Câu 22: AI-103: Developing AI Apps and Agents on Azure

You have a Microsoft Foundry project that contains a customer support agent. The agent calls an internal knowledge API tool before generating responses. Users report the following issues:Some requests take more than 15 seconds to complete. Some responses are incorrect, even when the knowledge API returns the expected data. You need to inspect individual agent runs to view the ordered sequence of large language model (LLM) calls, tool invocations, and timing information. Which observability capability should you use?

1. A. token usage
2. B. monitoring
3. C. safety metrics
4. D. tracing — đáp án hiện tại