Your organization has a Microsoft Foundry Service resource that is used by multiple teams for AI model training. You need to identify which teams are consuming the most compute hours and how that correlates with cost. You must minimize the effort required to produce this report. What should you do?

Configure Azure Monitor alerts to notify you when compute usage exceeds a threshold, then use the alert history to estimate costs.

Enable diagnostic settings to send resource logs to a Log Analytics workspace, then run a KQL query that joins resource logs with cost data.

Use the Metrics blade in the Azure portal to view CPU usage per team, then manually export the data to Excel for cost analysis.

Use the Azure Cost Management + Billing blade to export cost data to a storage account, then manually match it with usage logs.

Your organization uses a Foundry service for batch inference jobs that run nightly. The finance team reports that costs have increased significantly over the past month. You need to identify which specific models and endpoints are driving the cost increase. What should you do?

Set up a budget alert at the subscription level and wait for the next month's invoice to analyze the charges.

Export the Foundry service activity logs to a Log Analytics workspace and query for all 'deploy' operations.

Review the Foundry service's built-in metrics for total token consumption and compare with the previous month's invoice.

Use Azure Cost Management to filter Foundry service costs by resource, meter, and tag, and correlate with endpoint usage logs.

What is the recommended practice for protecting account keys used to access an Azure AI resource?

Embed keys directly in client application code

Store keys in Azure Key Vault and rotate them regularly

Share keys with all team members for convenience

Disable key regeneration to keep keys stable

Microsoft Certified:Azure AI Engineer Associate

Domain 1Objective 3

Manage, Monitor, and Secure a Microsoft Foundry Service AI-102 Practice Questions (Page 7)

Part of the Plan and manage an Azure AI solution domain, which accounts for 20-25% of the AI-102 exam. Microsoft does not publish an official question count, but from its 100-minute exam (~40–65 total, ~8–16 in this domain), expect 2–4 from this objective — we provide 34 practice questions to prepare you well beyond it. (estimate)

34questions here

7free pages

4concepts

20-25%of the exam

Questions 31–34

31application · medium
Your organization has a Microsoft Foundry Service resource that is used by multiple teams for AI model training. You need to identify which teams are consuming the most compute hours and how that correlates with cost. You must minimize the effort required to produce this report. What should you do?
Select an answer first
32foundation · easy
Which authentication method is recommended for an application running on Azure to access an Azure AI resource without storing keys?
Select an answer first
33application · medium
Your organization uses a Foundry service for batch inference jobs that run nightly. The finance team reports that costs have increased significantly over the past month. You need to identify which specific models and endpoints are driving the cost increase. What should you do?
Select an answer first
34foundation · easy
What is the recommended practice for protecting account keys used to access an Azure AI resource?
Select an answer first

Finished these 4 questions?

Review the revealed explanations, or continue through the curriculum.

No more pagesBack to AI-102

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Microsoft. “AI-102” is a trademark of its owner, used for identification only.

Manage, Monitor, and Secure a Microsoft Foundry Service AI-102 Practice Questions (Page 7)

Questions 31–34

Your organization has a Microsoft Foundry Service resource that is used by multiple teams for AI model training. You need to identify which teams are consuming the most compute hours and how that correlates with cost. You must minimize the effort required to produce this report. What should you do?

Which authentication method is recommended for an application running on Azure to access an Azure AI resource without storing keys?

Your organization uses a Foundry service for batch inference jobs that run nightly. The finance team reports that costs have increased significantly over the past month. You need to identify which specific models and endpoints are driving the cost increase. What should you do?

What is the recommended practice for protecting account keys used to access an Azure AI resource?

Keep studying — Plan and manage an Azure AI solution