AI-103 Plan And Manage AN Azure AI Solution Practice Question
You are deploying a model that requires significant GPU resources. You want to ensure the deployment only scales when the average CPU load exceeds 70%. Which feature of Azure AI managed endpoints do you configure?
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
The 'Endpoints' deployment configuration 'autoscaling' settings.
Autoscaling settings on Azure AI managed endpoints allow you to define rules based on resource utilization metrics like CPU or GPU load.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
The 'Load Balancer' settings in the VNET.
Why it's wrong here
Managed endpoints handle scaling internally; you don't manage the load balancer manually.
- ✗
Azure Front Door health probe settings.
Why it's wrong here
Front Door routes traffic but does not manage internal AI model scaling.
- ✓
The 'Endpoints' deployment configuration 'autoscaling' settings.
Why this is correct
Autoscaling rules are defined within the endpoint deployment properties.
- ✗
The 'Compute' instance restart policy.
Why it's wrong here
Compute instances are for development, not scalable production endpoints.
About these practice questions
This AI-103 question is part of Courseiva's 510-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed August 2026 · checked against the official Microsoft exam blueprint
This AI-103 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-103 exam.