◆ Google Looker

Create native derived tables in Looker

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 taskCreate a new native derived table named 'customer_lifetime_value' that calculates the total…+
Create a new native derived table named 'customer_lifetime_value' that calculates the total revenue for each customer from the 'orders' table.
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 acceptThe marketing team needs a 'customer lifetime value' metric for their campaigns, which requires…+
The marketing team needs a 'customer lifetime value' metric for their campaigns, which requires complex calculations across the 'orders' and 'customers' tables. Design and implement a native derived table that accurately calculates CLTV, ensuring it's efficient to query and correctly joins with existing customer attributes for their analysis.
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 marketing team needs a 'customer lifetime value' metric by Friday for their new campaign,…+
The marketing team needs a 'customer lifetime value' metric by Friday for their new campaign, but I'm struggling with the complex SQL needed to combine order history and customer data reliably.
The marketing team needs a 'customer lifetime value' metric by Friday for their new campaign, but I'm struggling with the complex SQL needed to combine order history and customer data reliably. I'm worried about getting the joins wrong or missing edge cases in the calculation. I don't know if a simple view is enough or if I need a full derived table. What's the best approach to build a robust and accurate CLTV calculation that's ready for them by Friday, ensuring data integrity?
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 writing the same complex SQL queries repeatedly across different…+
I often find myself writing the same complex SQL queries repeatedly across different explorations for common business metrics.
I often find myself writing the same complex SQL queries repeatedly across different explorations for common business metrics, like customer lifetime value. This leads to inconsistencies and wasted effort. What habit should I change in my data modeling practice to proactively identify these recurring complex calculations and encapsulate them into robust native derived tables, ensuring consistency and efficiency across all user analyses?
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.