Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

Your team deployed a GPT-4 model inside an Azure AI Foundry project. A production web app, already instrumented with Application Insights, calls the endpoint. You must collect per-call prompt/completion token counts, latency, and cost, correlate them with the app's existing telemetry, and keep the data for at least 30 days. What should you do?

  • Route all inference requests through Azure Event Grid, ingest the events into Azure Data Explorer, and build dashboards by querying the ADX table for token usage and latency.

  • Create an Azure Monitor diagnostic setting on the Azure OpenAI resource that sends Usage and RequestResponse logs to a Log Analytics workspace, ensure Azure Monitor metrics are enabled, link the workspace to the existing Application Insights instance, and set the workspace retention to 30 days.

  • Enable Microsoft Purview Data Sharing for the Azure OpenAI resource and use Power BI incremental refresh to import the Audit log with a 30-day window.

  • Add the header "logging_mode=all" to every inference call and configure the Azure OpenAI resource to archive logs to an Azure Storage account with a 30-day lifecycle-management rule.

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