Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

In an Azure AI Studio project, you plan to answer employee questions about 10,000 internal PDF manuals stored in Azure Blob Storage. You must minimize hallucinations, include source citations, and avoid retraining the model. Which approach should you implement before calling the gpt-35-turbo deployment from your prompt flow?

  • Create a data source connection that indexes the PDFs in Azure AI Search with semantic vector search, then attach the connection to an Index Lookup tool in your prompt flow so the model receives the top passages at runtime.

  • Call the chat completion endpoint with temperature set to 0 and a higher max_tokens value so the model can recall more facts.

  • Fine-tune gpt-35-turbo on the extracted text of the PDFs and deploy the custom model in the project.

  • Enable content safety filters and define a strict user content policy in the system message to reduce hallucinations.

Microsoft Azure AI Engineer Associate AI-102
Implement generative AI solutions
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