◆ Microsoft Azure

Create a workflow in Azure

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 taskGet the new dev environment ready for the marketing team's web app. Spin up the standard B2s_v2…+
Get the new dev environment ready for the marketing team's web app. Spin up the standard B2s_v2 VMs, set up the network security groups to allow only internal access, and make sure the staging database is accessible to them by end of day Friday.
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 provision these new VMs for the marketing team, check for any cost-saving alternatives…+
Before I provision these new VMs for the marketing team, check for any cost-saving alternatives that still meet their performance needs. We've been overspending on similar projects, and I want to avoid that again. Also, ensure the network rules are robust but not overly restrictive.
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 analytics team's new VM deployment failed for the third time this morning, and I'm getting…+
The new VM deployment for the analytics team failed, and I'm not sure why.
The analytics team's new VM deployment failed for the third time this morning, and I'm getting pressure from Mark in leadership about the delay. The error logs are generic, and I can't pinpoint if it's a resource quota issue, a misconfigured template, or something deeper with the subscription. What's the most likely cause, and what's the fastest way to get this running without another rollback?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternI'm constantly reacting to urgent, unexpected resource provisioning requests, often leading to…+
I keep getting pulled into urgent, unexpected resource provisioning requests.
I'm constantly reacting to urgent, unexpected resource provisioning requests, often leading to rushed deployments and missed details. This is burning me out and creating technical debt. What habit could I change to anticipate these needs better and build a more proactive, less reactive provisioning process?
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 Azure'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.