AI-102 Implement generative AI solutions Practice Question
You are designing a generative AI solution using Azure OpenAI Service. The solution must meet compliance requirements by preventing the model from generating sensitive personal data. Which TWO configurations should you implement? (Select TWO.)
⚠ Common exam trap
Watch out — candidates often choose a system message (Option C) as a reliable control, but Microsoft explicitly warns that system messages are not a security boundary and can be bypassed, whereas DLP and content filters provide enforceable guardrails.
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
✓
Implement data loss prevention (DLP) policies using Microsoft Purview
Microsoft Purview DLP policies can scan and block sensitive data (e.g., PII, credit card numbers) in prompts and responses when integrated with Azure OpenAI Service, ensuring compliance by preventing data exfiltration. Azure AI Content Safety content filters allow you to configure severity thresholds to block harmful or sensitive content categories, directly preventing the model from generating personal data at the inference layer.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Implement data loss prevention (DLP) policies using Microsoft Purview
Why this is correct
DLP policies provide data governance and protection.
- ✓
Configure content filters in Azure AI Content Safety
Why this is correct
Content filters can block sensitive data patterns.
- ✗
Add a system message instructing the model not to generate personal data
Why it's wrong here
System messages are not enforced and can be bypassed.
- ✗
Deploy the model in a specific region
Why it's wrong here
Region deployment does not prevent generation of personal data.
- ✗
Fine-tune the model with a dataset that excludes personal data
Why it's wrong here
Fine-tuning does not guarantee the model won't generate personal data.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 945-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 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.