◆ Microsoft Power BI

Tune Power BI performance

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 taskOptimize the 'Financial Forecast' dataset by removing all columns not actively used in any…+
Optimize the 'Financial Forecast' dataset by removing all columns not actively used in any report within the 'Finance' workspace to reduce its size.
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 the end-of-quarter push, review the data model for the 'Sales Pipeline' report. Suggest…+
Before the end-of-quarter push, review the data model for the 'Sales Pipeline' report. Suggest specific improvements to its DAX measures and relationships to ensure it loads faster and recalculates totals efficiently for the sales VPs.
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 head of operations just said the 'Supply Chain Efficiency' report is still refreshing…+
The head of operations just told me the 'Supply Chain Efficiency' report is still taking ages to refresh, even after I updated the data source connection.
The head of operations just said the 'Supply Chain Efficiency' report is still refreshing slowly, even after I fixed the data source. I'm afraid of the operations team making critical decisions on outdated figures. I can't tell them I'm unsure if the issue is with the gateway, the data model's complexity, or a specific query. What's the likely diagnosis for the continued slow refresh, and what's the most impactful next step to tune it?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternMy reports always start fast, but as I add more data and complex calculations, they inevitably…+
My reports often start fast but get progressively slower as more data and complexity are added over time.
My reports always start fast, but as I add more data and complex calculations, they inevitably slow down, leading to user frustration and rework. This makes me lose credibility with stakeholders. What habit should I change in my report development process to proactively build for performance and prevent this gradual degradation over time?
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.