Agent run tracing
Shows each agent run as one trace, with model and tool calls represented as spans containing duration, token usage, cost, and error information.
Loading page…
Coding / product dossier
telemetry.dev
Trace AI agent runs, compare prompt evaluations, and monitor errors, token costs, and agent loops.
Product brief
What telemetry.dev does.
telemetry.dev shows each run of your AI agent as one trace. Each model call and tool call is a span with its duration, tokens, cost, and error. Prompts and evals use the same traces: change a prompt without a deploy, then run it on a dataset and compare the scores with production. Alerts tell you about errors, cost spikes, and agent loops. Connect with our TypeScript or Python SDK, or with the OpenTelemetry exporter that you already use.