◆ Salesforce

Analyze data silos in unit tests

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 taskI need to analyze the data silos in the unit tests for the 'OpportunityTriggerHandler' class.…+
I need to analyze the data silos in the unit tests for the 'OpportunityTriggerHandler' class. Specifically, check if the tests are creating their own Account and Contact records or relying on existing data.
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 off the 'LeadConversion' module for UAT, analyze the unit tests for the…+
Before I hand off the 'LeadConversion' module for UAT, analyze the unit tests for the 'LeadProcessor' class. Point out any tests that aren't properly isolating their data, which could lead to inconsistent results when run in different environments or with varying existing data.
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 unit tests for our 'CaseEscalation' logic are failing intermittently, and the release…+
Our unit tests for the 'CaseEscalation' logic are failing intermittently, and the release manager is holding up deployment.
The unit tests for our 'CaseEscalation' logic are failing intermittently, and the release manager is holding up our deployment for Friday. Sometimes they pass, sometimes they don't, and I can't tell if it's an issue with shared test data, a timing dependency, or something else entirely. What's the most likely source of this inconsistency, and what's the best next step to diagnose and fix it so we can deploy?
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 writing unit tests that pass initially but then break or give inconsistent results when…+
My unit tests frequently break when new data is introduced or when run in different environments.
I keep writing unit tests that pass initially but then break or give inconsistent results when new data is added or when they're run in a different sandbox. It's making our deployments slow and unreliable. What habit should I change in how I set up test data to ensure my unit tests are truly isolated and robust?
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 Salesforce'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.