Q
A company has two production agents: One is built in Microsoft Copilot Studio, and the other is built in Microsoft Foundry. Both agents send telemetry to the same Azure Monitor Application Insights resource.
Users report intermittent slow responses.
You confirm that the slowdowns correlate with spikes in token usage.
You need to identify agent runs that have the highest token usage and review the related model and tool calls across both agents from a single monitoring experience.
What should you use?
Question Info
Choose the Best Option
Click any option to instantly check if you're correct.
Explanation
Objective:
Analyze, monitor, and tune AI-powered business solutions
What This Item Tests:
Recommend the process and tools required for monitoring agents
Additional Reading:
Monitor AI agents with Application Insights
Monitor and analyze AI Agent usage and performance
Rationale:
The Agent details view provides an agent-centric execution history that sorts runs by token usage and drills into traces, dependencies, and tool calls across multiple agents. Metrics Explorer shows aggregated metrics without execution detail, Copilot Studio analytics is limited to Copilot Studio agents, and Azure Monitor workbooks support visualization but cannot surface or correlate individual agent runs or their detailed telemetry.
Share This Question
Challenge a friend or share with your study group.