◆ Figma

Comment on design files

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 taskAnnotate the design file with specific, actionable comments for Miguel in engineering and…+
Annotate the design file with specific, actionable comments for Miguel in engineering and Hannah in QA. Point to the interactive button at the top right, explain expected hover and disabled states, link to the accessibility contrast target, and request a quick sync if either sees feasibility issues.
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 add comments to the file, make them scannable for engineers: move…+
Before I add comments to the file, make them scannable for engineers: move implementation-critical notes to the top, convert vague requests into acceptance criteria (what counts as done), call out dependencies on the API team, and add estimated effort where I’m confident so engineers can prioritize.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
CDecide — diagnose the stuck momentMiguel replied 'works for me' under a comment about the header animation, then implemented a…+
An engineer replied to a comment with 'works for me' but later built it differently
Miguel replied 'works for me' under a comment about the header animation, then implemented a different timing. I am the designer, Miguel is the engineer, and the sprint starts Monday. I don’t know if his change was performance-driven, a misunderstanding, or intentional. What’s the most likely cause and the best next step to align before the sprint?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternComment threads in design files become a messy mix of opinions, leading to rework and missed…+
Comments in files are noisy and conflict
Comment threads in design files become a messy mix of opinions, leading to rework and missed details. I work with engineers and QA. What habit should we adopt for file comments to reduce ambiguity and speed implementation handoffs?
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.