◆ JavaScript

Design and develop intelligent systems

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 JavaScript tasks

The same task, four prompts

today's deadline · the next reviewer · the stuck moment · the pattern
AExecute — do the immediate taskImplement a machine learning model to classify incoming customer support tickets into…+
Implement a machine learning model to classify incoming customer support tickets into predefined categories: 'billing', 'technical issue', or 'feature request'.
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 deploy this intelligent system for customer support, make sure it's robust against…+
Before I deploy this intelligent system for customer support, make sure it's robust against common user input variations and edge cases. The support team lead, Mark, needs it to be highly accurate to reduce manual triage, so focus on improving its performance on ambiguous or misspelled queries, and flag any categories where its confidence is low.
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 recommendation engine is suggesting irrelevant products to a significant portion of…+
The new recommendation engine is suggesting irrelevant products to a significant portion of users.
The new recommendation engine is suggesting irrelevant products to a significant portion of users, and I'm getting urgent calls from the marketing director, Emily, because it's impacting conversion rates. I suspect an issue with the user profiles or item embeddings, but I can't risk a full rollback without understanding the root cause. What's the likely diagnosis, and what's the best next move to quickly identify and mitigate the problem without taking the system offline?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternI often find myself building intelligent systems that work well in testing but fail in…+
I often find myself building intelligent systems that work well in testing but fail in production with real user data.
I often find myself building intelligent systems that work well in testing but fail in production with real user data, leading to rework and missed deadlines. This erodes trust with product owners. What habit should I change to better anticipate the complexities and biases of live data during the initial design and development phases?
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 JavaScript'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.