AI-300 Genaiops Infrastructure Practice Question
Your team is using Semantic Kernel for agent orchestration. You notice frequent transient errors when the agent interacts with multiple LLM services. How should you implement infrastructure-level resiliency?
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
✓
Use an 'Azure API Management' policy to implement a retry pattern.
Implementing exponential backoff and retries via the 'RetryHandler' in the HttpClient factory or Semantic Kernel settings is the standard approach for infrastructure-level resiliency.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Disable the 'Streaming' flag in the agent request.
Why it's wrong here
Streaming is independent of connection reliability.
- ✓
Use an 'Azure API Management' policy to implement a retry pattern.
Why this is correct
APIM policies provide a robust, centralized mechanism to handle retries for LLM endpoints.
- ✗
Switch the model to a higher tier instance type.
Why it's wrong here
Instance size does not mitigate transient network errors.
- ✗
Increase the 'Timeout' parameter in the model deployment manifest.
Why it's wrong here
Timeout settings do not handle transient network failures.
About these practice questions
One of 204 original AI-300 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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-300 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-300 exam.