◆ HTML

Implement online features

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 taskImplement the new 'dark mode' toggle for the website using CSS variables and JavaScript. Ensure…+
Implement the new 'dark mode' toggle for the website using CSS variables and JavaScript. Ensure the preference is saved in local storage and applies site-wide.
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 acceptI need to implement the new user profile dashboard. Make sure the data loads efficiently, even…+
I need to implement the new user profile dashboard. Make sure the data loads efficiently, even for users with many orders, and that the UI feels responsive. I also need to ensure all form submissions are secure and provide clear feedback to the user.
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 new 'live chat' feature I pushed to production yesterday is sporadically failing for about…+
A critical feature I just implemented is causing intermittent errors on live production.
The new 'live chat' feature I pushed to production yesterday is sporadically failing for about 10% of users, throwing generic 'server error' messages. I've checked the logs, but they're not pointing to a clear cause, and support is getting swamped. What are the most common subtle causes of intermittent, hard-to-reproduce live feature failures, and what's the quickest way to isolate the root cause without impacting more users?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternI'm spending too much time fixing bugs in live features that should have been caught during…+
I frequently find myself fixing bugs in production that should have been caught earlier.
I'm spending too much time fixing bugs in live features that should have been caught during development or testing. This impacts my credibility and causes stress. What's one habit I can change in my implementation process to proactively identify and prevent these kinds of issues before they ever reach our users?
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 HTML'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.