AI-102 Implement generative AI solutions Practice Question
Your team is building an internal knowledge assistant with Azure OpenAI Service. Legal requires that every generated answer include a traceable reference to the source document so reviewers can verify claims. The documents already live in Azure AI Search, and you want the service to return citation metadata alongside the generated text. Which feature should you configure?
⚠ Common exam trap
The trap here is assuming that a prompt instruction or diagnostic logging yields verifiable citations, when citation metadata must come from the retrieval integration that actually tracks which documents grounded the answer.
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
✓
The On Your Data feature configured with an Azure AI Search data source, which returns citations with the response.
On Your Data integrates an Azure AI Search index as the grounding source and returns the model's answer together with citation information identifying the retrieved documents. Because the documents already live in Azure AI Search and the requirement is traceable references in the output, this feature directly provides the needed attribution without custom retrieval code.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Azure OpenAI content filtering with annotating models enabled on the deployment.
Why it's wrong here
Content filtering with annotations flags potentially harmful categories in prompts and completions, producing severity and category information. It says nothing about which source document supported a statement, so reviewers would still be unable to trace an answer to its origin. Enabling annotations may help with safety review, but it does not satisfy the legal requirement for source attribution in the generated response.
- ✗
A system message instructing the model to always mention the file name it used to answer.
Why it's wrong here
Prompt instructions influence tone and format but rely on the model to remember and truthfully report its sources, which it cannot reliably do because retrieved chunks may not carry durable file names. The model can invent or misattribute a name, producing citations that fail verification. This approach offers no structured metadata and is therefore unsuitable when legal demands traceable, verifiable references.
- ✗
Logging every request and response to Azure Monitor and querying the logs after the fact.
Why it's wrong here
Diagnostic logging records what was asked and answered, which supports auditing, but the logs do not attach source references to the answer itself. Reviewers would have to reconstruct which documents were retrieved, and the response text still lacks citations. The requirement is that each generated answer carry a traceable reference, so post-hoc log analysis does not meet it even though logging is valuable for other compliance goals.
- ✓
The On Your Data feature configured with an Azure AI Search data source, which returns citations with the response.
Why this is correct
On Your Data connects the model to an Azure AI Search index and returns the generated answer together with citation entries that identify the retrieved documents and their content. This gives reviewers the traceable references legal requires without building custom retrieval plumbing. Because the documents already reside in Azure AI Search, this configuration fits the existing environment and produces the attribution metadata in the response payload.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-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 and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
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.