◆ Figma

Prototype user flows

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 the user flows for onboarding prototyped so engineers and PMs can test handoffs. Start…+
I need the user flows for onboarding prototyped so engineers and PMs can test handoffs. Start with the signup path for returning users who skipped verification, include the email-resent screen, the verification success state, and the first-time dashboard tour. Link screens so the 'resend email' and 'skip tour' actions navigate correctly. Finish by flagging any missing microcopy or assets. Deadline Friday EOD.
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 onboarding prototype to product for usability testing, make the key…+
Before I hand this onboarding prototype to product for usability testing, make the key decisions visible: surface the conversion funnel (signup → verify → first task) on the first frame, highlight the points where users can drop off, make the primary CTAs consistent across screens, and call out any broken or placeholder flows that would confuse testers.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
CDecide — diagnose the stuck momentWe just ran a quick usability run and three users hit the resend email flow and then abandoned.…+
Tester found users dropping off after 'resend email'.
We just ran a quick usability run and three users hit the resend email flow and then abandoned. I need a diagnosis and the next move. Tell me the likely reason they quit (copy, timing, perceived spam risk, or flow loop) and the single best change to prototype and retest tomorrow morning.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternOver the last three launches we keep redoing onboarding screens after engineering sprints…+
Repeated rework after handoff to engineers delays product sprints.
Over the last three launches we keep redoing onboarding screens after engineering sprints start. Where is the time lost and what single habit should I change so prototypes ship with fewer surprises? Be concrete: what checklist, naming convention, or stage gate to add before handoff.
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.