◆ Salesforce

Break a flow into two transactions

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 taskWhen a new lead is created, assign them to a sales rep and then create a follow-up task for…+
When a new lead is created, assign them to a sales rep and then create a follow-up task for that rep to call the lead by tomorrow.
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 deploy this flow, make sure that if the lead assignment fails for any reason, the…+
Before I deploy this flow, make sure that if the lead assignment fails for any reason, the follow-up task is not created, so we don't end up with orphaned tasks.
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 new lead onboarding flow is creating follow-up tasks even when the lead assignment fails,…+
The lead creation flow is sometimes assigning tasks even when the lead assignment itself fails.
The new lead onboarding flow is creating follow-up tasks even when the lead assignment fails, which is confusing the sales team. I'm trying to break it into two transactions so the task only creates after a successful assignment, but I'm worried about unintended side effects. What's the safest way to ensure the task creation is completely dependent on the lead assignment's success, without making the flow too complex?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternI frequently build flows where a critical initial step might fail, but subsequent dependent…+
I often build flows where one part's failure doesn't stop subsequent, dependent actions.
I frequently build flows where a critical initial step might fail, but subsequent dependent actions still execute, creating bad data or unnecessary work. This leads to cleanup headaches for the support team. What habit should I change to consistently structure my flows so that dependent actions only run if preceding critical steps succeed, making them more resilient?
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.