Skills
Instrument agents with OpenTelemetry GenAI/OpenInference conventions so traces stay portable across eval vendors
The OpenTelemetry GenAI semantic conventions give a vendor-neutral schema for agent traces, and open-source tools (Phoenix, Langfuse) plus managed ones (LangSmith, Weave) build on OTel/OpenInference. Instrumenting to the standard schema now means your trajectory data — LLM calls, tool invocations, intermediate outputs, error states — moves between observability backends without re-instrumentation. The conventions are still marked experimental in 2026, but adopting them early avoids lock-in to a single dashboard's proprietary trace format.
Source
↳ Follow the thread