AI prompt to archive texts and emails for compliance

Insurance marketing and client communications are regulated, and records must be kept. AI can pre-check drafts for risky language and help organize compliance tasks, but it doesn't replace your compliance team.

Below is a ready-to-copy prompt to archive texts and emails for compliance, a detailed version that asks you clarifying questions first, and 2 specialized AI tools (Smarsh and Global Relay) with instructions for this task. It also works in ChatGPT, Claude, Gemini or Copilot.

Try it in the search box ›

The prompt

Draft an internal policy summary for staff on which client communication channels are approved and archived, in plain language.

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 (the type of content or record, the audience, and the rules you must follow). Then complete this task, and finish with a short checklist of statements I should verify with my compliance team.

Task: Draft an internal policy summary for staff on which client communication channels are approved and archived, in plain language.

What a good result looks like

A good staff summary says plainly which channels are approved for client communication (for example agency email, the archived texting platform), which are not (personal phones, personal social media messages), and what to do if a client contacts you on an unapproved channel.

Common mistakes and watch-outs

Requirements depend on your regulators: broker-dealer and investment rules can require retention of business communications, and carriers or states may add their own. Confirm with compliance before rolling it out. Archiving tools like Smarsh, Global Relay or FMG only help if staff actually use the approved channels.

How to adapt the prompt

Add the specific apps your agency uses, retention periods your compliance team confirms, and a short script for moving a client conversation to an approved channel.

EXAMPLE output (placeholder data, not a real client)

Client communication channels - [Agency Name] (summary)

Approved and archived:
- Agency email ([Domain])
- Agency texting platform ([Platform Name])
- Agency phone system

Not approved for client business:
- Personal cell texts or messaging apps
- Personal social media messages

If a client contacts you on an unapproved channel: reply once to move the conversation, for example "Thanks! I'll reply from our agency email so it's on file."

Questions: [Compliance Contact]

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 ChatGPT, Claude, Gemini or Copilot, or use Smarsh and Global Relay as described below.
Review before you use it. Follow your state, carrier and broker-dealer rules for record keeping and approvals. Check every fact, name and number yourself.
Take the next step. Next, see: Check marketing content for compliance.

Best AI tools for this task

Specialized tools first, ordered by fit for this task (never by payout), then any general AI assistant.

Smarsh site ↗

Capture, archiving and supervision of electronic communications across 80+ channels.

How to use it

Use Smarsh to capture and archive electronic communications across channels.

Global Relay site ↗

Compliant communications archiving, messaging, supervision and eDiscovery.

How to use it

Use Global Relay for compliant messaging, archiving and supervision.

Any AI assistant

ChatGPT Claude Google Gemini Microsoft Copilot

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

Before you use it

Follow your state, carrier and broker-dealer rules for record keeping and approvals.
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?