Free Microsoft AI-300 Exam Dumps Questions & Answers

A real-time endpoint experiences sporadic latency spikes. Investigation reveals instances scale down to zero during inactivity. You need to reduce latency without significantly increasing cost.
What should you configure?

• A.Set minimum instance count
• B.Increase timeout settings
• C.Reduce logging
• D.Switch to batch endpoint

Drag and Drop Question
You manage an Azure Machine Learning workspace. You train a model named model1.
You must identify the features to modify for a differing model prediction result.
You need to configure the Responsible AI (RAI) dashboard for model1.
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.

Correct Answer:

Explanation:
To setup the Responsible AI (RAI) dashboard in Azure Machine Learning and specifically analyze minimal feature modifications needed to change a prediction result, you must use Counterfactual Analysis.
Here are the specific sequential steps you need to take:
Step 1: Load and configure the Responsible AI Insights dashboard constructor component.
Initialize the RAI Insights Dashboard Constructor
1. Create the root pipeline component that acts as the container for your tools.
2. Call the RAI Insights dashboard constructor component.
3. Pass your registered model and your test dataset as the mandatory inputs to this component.
Step 2: Add the Counterfactuals to Responsible AI Insights dashboard
Configure Counterfactual Analysis
1. Add the specific component required to identify what features to modify for a differing prediction.
2. Call the Add Counterfactuals to RAI Insights dashboard component.
3. Link its input to the output of the constructor component initialized in Step 1 above.
4. Configure the parameter variables, including the number of counterfactual examples you want to generate per data point.
Step 3: Use the Gather Responsible AI Insights dashboard component to present the dashboard.
Assemble and Submit the Dashboard Pipeline
1. Gather the components into a cohesive Azure ML pipeline job to execute them.
-> 2. Call the Gather RAI Insights dashboard component to aggregate the constructor and the counterfactual tool outputs.
3. Submit the pipeline job to your Azure Machine Learning workspace compute cluster for processing.
Reference:
https://oneuptime.com/blog/post/2026-02-16-how-to-implement-responsible-ai-dashboards-in-azure-machine-learning/view

Drag and Drop Question
A team deploys a machine learning model to production and monitors it continuously. Alerts are configured on performance and data quality metrics.
Multiple alerts are triggered during normal operation.
You need to perform the appropriate action for each model alert condition.
Which action should you perform for each alert condition? To answer, move the appropriate actions to the correct model alert conditions. You may use each action once, more than once, or not at all. You may need to move the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.

Correct Answer:

An Azure Machine Learning workspace contains multiple registered versions of a model that is used in production.
An older model version must no longer be deployable, but it must remain available for compliance review and potential rollback.
You need to change the state of the model version to meet the requirements.
What should you do?

• A.Archive the training dataset for the model version.
• B.Unregister the model version.
• C.Delete the model version.
• D.Archive the model version.

A team develops and manages a conversational assistant by using Microsoft Foundry.
The team requires generative AI to automatically evaluate every pull request of an agentic application and fail the build if safety thresholds are exceeded.
You need to automate evaluations as part of CI.
What should you configure?

• A.Retrieval chunking strategy
• B.Blocklist applied to the model endpoint
• C.Content filter configured in warning mode
• D.GitHub Actions workflow that executes the runs