Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

You created a multi-step agent in Azure AI Studio by orchestrating a Semantic Kernel planner, several function skills, and Azure OpenAI. Before exposing the agent endpoint to business users, you must verify that every new version still answers a fixed set of 100 test prompts correctly, and you want an automated scorecard that includes groundedness and relevancy metrics after each run. Which Azure AI Studio capability should you use to meet these requirements with the least custom code?

  • Run an evaluation from the Evaluate tab, which uses Prompt Flow to score the agent against the test dataset

  • Export the conversation transcript after each manual session and compare it in Excel

  • Add additional instructions to the agent's system message to log groundedness scores

  • Test the agent manually in the playground chat panel and record the responses

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