AI-103 Certification Practice Question #29

Question

You have a Microsoft Foundry project.
You plan to build a customer support solution that contains an agent. The solution must meet the following requirements:
Provide accurate, context-aware responses grounded in internal product documentation stored in Azure AI Search.
Require deep, multi-step reasoning across long contexts.
Generate detailed natural language responses.
Which type of model should you use to power the agent?

Accepted Answer

The agent must perform deep, multi-step reasoning across long contexts and generate detailed natural-language responses while staying grounded in documentation retrieved from Azure AI Search (RAG). These are the hallmark capabilities of a large language model, which serves as the generative reasoning engine of a Foundry agent. A small language model trades away the deep reasoning and long-context strength; a multimodal model adds capabilities (vision/audio) the text-only scenario doesn't need; and key-phrase extraction is a narrow analytical model that cannot generate detailed responses. The Suggested Answer (D) matches the requirements cleanly, so confidence is high; the only deduction is the absence of community confirmation.

More AI-103 practice questions