◆ Elasticsearch

Query with multi_match and wildcard

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 Elasticsearch tasks

The same task, four prompts

today's deadline · the next reviewer · the stuck moment · the pattern
AExecute — do the immediate taskWrite a query to find documents in the 'product_catalog' index where the 'name' or…+
Write a query to find documents in the 'product_catalog' index where the 'name' or 'description' fields contain 'laptop' and the 'sku' field starts with 'ABC'.
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 off to the marketing team, create a query for the 'product_catalog' index…+
Before I hand this off to the marketing team, create a query for the 'product_catalog' index that uses multi_match to search 'name', 'description', and 'tags' for 'summer collection', and also includes a wildcard search on 'sku' for 'SUMMER-*', ensuring it returns relevant products even with slight variations in the search terms.
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'm trying to build a query for the 'customer_feedback' index to find mentions of 'slow' or…+
I'm trying to build a query for the 'customer_feedback' index to find mentions of 'slow' or 'buggy' in the 'comment' field, but also want to narrow it down to 'product_A*' SKUs. The multi_match is working, but the wildcard on the SKU isn't filtering correctly, or it's making the query too slow. I'm afraid of missing critical feedback or overloading the cluster. What's the best way to combine these efficiently, and how do I ensure the wildcard is performant on a large dataset?
I'm trying to build a query for the 'customer_feedback' index to find mentions of 'slow' or 'buggy' in the 'comment' field, but also want to narrow it down to 'product_A*' SKUs. The multi_match is working, but the wildcard on the SKU isn't filtering correctly, or it's making the query too slow. I'm afraid of missing critical feedback or overloading the cluster. What's the best way to combine these efficiently, and how do I ensure the wildcard is performant on a large dataset?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternI constantly struggle to balance query complexity with performance when combining multi_match…+
I constantly struggle to balance query complexity with performance when combining multi_match and wildcard searches for user-facing applications.
I constantly struggle to balance query complexity with performance when combining multi_match and wildcard searches for user-facing applications. This leads to slow search results or incomplete data for our users, impacting their experience. What habit should I change in how I approach query design, especially when dealing with free-text and partial-match requirements, so I consistently build efficient and accurate queries without hitting performance bottlenecks?
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 Elasticsearch'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.