◆ MATLAB

Change font size in plots

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 taskIncrease the font size of the axis labels and title on this plot to 14 points so it's readable…+
Increase the font size of the axis labels and title on this plot to 14 points so it's readable in the presentation slides.
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 embed this into the final report for the grant committee, adjust the font sizes on…+
Before I embed this into the final report for the grant committee, adjust the font sizes on this plot. Make the axis labels and legend larger and ensure the title stands out, so it's easily legible even when printed in a smaller format.
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 just generated the plot for the quarterly review, and the axis labels and legend are tiny.…+
The plot I just generated has tiny labels, and I'm worried it won't be readable for the review panel.
I just generated the plot for the quarterly review, and the axis labels and legend are tiny. I'm afraid the review panel won't be able to read the details on the projector screen, which could undermine my argument. I'm not sure if I should just increase everything or if there's a standard size for presentations. What's the best approach to quickly adjust all relevant font sizes on a plot for optimal readability in a large meeting room, and what's a good default size to aim for?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternI consistently get dinged by reviewers and professors for illegible font sizes in my plots,…+
I keep getting feedback that my plot labels are too small, forcing me to re-export figures for papers and presentations.
I consistently get dinged by reviewers and professors for illegible font sizes in my plots, forcing me to re-render figures multiple times. This wastes a lot of time before submission deadlines. What habit could I change to ensure my plot fonts are always appropriately sized for publication and presentations from the start, avoiding these last-minute revisions?
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 MATLAB'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.