AI-103 Certification Practice Question #17

Question

You have a Microsoft Foundry project that serves a high-volume chat app.
Most requests are simple FAQs, but some require advanced reasoning.
You need to reduce costs and latency for common queries, without degrading the quality of the responses to complex questions.
What should you do?

Accepted Answer

The goal is to cut cost and latency for common/simple queries while keeping quality on the rare complex ones. A model cascade / router does exactly this: simple FAQs go to small fast models and only hard prompts escalate to capable models, lowering average cost and latency without sacrificing complex-query quality. Routing everything to a small model (A) sacrifices quality on the complex questions, routing everything to the most capable model (D) is the costly status quo, and raising `max_tokens` (C) is unrelated to the routing problem. Suggested Answer and the Foundry model-router/traffic-shaping guidance align.

More AI-103 practice questions