OpenTelemetry GenAI Semantic Conventions
Development-status OpenTelemetry semantics for generative AI agents, model calls, retrieval, tools, plans, evaluations, and MCP activity.
The Trace Map
Explore what each system publicly documents across identity, principal and delegation, context, decision artifacts, models, tools, effects, human control, outcomes, integrity, portability, and privacy.
6 profiles
Development-status OpenTelemetry semantics for generative AI agents, model calls, retrieval, tools, plans, evaluations, and MCP activity.
An OpenTelemetry-based semantic convention for AI model, agent, retrieval, tool, graph, evaluation, and annotation traces.
A W3C Recommendation defining interoperable HTTP trace-context propagation through traceparent and tracestate headers.
A JSON-RPC protocol for connecting AI applications to tools, resources, prompts, and related capabilities, with W3C trace-context propagation.
The OpenTelemetry wire and file protocol for exporting trace, metric, and log telemetry between sources, collectors, and backends.
A vendor-neutral JSON record for attributing AI-generated code alongside human authorship in version-controlled files.
4 profiles
Built-in tracing for OpenAI Agents SDK workflows, including model calls, tools, handoffs, guardrails, and custom spans.
A stateful agent runtime whose checkpoint, thread, subgraph, replay, and interrupt semantics can preserve execution state independently of an observability backend.
A coding-agent and SDK family with local session JSONL, subagent hierarchy, tool permission decisions, hooks, OTel spans/events, and W3C trace propagation.
A coding-agent CLI with a public JSONL event stream and opt-in OpenTelemetry logs, metrics, and traces for execution, plans, tools, approvals, usage, and outcomes.
5 profiles
An observability and evaluation platform with an explicit run/trace/thread model, rich execution payloads, export APIs, distributed context, and capture controls.
An OpenTelemetry-rooted observability platform with typed generation, agent, tool, retriever, evaluator, and guardrail observations plus export and privacy controls.
An open-source observability and evaluation platform that accepts OTLP traces and uses OpenInference semantics for model, retrieval, agent, and tool activity.
An observability and evaluation platform with nested application spans, OTel ingestion, raw JSON, query export, scoring, masking, and separated data-plane options.
An OTel-compatible application and evaluation tracing system with explicit spans, OTLP import/export, feedback, masking, archive, retention, and deletion controls.
Documentation view
Need the detail?