Launching today
telemetry.dev
LLM observability for AI agents
303 followers
LLM observability for AI agents
303 followers
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.
Free Options
Launch Team
AWS Startup AdvisorPersonalized AWS guidance that meets you where you’re already building
Promoted
@rotimi_best Thank you❤️
Congrats on the launch @ephraimduncan
@talktogoutham Thank you❤️
@german_merlo1 Thank you❤️
Swapping a prompt without deploying and scoring it against the same traces that came from production is the loop I have been faking with spreadsheets, and alerting on agent loops alone would pay for itself.