telemetry.dev
An observability platform that traces every model and tool call in an AI agent run, with tokens, cost, latency and errors in one view.
Category
Explore 3+ ai research evaluation tools for researchers, analysts, and program teams. Measure outcomes, organize evidence, and report results clearly. Compare evaluation criteria, reporting, and export options to find the right fit.
Explore the tools currently published in this category.
An observability platform that traces every model and tool call in an AI agent run, with tokens, cost, latency and errors in one view.
A free tool that reads your public GitHub repositories and maps the AI skills your code actually demonstrates across six domains.
Voice agent testing with configurable AI callers, call recordings, transcripts and evaluations.