AI-103 Implement Generative AI And Agentic Solutions Practice Question
When designing an evaluation pipeline in Azure AI Foundry for generative AI applications, which TWO metrics are commonly used to assess safety and risk? (Choose TWO)
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
✓
Sexual content and violence safety metrics
Hate speech, sexual content, violence, and self-harm detection metrics assess safety and risk in Azure AI Foundry evaluation pipelines.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Database transaction log growth rate
Why it's wrong here
Transaction log rates track database storage, not AI safety.
- ✗
Storage account geo-replication latency
Why it's wrong here
Replication latency monitors storage synchronization, not AI content risk.
- ✓
Sexual content and violence safety metrics
Why this is correct
Safety metrics measure the presence of harmful or explicit content in completions.
- ✗
Network bandwidth throughput in megabits per second
Why it's wrong here
Bandwidth measures network performance, not model safety.
- ✓
Hate speech and unfairness detection
Why this is correct
Hate speech metrics evaluate models for toxic or discriminatory language.
About these practice questions
Courseiva writes every AI-103 question from scratch — 510 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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.