◆ Elasticsearch

Search for part of a word

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 taskSearch the 'product_catalog' index for documents where the 'description' field contains 'smart'…+
Search the 'product_catalog' index for documents where the 'description' field contains 'smart' and return the top 10 results. The marketing team needs this list by end of day for their campaign planning.
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 customer support team starts using this, create a search query for the…+
Before the customer support team starts using this, create a search query for the 'support_tickets' index that can find tickets even if the user only types part of a word in the 'summary' field, like 'conn' for 'connection'. It needs to be fast and relevant for them.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
CDecide — diagnose the stuck momentA critical user just reported that their search for 'report' in the 'docs' index isn't…+
A user is complaining that their search for 'report' isn't finding documents containing 'reporting' or 'reports' in the 'docs' index.
A critical user just reported that their search for 'report' in the 'docs' index isn't returning documents that contain 'reporting' or 'reports'. They're frustrated because they can't find what they need, and I'm worried this is impacting their productivity. I can't tell if it's the tokenizer or the query itself. What's the likely issue, and what's the best way to quickly build a query that handles these partial word matches gracefully?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternOur internal users consistently struggle to find relevant documents because their searches for…+
Our internal search users frequently complain about not finding relevant results when they use partial words or slight misspellings.
Our internal users consistently struggle to find relevant documents because their searches for partial words or slight misspellings yield poor results. It's eroding their trust in our search capabilities. What habit should I change in our index mapping or query construction to ensure we're consistently providing more forgiving and intelligent search results for these common user behaviors?
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.