Skip to content

telemetry.dev

Observability for AI agents

Visit website

Upvote this launch

Product media preview

5 launch images

About this launch

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.

Discussion

0 comments

Questions, feedback, and notes from the community.

Join the conversation

Sign in or create an account to share feedback with the maker.