◆ Figma

Design interactive prototypes

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 taskI need an interactive prototype of the checkout flow for the mobile app so we can test whether…+
I need an interactive prototype of the checkout flow for the mobile app so we can test whether users complete purchase steps without help. Build the flow from the current screens in the project file named Mobile Checkout v3, include tap states for Continue and Back, an animated transition from Shipping to Payment, and a working address-autocomplete mock. Share a single link I can open on my phone by Friday so UX research can run five moderated sessions.
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 prototype to research, make it quick to test: surface the…+
Before I hand this prototype to research, make it quick to test: surface the conversion-critical steps up front, label which taps are mocked versus functioning, make the cart total persist across screens so researchers can validate pricing, and flag any microcopy that might confuse users. Highlight anything that will make a reviewer hesitate during a live session.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
CDecide — diagnose the stuck momentThe team pushed the new Payment screen and when I opened the prototype on my phone the…+
I just linked the new Payment screen and the animation stutters on the phone build
The team pushed the new Payment screen and when I opened the prototype on my phone the transition stutters and the address-autocomplete mock doesn't populate. Engineers say it looks fine on desktop. I need to know whether this is a prototype performance issue I can fix here, a file setup problem, or a device-specific limitation. Should I strip the animation and test again, reduce image sizes, or ask the engineers to re-run the web build? What’s the fastest test that will tell me which it is?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternAcross projects I keep losing time because prototypes look polished on desktop but break in…+
Prototypes repeatedly fail in research because of performance and unclear mocked interactions
Across projects I keep losing time because prototypes look polished on desktop but break in moderated sessions on phones: animations stutter, mocked inputs don't behave, and researchers waste session minutes explaining fakes. Where should I change my habit so prototypes work reliably in research? Recommend a checklist or three rules I can follow during handoff that stop these failures from happening.
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 Figma'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.