AI-300 Exam Question 31

Drag and Drop Question
A team validates a generative AI application that produces free-form text responses by using Microsoft Foundry SDK.
The evaluation dataset is registered in the Microsoft Foundry environment.
You need to configure a safety evaluation pipeline that reliably evaluates model outputs for harmful content.
Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.

AI-300 Exam Question 32

Hotspot Question
You monitor an Azure Machine Learning classification training experiment named train_classification on Azure Notebooks.
You must store a table named table as an artifact in Azure Machine Learning Studio during model training.
You need to collect and list the metrics by using MLflow.
How should you complete the code segment? To answer, select the appropriate option in the answer area.
NOTE: Each correct selection is worth one point.

AI-300 Exam Question 33

An organization maintains separate Azure Machine Learning workspaces for development and production.
Both environments must use the same validated assets without duplicating them.
Assets must be shared across workspaces while maintaining centralized governance and version control.
You need to enable reuse of assets across workspaces without copying them.
What should you do?
  • AI-300 Exam Question 34

    A product team is building a customer support assistant that must respond consistently across multiple channels.
    Early testing shows that small wording changes in prompts cause large differences in tone and factual accuracy.
    The team needs prompts that are reliable, reusable, and adaptable across multiple use cases without retraining the underlying model.
    You need to design prompts that improve response quality while remaining flexible for future changes.
    Which two actions should you perform? Each correct answer presents part of the solution.
    (Choose two.)
    NOTE: Each correct selection is worth one point.
  • AI-300 Exam Question 35

    Your ML pipeline contains independent feature engineering steps that currently execute sequentially, increasing overall runtime. You want to optimize execution without modifying logic.
    What is the BEST solution?