◆ Microsoft SQL Server

Investigate suspicious financial activity

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 taskRetrieve all transactions for account number 'XYZ789' from the past six months, specifically…+
Retrieve all transactions for account number 'XYZ789' from the past six months, specifically focusing on transfers exceeding $10,000. Include sender and receiver details, and the transaction timestamps. Export this data to a temporary table for further analysis by the financial investigations unit.
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 send this transaction history for account 'XYZ789' to the compliance officer, make it…+
Before I send this transaction history for account 'XYZ789' to the compliance officer, make it easier for them to spot unusual activity. Group all transactions by counterparty, show the sum of all transfers to each, and flag any single transaction that exceeds $50,000. Also, add a column showing the originating IP address for each transfer for easier tracing.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
CDecide — diagnose the stuck momentWe just got an alert for a client, 'Global Innovations Inc.', who suddenly started making large…+
A new alert just came in about a series of international transfers from a client with no prior overseas activity.
We just got an alert for a client, 'Global Innovations Inc.', who suddenly started making large international transfers to a country they've never dealt with before, and the amounts are just below our automatic flagging threshold. I'm afraid of missing a crucial money laundering signal, but I also don't want to over-report every new client behavior. What's the most likely explanation for this sudden change, and what's my best next move to quickly assess the risk before I escalate it to the AML team?
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 lose valuable time trying to manually correlate suspicious transactions that span…+
I frequently struggle to correlate seemingly unrelated transactions across different systems during investigations.
I often lose valuable time trying to manually correlate suspicious transactions that span multiple internal systems and external data feeds. This makes my investigations slower and less comprehensive. What habit should I change in how I approach data aggregation and linking during the initial phase of an investigation to more efficiently identify connected activities and improve the accuracy of my findings for the compliance 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 Microsoft SQL Server'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.