# Email list send decision prompt: free ChatGPT template > A copy-ready prompt that turns an email verification result into a send plan: who gets the campaign, who is held back and what to fix first. Source: https://learn.ynteractive.com/content/prompts/email-list-send-decision-prompt · Updated 2026-10-13 · Free from Stepthrough (https://learn.ynteractive.com) [Marketing and social](https://learn.ynteractive.com/content/prompts#job-marketing-and-social) · [Marketing](https://learn.ynteractive.com/content/prompts#industry-marketing) · [Operations](https://learn.ynteractive.com/content/prompts#industry-operations) · Works in ChatGPT, Claude, Gemini and Copilot Updated October 13, 2026 · By [Robert Breen](https://learn.ynteractive.com/content/about) Use this after you have run a contact list through an email checker and have the counts for each group, such as Deliverable, Risky and UnDeliverable. It writes a short plan for the send: who gets it, who is held back and what to clean up first. It protects your sender reputation by keeping the decision written down. It uses only the counts you provide and never sees the addresses. Read about the [email bounce](https://learn.ynteractive.com/content/glossary/email-bounce) first if the terms are new. ## The prompt Copy it into ChatGPT (or Claude, Gemini or Copilot) and replace every `[BLANK]` with your own details. It uses the four parts from [Prompt Writing 101](https://learn.ynteractive.com/content/prompt-writing-101-role-context-task-format): Role, Context, Task and Format. Copy prompt ```text Role: You are an email marketing assistant at [ORGANIZATION], helping the marketing lead decide who should receive a campaign. Context: We checked a list of [LIST SIZE] contacts before sending [CAMPAIGN]. The results were: [RESULTS]. Other facts: [NOTES]. Use only these numbers. Do not guess which individual addresses are good. Our rule is that we only email people who have a reason to hear from us. Task: Write a send plan that says who receives the campaign, who is held back and why, what to do with each group, and what to fix before the next send. Add one sentence on the risk of a high bounce rate in plain words, without quoting a number you were not given. Format: A short table with the columns Group, Count, Decision and Reason, then 4 to 5 bullet points for next steps. Plain words, under [WORD LIMIT] words. ``` ## Fill in the blanks **`[ORGANIZATION]`** Your business or team and what it does, in a few words. **`[LIST SIZE]`** How many contacts you checked. **`[CAMPAIGN]`** What you plan to send, such as an open house invitation. **`[RESULTS]`** The counts per group from the checker, such as 20 Deliverable, 2 Risky and 8 UnDeliverable. **`[NOTES]`** Anything else that matters, such as catch-all domains or shared inboxes like info@. **`[WORD LIMIT]`** 200 keeps it to a page. ## Example, filled in **A made-up example** from the free lesson [Protect Your Sender Reputation Before a Big Send using no2bounce](https://learn.ynteractive.com/content/no2bounce-clean-email-list-sender-reputation). Lantern Hill Venue is the made-up event space in the no2bounce lesson. Nora checked her 30-row list and wants a plan before the next open house invitation. The counts here are an illustration, not the lesson's result. Copy example ```text Role: You are an email marketing assistant at Lantern Hill Venue, a small event space, helping the marketing lead decide who should receive a campaign. Context: We checked a list of 30 contacts before sending an open house invitation. The results were: 20 Deliverable, 2 Risky and 8 UnDeliverable. Other facts: several addresses are on catch-all domains, three are shared inboxes such as info@ and sales@, and one contact is a former employee. Use only these numbers. Do not guess which individual addresses are good. Our rule is that we only email people who have a reason to hear from us. Task: Write a send plan that says who receives the campaign, who is held back and why, what to do with each group, and what to fix before the next send. Add one sentence on the risk of a high bounce rate in plain words, without quoting a number you were not given. Format: A short table with the columns Group, Count, Decision and Reason, then 4 to 5 bullet points for next steps. Plain words, under 200 words. ``` ## What a good answer looks like - The plan sends only to the confirmed group and holds the Risky group until someone decides. - Shared inboxes and catch-all domains are called out as judgment calls, not decided by the model. - The bounce risk sentence is plain and quotes no invented number. ## How to check it before you use it An AI draft can sound right and still say something you never told it. Use the habit from the [Reply Faster lesson](https://learn.ynteractive.com/content/chatgpt-reply-to-customer-emails): check every promise, name, date and number against what you gave it before anything goes out. - Confirm the counts against your checker's report before you paste them in. - Look at your email service's own bounce guidance. Each provider sets its own limits. - Make sure everyone you send to has a reason to hear from you, and follow the opt-in and unsubscribe rules where you send. - Do the actual send from a file you exported from the checker, not from the plan. ## Why this prompt works Feeding it counts instead of addresses keeps contact data out of the chat, and the rule against quoting unprovided numbers stops the model from inventing a bounce benchmark. ## Practice it in the free lesson **[Protect Your Sender Reputation Before a Big Send using no2bounce](https://learn.ynteractive.com/content/no2bounce-clean-email-list-sender-reputation)**: A business case: a 9% bounce rate puts your email account and inbox placement at risk. Use no2bounce to check a contact list, read what it finds, and send only to addresses that are safe. You do every step yourself in a practice copy of no2bounce, and nothing touches your real accounts. [Start the free lesson](https://learn.ynteractive.com/modules/no2bounce-clean-email-list) ## Terms used here [Email bounce](https://learn.ynteractive.com/content/glossary/email-bounce) · [Email deliverability](https://learn.ynteractive.com/content/glossary/email-deliverability) · [Cold email](https://learn.ynteractive.com/content/glossary/cold-email) ## Related prompts - [Data cleanup plan prompt](https://learn.ynteractive.com/content/prompts/data-cleanup-plan-prompt): Turn messy spreadsheet columns into clean, consistent ones: a column-by-column plan with standard values, rules for odd entries… - [Social post ideas prompt](https://learn.ynteractive.com/content/prompts/social-post-ideas-prompt): A four-part ChatGPT prompt for social post ideas built on your services and real customer questions: platform, hook and call to… - [Blog post to social posts prompt](https://learn.ynteractive.com/content/prompts/repurpose-blog-into-social-posts-prompt): Turn one blog post into several social posts with a ChatGPT prompt that quotes the line each post is built on, so nothing new… ## More marketing and social prompts - [Email newsletter prompt](https://learn.ynteractive.com/content/prompts/email-newsletter-prompt): A ChatGPT prompt for a short customer newsletter built from your numbered updates: one section each, one main call to action, no… - [Email subject lines prompt](https://learn.ynteractive.com/content/prompts/email-subject-lines-prompt): Get ten honest subject lines for a finished email, each with preview text and a character count, grouped by approach so you can… - [Event invitation email prompt](https://learn.ynteractive.com/content/prompts/event-invitation-email-prompt): A ChatGPT prompt for an event invitation that puts the date, time, place, cost and RSVP up front and repeats them in a Details… ## Frequently asked questions **Can ChatGPT clean my email list?** No. A verification tool checks the addresses. ChatGPT can help you write the plan once you have the counts. **Should I send to risky addresses?** That is your call. Many teams hold them back, or send a small batch by hand to people they know. [All free prompt templates](https://learn.ynteractive.com/content/prompts) · [AI glossary](https://learn.ynteractive.com/content/glossary)