![]() |
VOOZH | about |
This guide explains how you can use both Agent Observability and APM to correlate Agent Observability and APM spans in Datadog.
By instrumenting your LLM-specific operations with Agent Observability and your broader application with APM, you can accomplish the following:
The Agent Observability SDK is built on APM’s dd-tracer. This allows you to use Agent Observability with Application Performance Monitoring (APM)
If you are using the Agent Observability SDK for Python along with APM’s dd-tracer, you can navigate between spans in Datadog APM and Agent Observability without additional setup.
If you are using the Agent Observability API with dd-tracer for APM:
span.Context().SpanID() for the Go tracer).By using this integration, you can correlate data across your application stack and understand how your LLM applications interact with other components. You can also resolve issues more quickly and optimize your application’s performance.
To understand the broader context of your LLM operations within your application ecosystem, select an Agent Observability span in the Agent Observability Explorer and click APM span to navigate to the relevant APM span.
To access LLM-specific insights, select an APM span in the Trace Explorer and click View Span in the Agent Observability section on the Info tab to navigate to the corresponding Agent Observability span.
Additional helpful documentation, links, and articles:
| |