AI-103: Developing AI Apps and Agents on Azure

By Microsoft · Question Mode

QuestionQ58

VerifiedImplement generative AI and agentic solutions

You have a Microsoft Foundry project that contains a prompt agent used by a customer support web app.

The agent is invoked from a Python service that does not run in the Foundry portal.

You need to implement end-to-end tracing to capture latency breakdowns and exceptions across agent runs.

Which two components can you use? Each correct answer presents a complete solution.

NOTE: Each correct selection is worth one point.

Choose two
Explanation

OpenTelemetry lets you instrument the external Python service to emit standardized spans covering LLM calls, tool invocations, latency, and exceptions even though it runs outside the Foundry portal, and Application Insights (Azure Monitor) is the backend Microsoft Foundry uses to ingest, store, and visualize those OpenTelemetry traces end to end. Together they form a complete, code-level tracing solution for an agent invoked from external code. A Log Analytics workspace is only the underlying data store behind Application Insights rather than a tracing capability in its own right, and Azure Monitor Agent and Microsoft Sentinel are infrastructure-monitoring and SIEM tools, not per-run agent tracing mechanisms.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!