AB-100 Certification Practice Question #110

Question

A company has a Microsoft Foundry agent that summarizes customer feedback and recommends products to customers. The agent references data from multiple knowledge sources.

Users report that the agent response time is slow.

Telemetry data shows that the agent frequently reaches its token usage limit.

You need to recommend a solution to reduce token usage without degrading the quality of the generated responses.

What should you recommend?

Accepted Answer

The question requires reducing token usage without degrading response quality. Option D (lower the token limit) directly degrades quality by truncating answers. Option B (reduce knowledge sources) removes information, risking degraded answers. That leaves A and C. Chunking (A) is an indexing-time optimization that improves retrieval precision, but it doesn't directly control how much content is pulled into the prompt at inference time. Reconfiguring prompts to limit retrieved content (C) is a direct retrieval-scope control — instructing the agent to fetch only the most relevant chunks per query — which is the standard Microsoft-recommended approach for Foundry agents hitting token ceilings. MS Learn RAG documentation confirms that controlling retrieved passage volume is the primary lever for token reduction. The suggested answer and community vote both align on C.

More AB-100 practice questions