remove contact details: addresses, phone numbers, emails
- Remove identifiers: policy, claim and account numbers, SSNs
- Generalize: "born 03/14/1961" -> "early 60s"; exact address -> "suburban home"
- Keep only what the AI needs: coverage type, limits, the question you're asking
- Use only agency-approved AI tools

Example: "Client A, early 60s, has a homeowners policy with a [Amount] deductible and asks how a roof claim works."

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: Use ChatGPT safely at work.

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?