◆ Mailchimp

Optimize images for email

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 taskOptimize the four product photos for our weekly newsletter so they load fast and look sharp:…+
Optimize the four product photos for our weekly newsletter so they load fast and look sharp: export each at 600px wide for desktop and a separate 320px-wide version for mobile, save as progressive JPEGs under 150 KB, and name files with SKU and size. Replace the originals in the campaign, update alt text with product names, and send to Marcus to run an inbox preview before scheduling.
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 finalize images for the weekly newsletter, make them approval-ready: show the exported…+
Before I finalize images for the weekly newsletter, make them approval-ready: show the exported file sizes next to each image, surface a 600px and 320px version, call out any image over 150 KB, suggest a compression level to hit target size while keeping product detail, and note which three images need a recolor or crop to avoid dark bands on mobile.
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 exported the newsletter images but three files are over 150 KB and previews load slowly;…+
File sizes are over the 150 KB limit and previews load slowly
I exported the newsletter images but three files are over 150 KB and previews load slowly; Marcus will balk at poor load times and Sarah will want image quality preserved. I don't know whether to reduce dimensions, increase compression, or use a different format. What's the most likely trade-off and the fastest adjustment that keeps product detail while meeting the 150 KB guideline?
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 exceeding the 150 KB per-image guideline and inbox previews slow, causing delays and…+
We repeatedly exceed our email image size target
We keep exceeding the 150 KB per-image guideline and inbox previews slow, causing delays and pushback from ops. I need a repeatable rule to prevent this: what export settings, format choices, and a one-line acceptance test should every designer follow so images consistently meet our email performance standard?
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.