AI-103: Developing AI Apps and Agents on Azure

By Microsoft · Question Mode

QuestionQ14

VerifiedImplement generative AI and agentic solutions

You have a Microsoft Foundry project.

You are planning a customer support solution built around an agent. The solution must:

  • 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?

Explanation

Large language models are built for deep, multi-step reasoning over long context windows and for producing detailed, fluent natural-language output, which is exactly what grounded, retrieval-based customer-support reasoning requires. Small language models trade reasoning depth and context-window size for lower cost and latency, a multimodal model adds image/audio handling that is not called for here, and a key-phrase extraction model performs narrow text extraction rather than open-ended generation and reasoning.

Community Discussion

No comments yet. Be the first to start the discussion!