As of 13 August 2026, AI can analyse your email campaign open rates.

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. Use a tool built for this

   Second choice

3. Do it yourself

   The distant third

   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 campaign data as CSV, including delivered emails, opens, unique opens if available, clicks, subject line, send date and audience segment.
   2. Gather the context the export does not contain, including your campaign objective, audience definitions, send-time changes, list changes, tracking changes and any campaigns that were sent to unusual groups.
   3. Remove names, email addresses and other unnecessary personal data from the export, then paste the remaining table and context into a chatbot with the prompt above.
   4. Ask the chatbot to show the open-rate calculation for each campaign and to separate observed figures from explanations and recommendations.
   5. Compare every reported total and open-rate calculation with the original campaign reports in your email platform, checking that delivered emails, opens and segment definitions use the same meaning throughout.
   6. Check unusual results against delivery issues, privacy-related tracking changes, automated activity, list growth and changes to the audience before accepting an explanation.
   7. Choose no more than three follow-up tests, record their success measures, and send the revised campaign only after a colleague has checked the proposed change against your marketing plan.

   Prompt

   Analyse the email campaign data below. Calculate the open rate for each campaign as total opens divided by delivered emails, and show the calculation clearly. Compare campaigns by date, subject line, audience segment, send time and any other column provided. Identify meaningful patterns, but do not claim causation from correlations. Flag small samples, missing values, duplicate rows, inconsistent definitions and any result that cannot be checked from the data. Treat open rates as an imperfect measure because tracking can be affected by privacy features, blocked images and automated activity. Separate observed facts, reasonable hypotheses and recommendations. Recommend no more than three follow-up tests, each with a clear success measure and the data needed to assess it. Do not invent figures, campaign context or industry benchmarks. If the export does not contain enough information, say exactly what is missing. Finish with a concise list of the most reliable findings and the checks I must make in my email platform before acting.
   
   Business objective: [insert objective]
   Email platform and export definitions: [insert platform and definitions]
   Campaign data:
   [paste the CSV or table here]

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