Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

You built a custom agent with Azure AI Foundry Agent Service in Azure AI Studio. A JSONL file contains 200 user utterances, the expected agent replies, and grading labels. Before releasing the agent, you need to calculate precision, recall, and F1 and save the results so that future prompt versions can be compared. Which action should you take in Azure AI Studio?

  • Import the JSONL file as a knowledge base data source and trigger a bulk chat simulation.

  • Create and run an evaluation run against the agent deployment, supplying the JSONL conversation dataset.

  • Configure a traffic-splitting deployment slot and route 5 percent of users to the new agent version.

  • Enable session transcripts in Application Insights on the staging endpoint and manually review the logs.

Microsoft Azure AI Engineer Associate AI-102
Implement an agentic solution
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