Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.
After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear on the review screen.
You work in Microsoft Foundry with a prompt flow.
You must manually evaluate prompts and compare results across prompt variants.
You need to capture the inputs, outputs, token usage, and latencies for each flow run for the evaluation.
Solution: In Microsoft Foundry, turn on Tracing for the prompt flow of the project and execute test runs to produce trace data.
Does the solution meet the goal?
You manage an Azure Machine Learning workspace and a GitHub repository. The GitMub repository contains a CSV tile located at https://fawojthubusercontent.com/accountt/repo1/main/docVdatal.csv. The CSV file includes embedded newlines.
You plan to consume the content of the CSV file in the workspace. The solution must minimize the possibility of misaligned field values when reading the file content.
You need to create a data asset that references the CSV file.
Which data asset configuration values should you use? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.

You use Azure Machine Learning to train models across multiple experiments by using the same workspace.
You must record training runs in a centralized location to compare results from different jobs.
During training, performance values must be captured so they appear in the experiment run history.
You need to configure experiment tracking.
What should you configure for each requirement? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

You manage an Azure Machine Learning workspace that includes a batch endpoint. You plan to deploy a model to the batch endpoint. You need to configure compute for the deployment. Which compute should you use?
You create an Azure Machine Learning workspace.
You plan to write an Azure Machine Learning SDK for Python v2 script that logs an image for an experiment. The logged image must be available from the images tab in Azure Machine Learning Studio.
You need to complete the script.
Which code segments should you use? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.

You create an Azure Machine Learning workspace.
You must use the Python SDK v2 to implement an experiment from a Jupyter notebook in the workspace. The experiment must log a list of numerical metrics.
You need to implement a method to log a list of numerical metrics.
Which method should you use?
You use the Azure Machine learning SDK v2 tor Python and notebooks to tram a model. You use Python code to create a compute target, an environment, and a taring script. You need to prepare information to submit a training job.
Which class should you use?
You are designing a new machine learning solution to predict customer churn by using Azure Machine Learning. You have raw data in CSV format stored in Azure Data Lake.
You need to design the solution so that it can efficiently handle large-scale model training and iterative development.
Which two actions should you perform? Each correct answer presents part of the solution. Choose two.
NOTE: Each correct selection is worth one point
A team is preparing a generative Ai application for production deployment. The application generates structured responses that must be evaluated for quality before each release.
The organization requires repeatable evaluation results that can be compared across builds and environments.
You need to configure evaluation inputs so quality metrics can be reliably calculated across test runs.
How should you prepare the evaluation Inputs? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.

You manage a Microsoft Foundry project.
You are developing a solution to generate content based on text and images. The solution requires the ability to manage high-volume processing and avoid disruptions to the online workloads.
You need to deploy the solution.
Which deployment type and large language model (LLM) should you use? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
