◆ JavaScript

Automate data cleaning and preprocessing

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 taskTake the raw customer feedback data from the survey tool, remove any entries with missing email…+
Take the raw customer feedback data from the survey tool, remove any entries with missing email addresses, and convert all text to lowercase. Save the cleaned data as a JSON file for the data science team.
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 import this new list of leads into our system, clean it up. Remove any duplicate email…+
Before I import this new list of leads into our system, clean it up. Remove any duplicate email addresses, standardize the phone number formats to E.164, and flag any entries where the company name is missing so I can follow up.
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 daily data import from the partner API just ran, and the analytics team is reporting that…+
The latest data import from the partner API has malformed timestamps, and the analytics team can't use it.
The daily data import from the partner API just ran, and the analytics team is reporting that all the timestamp fields are malformed, throwing errors in their dashboards. Our SLA requires this data to be ready by 9 AM. I can't tell if the partner changed their API format or if our ingestion script broke. What's the immediate fix to get usable data to the analytics team, and how should I prevent this from happening again?
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 constantly fixing inconsistent data formats in CSVs I receive from various internal teams –…+
I keep having to manually fix inconsistent data formats in CSVs provided by different internal teams.
I'm constantly fixing inconsistent data formats in CSVs I receive from various internal teams – dates, currencies, text fields. It's a huge time sink before I can even start my actual work. I need a more proactive approach to ensure data quality at the source or a faster way to standardize it. What habit should I change to stop this recurring problem?
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.