◆ Microsoft Azure

Build AI agentic workflows with Logic Apps

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 taskCreate an AI agentic workflow using Logic Apps that monitors the 'Customer Feedback' mailbox.…+
Create an AI agentic workflow using Logic Apps that monitors the 'Customer Feedback' mailbox. When a new email arrives, extract the sentiment (positive/negative) and log it into the 'Feedback Log' spreadsheet.
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 customer feedback agent, I need to ensure its accuracy and avoid…+
Before I deploy this customer feedback agent, I need to ensure its accuracy and avoid misclassifications that could upset clients. How can I incorporate a human-in-the-loop review for 'neutral' or 'ambiguous' sentiments? Also, how can I easily retrain or fine-tune the sentiment model if it starts making errors without rebuilding the whole workflow?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
CDecide — diagnose the stuck momentOur new AI agent for customer support, built with Logic Apps, is consistently misinterpreting…+
The AI agent for customer support is misinterpreting urgent requests as low priority.
Our new AI agent for customer support, built with Logic Apps, is consistently misinterpreting urgent customer requests as low priority, and I'm getting calls from angry clients and my manager, Sarah. I’m afraid this could damage our reputation. I've checked the prompt, but it seems fine. Is there a common pitfall in training or context setting for these agents that causes misclassification of urgency? What's the quickest way to diagnose and fix this without taking the agent offline completely?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternI've noticed my AI agents, built with Logic Apps, frequently drift in performance or make…+
My AI agents frequently drift in performance or make unexpected decisions.
I've noticed my AI agents, built with Logic Apps, frequently drift in performance or make unexpected decisions over time, leading to manual overrides and loss of trust. This forces me into constant reactive monitoring. What habit should I change in how I design, deploy, and monitor these agents to ensure their consistent, reliable performance and reduce the need for constant intervention?
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.