AI-102 Implement an agentic solution Practice Question
You are configuring an agent in Azure AI Foundry Agent Service to generate responses based on a large set of internal documents. The documents are stored in an Azure Storage account. You need to ensure the agent can retrieve relevant information from these documents to answer user queries. What should you do?
⚠ Common exam trap
The trap here is assuming that file upload or direct concatenation can handle large document sets, but they are limited by size and token constraints.
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 documents and connect it to the agent as a knowledge source.
For large document sets, Azure AI Search provides scalable indexing and retrieval. By creating an index and connecting it as a knowledge source, the agent can query the index and retrieve relevant passages. This is the recommended approach for grounding agent responses in extensive internal documents.
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 documents and connect it to the agent as a knowledge source.
Why this is correct
Azure AI Search is designed to index and query large volumes of documents. By creating an index and connecting it to the agent, you enable the agent to retrieve relevant information based on user queries. This approach scales well and provides advanced search capabilities like semantic ranking.
- ✗
Upload the documents to the agent's file storage and enable the file search tool.
Why it's wrong here
Uploading documents directly to the agent's file storage is limited by size and quantity constraints. For a large set of documents, this approach is impractical and may exceed limits. Instead, you should use a dedicated search service that can index and retrieve from large document sets efficiently.
- ✗
Use the Azure AI Foundry SDK to embed the documents into the agent's prompt by concatenating their contents.
Why it's wrong here
Concatenating a large set of documents into the prompt is not feasible due to token limits and would result in poor performance. It also lacks the ability to selectively retrieve relevant information. A search-based approach is necessary for scalability and relevance.
- ✗
Configure the agent to use a custom tool that calls the Azure Storage REST API to fetch documents on demand.
Why it's wrong here
While a custom tool can fetch documents, it would require the agent to know which documents to retrieve and would not provide relevance ranking. This approach is inefficient for large document sets and does not leverage built-in search capabilities. It also adds complexity in handling authentication and pagination.
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.