Skip to main content
Already instrumented with OpenTelemetry? Point any OTel SDK, auto-instrumentation library, or Collector otlphttpexporter straight at the engine - no AgentX SDK needed:

​
Wire formats

​
Attribute conventions

Each incoming span becomes one trace row, with input/output/model/token counts pulled from whichever convention the instrumentation actually sends: The framework label resolves from the signal itself: gen_ai.provider.name, then gen_ai.system, then the instrumentation scope name, then service.name, then the literal otel - so OTel traffic charts on Monitor’s Platforms chart and filters in Observe → Live Traces without any extra attribute. Monitor runs against every OTel-ingested root span by default; set AGENTX_OTEL_MONITOR=false to turn that off.

​
First-class citizenship

Four attributes make OTel traffic part of the full loop, not just rows in Live Traces:
  • Sessions - set session.id, gen_ai.conversation.id, or agentx.session_id and traces group into conversations on the Sessions surface, with session judging applying exactly like SDK traffic. Without one, spans still group by OTel trace id.
  • Prompt identity - set agentx.prompt_name (and optionally agentx.version) and the whole Improve loop lights up: prompt-registry evidence gathering and version comparison treat the trace as if the SDK had tagged it.
  • Span kinds - openinference.span.kind, gen_ai.operation.name, mlflow.spanType, and langfuse.observation.type are read (in that order) and stored as the span’s stated kind, so a span instrumented for OpenInference or the GenAI semconv arrives in the Execution Timeline already classified - LLM, tool, retrieval, guardrail - instead of being inferred from names.
  • Tool calls - a child span carrying gen_ai.tool.name (or an MLflow TOOL-typed span) is folded up into its root interaction’s tool_calls, with success/error derived from span status - so Tool quality, the built-in Tool-failure check, and Tool Schema evidence all work on OTel traffic. In-batch only: a parent exported in an earlier OTLP batch isn’t updated retroactively.

​
Limits

  • 5,000 spans per export request. A larger batch is refused with HTTP 413 before any span is processed, so a conforming exporter can split and resend without duplicates. The OTel SDK’s default batch size is 512, an order of magnitude below the cap.
  • 10 MB request body cap on the OTLP endpoint.
  • Child spans are skipped by Monitor by default - only root spans (no parent) are checked, matching how Braintrust and Langfuse scope online scoring. Set AGENTX_MONITOR_CHILD_SPANS=true to check every span instead.

​
Verify it’s flowing

Send one span, then check Observe → Live Traces - OTel spans arrive with their full span tree (Timeline and Graph views) whenever the instrumentation emits parent/child links. OTel traffic is first-class downstream too: online judge scorers sample and score it, low verdicts raise Signals, and the traces carry judge scores in Live Traces - exactly like SDK-ingested traffic. The runnable proof is monitor_ops/07_otel_ingest_scoring.py in the sample-scripts repo: pure-OTel export, then the judge’s verdict and the raised Signal read back.
Popular auto-instrumentation packages (openinference-instrumentation-langchain, OpenLLMetry’s SDK, MLflow Tracing) all export full span trees - one env var and your existing instrumentation becomes AgentX’s data source.