◆ Google Looker

Optimize Looker 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
See the prompt↓All Google Looker tasks

The same task, four prompts

today's deadline · the next reviewer · the stuck moment · the pattern
AExecute — do the immediate taskThe Q3 sales dashboard is running slow when I filter by region. Re-optimize the underlying…+
The Q3 sales dashboard is running slow when I filter by region. Re-optimize the underlying queries so it loads in under 5 seconds for any filter combination before the executive review on Thursday.
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 Q3 sales dashboard goes live for the executive team, analyze the query performance…+
Before the Q3 sales dashboard goes live for the executive team, analyze the query performance when filtering by region and product line. Identify the bottlenecks and suggest specific optimizations to ensure it loads quickly and reliably for all common filter selections.
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 Q3 sales dashboard is getting hammered by the executive team for slow load times,…+
The executive team is complaining that the Q3 sales dashboard is too slow, especially when they try to drill down into specific regions.
The Q3 sales dashboard is getting hammered by the executive team for slow load times, especially when they filter by region. I've tried a few quick fixes, but it's still dragging. I'm afraid if it doesn't load fast for the Thursday meeting, we'll lose credibility. What's the most likely root cause for regional filters being slow, and what's the fastest, most effective optimization I should prioritize right now to get it ready for Thursday?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternI keep getting pulled into last-minute performance fires for critical dashboards right before…+
I keep getting pulled into last-minute performance fires for critical dashboards right before big meetings.
I keep getting pulled into last-minute performance fires for critical dashboards right before big meetings, like the Q3 sales dashboard this week. It feels like I'm always reacting. What habit should I change in my dashboard development and deployment process to proactively identify and address performance bottlenecks before they become urgent problems for the executive team?
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 Google Looker'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.