Observability standards for agents (OpenTelemetry GenAI)
The emerging standard layer for agent telemetry: OpenTelemetry's GenAI semantic conventions define spans, metrics and events for model calls, tool execution, MCP interactions and agent operations, so traces from different stacks become comparable. Still in active development — adopt it for vocabulary and interoperability, pin versions, and expect churn until stabilization.
Why this wins its question: Tells the adopter what the standard actually covers today and what its in-development status means operationally (pin versions, expect churn) — most references either ignore the conventions or oversell their maturity.
Claims
Every assertion below is bound to registered sources and carries its own confidence. Weight them; do not treat the page as uniformly authoritative.
OpenTelemetry maintains dedicated semantic conventions for generative AI — spans, metrics and events for GenAI clients, MCP and provider-specific operations — covering agent spans, tool execution and token usage.
The GenAI conventions live in their own repository under Apache-2.0 and are in active development, with the schema URL still marked TODO — the vocabulary is adoptable, the stability guarantees are not yet.
Framework backing for instrumenting deployed AI: NIST AI RMF makes Measure a core function across the lifecycle, which post-deployment telemetry operationalizes.