As of 13 August 2026, AI can analyse click-through rates in your email campaigns.

What to actually do

1. Hand it to a person

   The route this page recommends

   A person who owns the outcome does this end to end, worth it when the failure is dear.

2. Do it yourself

   Second choice

   A chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.

   How to actually do it

   1. Open your email platform's campaign reporting area and export the relevant campaigns as CSV, including delivered emails, total clicks, unique clicks, click-through rate, subject line, send date, audience segment and call to action where available.
   2. Copy the platform's definitions of delivered, clicked, unique clicks, click-through rate and click-to-open rate into a separate note, including whether the figures are total or unique.
   3. Add the campaign goal, audience, offer, send type and any known changes in the list, consent process, tracking links or landing page to the context section of the prompt.
   4. Paste the definitions and the export into the prompt, then ask the chatbot to produce the data checks, calculations, comparisons and proposed tests in the requested format.
   5. Compare every displayed rate and total with the original platform report, checking the denominator, rounding, campaign names and date range before accepting the findings.
   6. Ask a colleague who understands your email platform to check any unusual tracking or audience differences, then select one proposed test and record its hypothesis, comparison group and primary metric before sending it.

   Prompt

   Analyse the email campaign data below. Treat the supplied figures as the source of truth and do not invent missing values.
   
   Business context: [describe the audience, offer and campaign goal]
   Platform and metric definitions: [state how the platform defines delivered, opened, clicked, click-through rate and unique clicks]
   Date range: [insert date range]
   Campaign data:
   [paste the CSV or table here]
   
   Do the following:
   1. Check the columns, identify missing or inconsistent values, and say what cannot be concluded.
   2. Calculate or verify click-through rate using delivered emails as the denominator where that matches the supplied definition. Keep click-through rate, click-to-open rate, total clicks and unique clicks separate.
   3. Compare campaigns by subject line, send date, audience segment, send type and call to action where those fields exist.
   4. Highlight the strongest and weakest patterns, but distinguish description from explanation. Do not claim that one factor caused another.
   5. Flag small, uneven or otherwise unreliable comparisons and explain what additional data would improve them.
   6. Give three practical next tests, each with a hypothesis, one change, the comparison group, the primary metric and a condition for stopping or changing course.
   7. Present the result under these headings: Data checks, Metric checks, Findings, Limits, Recommended tests. Show the calculations in a compact table and quote the campaign names used. Use plain UK English.

   Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.

3. Use a tool built for this

   The distant third