Your AI agent just took 45 seconds to answer a simple question. Was it the model? A slow tool call? A retry loop? Every time an application calls an LLM, a chain of model calls, tool invocations, and token exchanges happens behind the scenes — and without observability, you are guessing.
The OpenTelemetry Semantic Conventions for Generative AI give you that visibility. They standardize how GenAI operations are recorded — the model being called, input and output token counts, and when opted in, the full content of prompts, completions, tool calls, and tool results.

OpenTelemetry's platform is an observability framework, offering insights into distributed tracing, metrics collection, and log management for cloud-native applications. Through documentation, tutorials, and community contributions, OpenTelemetry provides insights into instrumenting applications to monitor performance and troubleshoot issues. Developers and DevOps teams can learn about distributed tracing standards, telemetry data formats, and integration with observability tools to gain visibility into complex distributed systems.

OpenTelemetry

OpenTelemetry's Semantic Conventions for Generative AI provide standardized observability for LLM-powered applications. The walkthrough covers exporting GenAI telemetry from VS Code Copilot (and other tools like Claude Code and OpenAI Codex), configuring the Aspire Dashboard as a local OTLP-compatible backend, and exploring traces, metrics, and events. Key attributes include model names, token counts, finish reasons, and optionally full prompt/response content. Metrics like operation duration and token usage help estimate costs, detect latency regressions, and monitor usage patterns across models and agents.

Inside the LLM Call: GenAI Observability with OpenTelemetry