◆ Microsoft Azure

Manage Azure DevOps tasks

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 taskUpdate the 'Deploy to Production' task in the 'Customer Portal' pipeline to use the 'latest'…+
Update the 'Deploy to Production' task in the 'Customer Portal' pipeline to use the 'latest' image tag, not '1.2.3', and ensure it points to the 'prod-eastus' resource group. Then, trigger a run of the pipeline.
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 new firewall rule to the 'Staging' environment, make sure the change won't…+
Before I deploy this new firewall rule to the 'Staging' environment, make sure the change won't disrupt existing traffic. Check the network security group rules for 'Staging-WebServers' and 'Staging-AppServers' and flag any potential conflicts or necessary pre-approvals from the security team.
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 'CustomerDB-Backup' pipeline failed last night, and I'm getting pressure from Maria in ops…+
The 'CustomerDB-Backup' pipeline failed last night, but the logs are vague.
The 'CustomerDB-Backup' pipeline failed last night, and I'm getting pressure from Maria in ops to understand why before the next backup window. The error message is generic, and I can't pinpoint if it's a permissions issue, a storage problem, or a timeout. What's the most likely cause for this kind of intermittent failure, and what's the fastest way to diagnose it without impacting the live database?
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 getting pulled into urgent debugging sessions for 'ghost' pipeline failures that turn…+
I keep getting pulled into urgent debugging sessions for 'ghost' pipeline failures.
I keep getting pulled into urgent debugging sessions for 'ghost' pipeline failures that turn out to be transient network hiccups or resource exhaustion, but the alerts aren't clear. I'm losing too much time chasing shadows. What habit should I change to proactively identify and differentiate between actual code issues and infrastructure flakiness before they escalate to an incident?
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.