◆ Mailchimp

Test deliverability issues

This is real work, not a feature someone invented — it comes from real job ads and real questions people asked. Below are four ready AI prompts: get it done, make it easy for the next person to say yes to, work out the right move when you are stuck, and stop it coming back.

4prompts

The same task, four prompts

today's deadline · the next reviewer · the stuck moment · the pattern
AExecute — do the immediate taskRun a deliverability test for the upcoming weekly newsletter to see if it will land in inboxes.…+
Run a deliverability test for the upcoming weekly newsletter to see if it will land in inboxes. Send test messages to Gmail, Outlook, and a mobile client, check spam-folder placement and header authentication results, and produce a one-page list of immediate fixes (subject lines, links, send cadence) before the Thursday send window.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
BImprove — make it easier to acceptBefore I send the list to the creative lead, surface the three deliverability risks they can…+
Before I send the list to the creative lead, surface the three deliverability risks they can act on: problematic subject lines, spammy link domains, and image-to-text ratio. Highlight the one change that will give the biggest inbox-win and mark any items that require legal approval.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
CDecide — diagnose the stuck momentI ran test sends and Gmail delivered to Promotions while Outlook put the same message in Junk.…+
Inbox placement is inconsistent across providers
I ran test sends and Gmail delivered to Promotions while Outlook put the same message in Junk. I'm the marketer and I can't interpret whether subject, authentication, or content is to blame. What is the most likely cause of divergent placement and what exact tweak should I try first to improve overall inboxing?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternWe keep doing test sends yet repeat the same issues week after week. Are we failing to track…+
We never learn from deliverability results
We keep doing test sends yet repeat the same issues week after week. Are we failing to track the right metrics, not assigning ownership for fixes, or altering too many variables at once? Recommend one habitual metric to record and one small experiment to run that will give reliable learning about audience inboxing.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?

Questions people actually ask

honest answers, no sign-up

Every task here was seen in the real world. Someone doing the job named it, a real job ad asked for it, or a lot of people asked about it online.

If nothing real showed a task, it is not on the page. That is the whole rule.

They are the same job approached four ways, because what you need depends on where you are.

Get it done today. Make it easy for the next person to say yes to. Work out the right move when you are stuck. Learn the pattern so the job stops coming back.

For most of these jobs it can carry the heavy thinking - draft it, sort it, check it, rehearse it with you.

It cannot sit in your chair, take the blame when a number is wrong, or notice what nobody wrote down. Let it do the first 80%. Keep the last 20% that is truly yours.

No. Copy any prompt and paste it into the AI you already use. No account, no score, no wall in the way.

Any of them. The prompts describe the work rather than naming a product, so they are not tied to one assistant.

That is also why they keep working when you switch.

Change it freely. Every prompt is a starting line, not a rule.

Put in your real numbers, your real names and your real deadline. The more you make it yours, the better the answer comes back.

The tasks come from real job ads, published job data and the questions people ask in public forums.

The steps come from Mailchimp's own documentation, with practitioner sources for the traps the manual does not mention.

Push once. Ask it to sharpen the weakest part and to say what it assumed.

Most wrong answers come from a missing detail rather than a bad prompt - tell it the thing it could not know.