◆ Microsoft Azure

Reference Azure Pipelines 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 taskAdd a 'Copy Files' task to the 'Build WebApp' pipeline, after the 'npm build' step, to copy all…+
Add a 'Copy Files' task to the 'Build WebApp' pipeline, after the 'npm build' step, to copy all files from the 'dist' folder to the artifact staging directory.
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 finalize this new 'Deploy to Kubernetes Service' task for the 'Microservice X'…+
Before I finalize this new 'Deploy to Kubernetes Service' task for the 'Microservice X' pipeline, check its configuration against our security best practices. Flag any hardcoded secrets, overly broad permissions, or non-standard image sources that would fail our security audit.
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 'Publish Artifacts' task in the 'Release-Client-App' pipeline is failing intermittently,…+
The 'Publish Artifacts' task in the 'Release-Client-App' pipeline is failing intermittently.
The 'Publish Artifacts' task in the 'Release-Client-App' pipeline is failing intermittently, but only for certain branches, and I can't figure out why. The error logs point to a generic 'access denied' message, but permissions look correct. The release manager needs this fixed by end of day. I don't know if it's a caching issue, a pathing error, or something deeper with the agent. What's the most likely culprit, and what's the quickest way to isolate it?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternI repeatedly debug pipeline tasks that break due to environment variable inconsistencies…+
I repeatedly debug pipeline tasks that break due to environment variable inconsistencies.
I repeatedly debug pipeline tasks that break due to environment variable inconsistencies between dev, staging, and production. This costs us hours every week. What habit should I change to standardize how environment variables are managed and referenced across all our pipelines, so tasks are more robust and less prone to these kinds of errors?
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.