Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

You are designing a line-of-business assistant in Azure OpenAI. The assistant must

  • maintain long-running conversational context across user sessions,
  • decide at run time whether to call an internal product-catalog search REST API or an order-status REST API,
  • combine the API results with the user's original question, and
  • return a single, natural-language answer-all without writing custom orchestration code for every tool call. Which Azure-based approach best satisfies these requirements?

  • Create an Azure Bot Service bot that uses a QnA knowledge base populated with catalog and order information.

  • Fine-tune a GPT model on historical chat transcripts that include API responses so the model learns when to answer with catalog or order data.

  • Send a single chat completion request that embeds the API documentation in the system message and instructs the model to respond with the correct data.

  • Register the catalog and order REST endpoints as tools in Azure AI Foundry Agent Service and let the agent decide which to call during the dialogue.

Microsoft Azure AI Engineer Associate AI-102
Implement an agentic 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