Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

You have deployed gpt-35-turbo on Azure OpenAI Service to generate answers for your company's employee portal. Certain internal project code names (for example, "Apollo" and "Zeus") must never appear in either the prompt or the model's response, even if a user explicitly requests them. You need a repeatable, centrally managed solution that will automatically block these terms without requiring changes in every client application. Which approach should you use?

  • Call the text moderation endpoint after each completion and discard any response that contains a forbidden term.

  • Configure stop sequences with the forbidden words so the model immediately ends generation when they appear.

  • Add a system message to every request that instructs the model never to reveal the forbidden code names.

  • Create a custom text blocklist in Azure AI Content Safety and attach it to a content-filter policy that is assigned to the gpt-35-turbo deployment.

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.

Wipe Score
Bash, the Crucial Exams Chat Bot
AI Bot