AI-103 Certification Practice Question #19

Question

You have a Microsoft Foundry project that contains a high-traffic agent.
After a recent update, operational costs increase significantly.
Monitoring confirms that the volume of user traffic to the agent remains unchanged.
You suspect that changes to the request or response characteristics are causing the increase. You need to identify whether the additional costs are driven by the model input size, the model output size, or expanded tool usage.
Which observability capability should you use?

Accepted Answer

Traffic volume is unchanged but cost rose, so the increase must come from per-request characteristics — larger inputs, larger outputs, or more tool calls. Since Azure OpenAI/Foundry bills primarily on tokens, the observability capability that decomposes cost into input tokens, output tokens, and tool-driven token expansion is token usage. Latency, evaluation metrics, and run success rate measure responsiveness, quality, and reliability respectively, none of which explain a cost change. Suggested Answer and MS Learn agree.

More AI-103 practice questions