Q
A company has a Microsoft Copilot Studio agent that uses Azure OpenAI to generate responses and retrieves grounding data from Microsoft Dataverse.
Multiple users can modify the agent's configurations, including the model behavior and data access settings. The company's security team requires that changes affecting the model be traced back to specific users.
You need to recommend a solution that protects the model by providing accountability for the configuration changes.
What should you recommend?
Question Info
Choose the Best Option
Click any option to instantly check if you're correct.
Explanation
Objective:
3.4 Design responsible AI, security, governance, risk management, and compliance
What This Item Tests:
Design model security
Additional Reading:
Apply responsible AI principles
Rationale:
Enabling comprehensive auditing in Power Platform and the Dataverse environment provides an auditable record of which users changed model-related configurations and data access settings, supporting accountability and protection of the model's integrity. DLP policies, continuous access evaluation, and secret storage meet other security concerns but do not provide traceability for configuration changes that affect the model behavior.
Share This Question
Challenge a friend or share with your study group.