Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

Your team is prototyping a development assistant that uses three specialized Azure AI Foundry agents (Researcher, Coder, Tester). At run time the model must decide which agent to call next and repeat the Researcher-Coder-Tester cycle until the Tester reports success or a maximum iteration limit is reached. Project managers need to inject clarifying chat messages at any point in the conversation, and the workflow should answer them before continuing without rebuilding the plan. Within Semantic Kernel, which mechanism provides this built-in iterative orchestration and human-in-the-loop support without writing external workflow code?

  • Register the three agent functions and enable FunctionChoiceBehavior.Auto so the kernel's built-in function-calling loop decides which agent to invoke until completion.

  • Create a SequentialPlanner plan that chains the agent functions inside a loop conditioned on the Tester result.

  • Publish each agent as an Azure Function and pass messages between them with Service Bus topics and subscriptions.

  • Implement the workflow in Azure Logic Apps with sequential actions and a Do-Until loop.

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