AI prompt to measure marketing ROI by channel

Consistent, helpful content keeps an agency visible in its community and builds trust before anyone needs a quote. AI drafts posts, emails, videos and web copy quickly, so an agent can publish regularly without a marketing team.

Below is a ready-to-copy prompt to measure marketing ROI by channel, a detailed version that asks you clarifying questions first, and 1 specialized AI tool (HubSpot) with instructions for this task. It also works in ChatGPT, Claude, Gemini or Copilot.

Try it in the search box ›

The prompt

Using these de-identified numbers by lead source (spend, leads, quotes, sales), calculate cost per lead and cost per sale, and suggest where to shift budget. Data: [paste]

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 audience, the channel and your agency's voice). Then complete this task, and finish with a short checklist of statements I should verify with my compliance team.

Task: Using these de-identified numbers by lead source (spend, leads, quotes, sales), calculate cost per lead and cost per sale, and suggest where to shift budget. Data: [paste]

What a good result looks like

A good analysis calculates cost per lead and cost per sale for each source from your de-identified numbers, shows the results in a simple table and suggests budget shifts based on those numbers, with a note on what else to check before deciding.

Common mistakes and watch-outs

Check the math: AI tools can make arithmetic mistakes, so recalculate key figures in a spreadsheet. Small samples can mislead; one good month doesn't make a channel the winner. Consider retention and policy value too, not just cost per sale. Use only totals, not client lists.

How to adapt the prompt

Add columns for premium or commission per sale to estimate return, and compare several months. HubSpot reports can supply the source data if you track lead sources there.

EXAMPLE output (placeholder data, not a real client)

Lead source analysis - [Quarter]

| Source | Spend | Leads | Sales | Cost/lead | Cost/sale |
| Internet leads | [Amount] | [Number] | [Number] | [Amount] | [Amount] |
| Referrals | [Amount] | [Number] | [Number] | [Amount] | [Amount] |
| Events | [Amount] | [Number] | [Number] | [Amount] | [Amount] |

Suggestions:
- Referrals have the lowest cost per sale: ask for referrals at every renewal.
- Check event results over two more quarters before cutting the budget.

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.
Fill in the placeholders. Replace [paste] with your own details. Use placeholders or de-identified details; never paste client personal information.
Run it in the right tool. Paste it into ChatGPT, Claude, Gemini or Copilot, or use HubSpot as described below.
Review before you use it. Use aggregated numbers, not individual client records, when you analyze results with AI. Check every fact, name and number yourself.
Take the next step. Next, see: Summarize monthly agency numbers.

Best AI tools for this task

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

HubSpot site ↗

CRM and marketing platform with AI features.

How to use it

Pull lead source reports from HubSpot to fill in the numbers.

Any AI assistant

ChatGPT Claude Google Gemini Microsoft Copilot

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

Before you use it

Use aggregated numbers, not individual client records, when you analyze results with AI.
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?