◆ Figma

Test prototype interactions

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
See the prompt↓All Figma tasks

The same task, four prompts

today's deadline · the next reviewer · the stuck moment · the pattern
AExecute — do the immediate taskRun the prototype test for the checkout flow with the PM and two engineers on Friday. Walk…+
Run the prototype test for the checkout flow with the PM and two engineers on Friday. Walk through the key success path and three critical edge cases, record the session, and capture where interactions break or feel off. Deliver a short bug list and a confidence score for each tested interaction by end of day Friday.
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 testing, make it easy to judge success: surface the expected micro-interaction timings,…+
Before testing, make it easy to judge success: surface the expected micro-interaction timings, list the three gestures that matter, and flag any transitions that are intentionally approximate versus those that must match production exactly so testers know what to scrutinize.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
CDecide — diagnose the stuck momentDuring a playthrough the prototype stuttered when moving between steps in the checkout flow and…+
Prototype playthrough stutters on certain micro-interactions.
During a playthrough the prototype stuttered when moving between steps in the checkout flow and the engineers are worried the timing won't match production. The PM will push for a quick go/no-go and I don't know if the issue is the prototype's frame rate, an overly complex animation, or a route-change in the real app. Should I record the interaction to show developers, simplify the animation timing in the prototype, or run the same steps on a device to isolate whether it's the prototype or the design? What's the fastest way to give Rahul a confident recommendation?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternAcross releases our prototype tests consistently turn into long debugging sessions on…+
Tests keep turning into long sessions chasing minor animation glitches.
Across releases our prototype tests consistently turn into long debugging sessions on micro-interactions, draining engineering time and delaying sign-off. I want a routine that preserves fidelity where it matters but stops wasting cycles on polish that will change in build. Which criteria should I use to decide which interactions need pixel-accurate testing, and what lightweight testing ritual will keep tests under 45 minutes while surfacing real blockers?
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.