AI-300 Certification Practice Question #20

Question

A team deploys a generative AI application that uses a model deployed in Microsoft Foundry. The application must support latency monitoring under production load.
You need to enable performance observability.
Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.

Accepted Answer

Performance observability is built in dependency order: you can't monitor what doesn't exist, so first **set up the model endpoint**, then **enable logging** to emit telemetry, then **configure monitoring metrics** that consume those logs to track latency under load. The blocklist (content safety) and token embeddings (retrieval) are unrelated distractors. All three community comments and the dependency logic (metrics depend on logs) agree on this sequence.

More AI-300 practice questions