Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

You are designing a generative AI application in Azure AI Foundry. The solution must orchestrate several steps:

  1. Call a GPT-4 model with a system prompt.
  2. Post-process the response with custom Python code.
  3. Automatically log token usage and latency for every run.

You decide to implement the workflow by creating a prompt flow in Azure AI Studio and plan to run it in your Foundry project.

Which action must you perform inside the flow definition so that token usage and latency for each model invocation are captured without writing additional code?

  • Set the PF_LOG_METRICS=on environment variable in the project settings.

  • Call the GPT-4 endpoint through a generic HTTP request node.

  • Add an evaluation node that calculates the tokens and latency_ms metrics after the model node.

  • Reference an Azure OpenAI managed connection in the model invocation node.

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