Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

You have deployed a gpt-35-turbo model to Azure AI Foundry by using an Azure OpenAI Service resource. You must:

  • observe how many tokens each request consumes and the 95th-percentile end-to-end latency,
  • receive alerts if the 95th-percentile latency ever exceeds 1000 ms,
  • analyze how often the built-in content filter blocks or annotates prompts or completions. Which configuration should you use?

  • Enable the "Audit" and "Trace" diagnostic log categories and create an alert rule on the Activity Log event "ActionLatency".

  • Create an alert rule on the "Total request latency" Azure Monitor metric (P95) and enable a diagnostic setting that sends the "RequestResponse" log category to a Log Analytics workspace.

  • Enable Application Insights request telemetry and depend on its performance charts; no diagnostic setting is required because content filter events are included automatically.

  • Create a metric alert on the "Tokens per minute" metric and export Activity Logs to a storage account for content filter analysis.

Microsoft Azure AI Engineer Associate AI-102
Implement generative AI solutions
Your Score:
Settings & Objectives
Random Mixed
Questions are selected randomly from all chosen topics, with a preference for those you haven’t seen before. You may see several questions from the same objective or domain in a row.
Rotate by Objective
Questions cycle through each objective or domain in turn, helping you avoid long streaks of questions from the same area. You may see some repeat questions, but the distribution will be more balanced across topics.

Check or uncheck an objective to set which questions you will receive.

Wipe Score
Bash, the Crucial Exams Chat Bot
AI Bot