🔥 40% Off Crucial Exams Memberships — This Week Only

3 days, 10 hours remaining!

Microsoft Azure AI Engineer Associate AI-102 Practice Question

You deploy a GPT-35-Turbo model using Azure OpenAI. To reduce brand-specific risks, the compliance team requires that any prompt or completion containing the name of your company's unreleased product be blocked automatically.

You must implement the requirement without writing additional code in the client application and without disabling the built-in content filters for hate, sexual, self-harm, or violence.

Which action should you take?

  • Lower the content filter severity thresholds for all four harmful categories to the lowest level.

  • Upload a custom blocklist that contains the unreleased product name and associate the list with the model deployment.

  • Enable log redaction in the Azure portal for the deployment.

  • Switch the deployment's moderation preset from standard to stricter.

Microsoft Azure AI Engineer Associate AI-102
Plan and manage an Azure AI solution
Your Score:
Settings & Objectives
Random Mixed
Questions are selected randomly from all chosen topics, with a preference for those you haven’t seen before. You may see several questions from the same objective or domain in a row.
Rotate by Objective
Questions cycle through each objective or domain in turn, helping you avoid long streaks of questions from the same area. You may see some repeat questions, but the distribution will be more balanced across topics.

Check or uncheck an objective to set which questions you will receive.

Bash, the Crucial Exams Chat Bot
AI Bot