◆ Microsoft Azure

Define or recommend model specifications

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
See the prompt↓All Microsoft Azure tasks

The same task, four prompts

today's deadline · the next reviewer · the stuck moment · the pattern
AExecute — do the immediate taskConfigure a new machine learning model endpoint for the 'CustomerChurnPredictor' service. Use a…+
Configure a new machine learning model endpoint for the 'CustomerChurnPredictor' service. Use a Standard D4s_v3 VM size, 8GB RAM, and deploy it to the 'ml-prod-eastus' inference cluster.
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 deploying this new model endpoint, analyze the historical inference traffic patterns for…+
Before deploying this new model endpoint, analyze the historical inference traffic patterns for similar models. Recommend an optimal VM size and auto-scaling configuration that can handle peak loads efficiently while minimizing cost, considering the expected daily request volume of 50,000.
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 data science team just told me their new 'Product Recommender' model actually requires a…+
The data science team just informed me their new model needs a GPU, which wasn't in the initial specs.
The data science team just told me their new 'Product Recommender' model actually requires a GPU for inference, not just a CPU, which changes the resource requirements significantly from what we planned. Our current budget for this project is tight, and I'm not sure if we have available GPU quota in that region. I'm afraid of delaying the project or going over budget. What's the best way to quickly assess GPU availability and cost implications, and what's the most cost-effective GPU instance recommendation for high-throughput inference?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternWe frequently encounter situations where model specifications change late in the deployment…+
Model deployment specs often change late in the cycle, causing rework and delays.
We frequently encounter situations where model specifications change late in the deployment cycle, like unexpected hardware requirements or data dependencies. This always leads to rework, missed deadlines, and frustrated data scientists. What habit should I change to better capture and confirm model requirements upfront, ensuring we define accurate specifications from the start and avoid these last-minute surprises?
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.