◆ Microsoft Power BI

Clean and maintain Power BI data

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 Microsoft Power BI tasks

The same task, four prompts

today's deadline · the next reviewer · the stuck moment · the pattern
AExecute — do the immediate taskRun the monthly data quality check on the customer database, specifically looking for duplicate…+
Run the monthly data quality check on the customer database, specifically looking for duplicate entries in the 'Company Name' field and missing values in 'Contact Email'. Export the findings to a CSV for Sarah in CRM by Tuesday.
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 hand this customer data over to the marketing team for their new campaign, clean it up…+
Before I hand this customer data over to the marketing team for their new campaign, clean it up so they don't waste time on bad leads. Standardize the 'State' abbreviations and remove any entries where the 'Subscription Status' is 'Cancelled' more than 6 months ago.
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 received a new product usage data feed, and it's a mess – inconsistent naming for…+
I just received a new data feed from the product team, but it has inconsistent naming conventions and missing fields compared to our existing database.
I just received a new product usage data feed, and it's a mess – inconsistent naming for 'Feature' and 'Event Type', plus 'User ID' is sometimes blank. If I integrate it as is, our analytics will be skewed, but if I spend too long cleaning it, I'll miss the deadline for the product launch report. I'm not sure if the product team can easily re-export it in a cleaner format, or if I have to manually map everything. What's the quickest way to get this data usable without compromising accuracy or delaying the launch?
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 spending time manually fixing small data errors – a misspelled product name…+
I'm constantly spending time manually fixing small data errors that pop up across different reports.
I'm constantly spending time manually fixing small data errors – a misspelled product name here, an incorrect date format there – across different reports. It's tedious and eats into my analysis time. What habit should I change to proactively catch and prevent these recurring data quality issues at the source, rather than always reacting to them?
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 Microsoft Power BI'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.