AI-102 Implement generative AI solutions Practice Question
You are implementing a generative AI solution using Azure OpenAI Service. The solution must generate responses that are grounded in your organization's proprietary documents and must return citations that link back to the source documents. You need to configure the deployment to meet these requirements. Which two actions should you perform? (Choose two.)
⚠ Common exam trap
The trap here is assuming fine-tuning can supply both grounding and citations, when citations depend on a search index and a data source binding rather than on model training.
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
✓
Create an Azure AI Search index that contains the proprietary documents with retrievable content and citation fields such as title and URL.
Grounded responses with citations in Azure OpenAI require a retrieval source and a deployment-level data source binding. An Azure AI Search index holds the proprietary documents with content and citation metadata, and associating that index with the model deployment through On Your Data enables service-side retrieval, prompt injection, and citation 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.
- ✓
Create an Azure AI Search index that contains the proprietary documents with retrievable content and citation fields such as title and URL.
Why this is correct
Grounding and citations require a searchable index whose documents expose content plus metadata fields like title and URL. Azure AI Search provides the retrieval layer that the Azure OpenAI On Your Data feature queries. Without an index containing retrievable content and citation fields, the service cannot retrieve relevant chunks or produce source links, so this action is required.
- ✗
Enable diagnostic logging on the Azure OpenAI resource to capture prompt and completion text.
Why it's wrong here
Diagnostic logging records operational and request data for monitoring and auditing. It does not retrieve proprietary documents, inject context into prompts, or generate citations. While useful for compliance, it is unrelated to the grounding and citation requirements, so it is not a required configuration action here.
- ✗
Fine-tune the model on the proprietary documents so it can reproduce them verbatim.
Why it's wrong here
Fine-tuning adjusts model behavior and style but does not provide retrieval or citation links to source documents. It also risks memorizing content without traceability and requires retraining when documents change. Because the requirement is grounded responses with citations, fine-tuning does not fulfill either condition and is not one of the required actions.
- ✓
Associate the Azure AI Search index as a data source on the model deployment by using the Azure OpenAI On Your Data configuration.
Why this is correct
Attaching the index as a data source on the deployment enables the service-side retrieval-augmented generation flow. At inference, the service queries the index, injects retrieved chunks into the prompt, and returns citations based on document fields. This is the configuration step that connects the model to the proprietary content and enables citation output, so it is required.
- ✗
Deploy a second model instance in a different Azure region for high availability.
Why it's wrong here
A second regional deployment improves resilience and latency but does not create retrieval or citation capability. Grounding still depends on a search index and data source configuration. Because the scenario asks for grounded answers with source links, adding another deployment does not satisfy the requirements and is not a required action.
Go deeper
Related to this question
About these practice questions
One of 761 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 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.