AI-102 Implement generative AI solutions Practice Question
You are developing a chat application that uses Azure OpenAI Service to answer customer queries. You need to ensure that the model does not generate responses containing internal company policies or confidential information. Which approach should you use?
⚠ Common exam trap
A common mix-up: candidates confuse content filtering (Option D) with instruction-based control, assuming that post-generation detection is equivalent to prevention, when in fact the system message (Option C) directly instructs the model's behavior before output is generated.
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
✓
Set the system message to instruct the model not to include confidential information.
Setting the system message in Azure OpenAI Service allows you to define high-level behavioral instructions for the model, such as prohibiting the disclosure of internal policies or confidential information. This approach leverages the model's instruction-following capability without requiring retraining or external filtering, making it a direct and effective guardrail for content generation.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use Azure AI Search with index filtering to exclude documents with confidential info.
Why it's wrong here
This affects retrieval, not the generative model's output.
- ✗
Fine-tune the model on a dataset that excludes confidential information.
Why it's wrong here
Fine-tuning reduces but does not eliminate risk; model may still produce unwanted content.
- ✓
Set the system message to instruct the model not to include confidential information.
Why this is correct
System messages guide model behavior effectively for content restrictions.
- ✗
Configure Azure AI Content Safety with custom categories for confidential terms.
Why it's wrong here
Content Safety filters after generation, but doesn't stop model from generating internal info.
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.