AI-102 Plan and manage an Azure AI solution Practice Question
Exhibit
{
"policies": [
{
"name": "AllowAllText",
"contentSource": {
"sourceType": "allowed",
"contentTypes": [
"ControlledMaterial",
"Normal"
]
}
},
{
"name": "BlockHateSpeech",
"severityThreshold": {
"Hate": "high",
"SelfHarm": "medium"
}
}
]
}Refer to the exhibit. You are configuring content filtering for an Azure OpenAI deployment using a JSON policy. You want to block all content with a 'Hate' severity of 'medium' or higher. What should you modify in the policy?
⚠ Common exam trap
It's easy for candidates to confuse 'severityThreshold' with a 'block' action flag, thinking they need to add an explicit block action, or they mistakenly adjust a different category's threshold instead of the correct one.
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
✓
Modify the "severityThreshold" for "Hate" to "medium".
In Azure OpenAI content filtering, the 'severityThreshold' for a given category (like 'Hate') defines the minimum severity level at which content is filtered. Setting it to 'medium' means all content with a severity of 'medium' or higher (including 'high') will be blocked, which matches the requirement to block 'Hate' severity 'medium' or higher.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Change the "severityThreshold" for "SelfHarm" to "low".
Why it's wrong here
SelfHarm threshold does not affect Hate filtering.
- ✗
Change the "contentTypes" to include only "Normal".
Why it's wrong here
contentTypes control which content types are allowed, not severity.
- ✓
Modify the "severityThreshold" for "Hate" to "medium".
Why this is correct
Setting the threshold to 'medium' blocks all hate content at medium severity and above.
- ✗
Add a "policyAction" with "block" to the "BlockHateSpeech" policy.
Why it's wrong here
The block action is implicit; no need to add explicitly.
Go deeper
Related to this question
About these practice questions
One of 945 original AI-102 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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 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-102 exam.