Microsoft Azure AI Engineer Associate AI-102 Practice Question

You have a Conversational language understanding project named SupportBot that is already deployed to production with the deployment name "prod". After adding new labeled utterances, you retrain the model. QA engineers must run tests against the new model while customers continue to use the existing model. Which action should you take?

  • Export the project and import it into a separate Azure AI Language resource in the same region for testers to use.

  • Publish the retrained model to the existing "prod" deployment and roll back if tests fail.

  • Create a new deployment that references the retrained model and give its endpoint to the QA engineers.

  • Enable evaluation mode in Language Studio so that 10% of production traffic is automatically routed to the new model.

Microsoft Azure AI Engineer Associate AI-102
Implement natural language processing 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.

Bash, the Crucial Exams Chat Bot
AI Bot