◆ Mailchimp

Authenticate sending domain

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 taskAuthenticate our sending domain so messages show as from marketing@lumenstudio.com and pass SPF…+
Authenticate our sending domain so messages show as from marketing@lumenstudio.com and pass SPF and DKIM checks. Add the DKIM public key and the SPF include at our DNS host, run the verification in our account, and confirm both show as authenticated before the Tuesday product launch.
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 hand this to the sysadmin, make the authentication request reviewer-friendly: show the…+
Before I hand this to the sysadmin, make the authentication request reviewer-friendly: show the exact TXT record strings to paste for DKIM and SPF, explain in one sentence why both are required, and flag any existing SPF TXT that will need merging to avoid breaking other services.
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 asked Raj to add DKIM and SPF but the dashboard says DKIM not found while SPF looks okay. I'm…+
DKIM still fails after records added
I asked Raj to add DKIM and SPF but the dashboard says DKIM not found while SPF looks okay. I'm the email owner and worried the campaign will be marked suspicious. I don't know if the DKIM selector is wrong, if there's a DNS propagation delay, or if the key was truncated. What three checks will quickly pinpoint the issue and what fix is most likely?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternWe routinely scramble because DKIM/SPF weren't validated before sends. Are we failing to…+
Authentication keeps failing at last minute
We routinely scramble because DKIM/SPF weren't validated before sends. Are we failing to request keys early, giving ops ambiguous strings, or lacking a follow-up verification step? Recommend a single change to our workflow and one line to add to the campaign kickoff that would prevent last-minute authentication failures.
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.