Tracing
Capture every LLM call, tool use, and agent step with OpenTelemetry-based instrumentation.
Detectors
Create your first detector and start surfacing failures, hallucinations, and missed tasks.
Self-Hosting
Run traceroot on your own infrastructure.
CLI
List, inspect, and export your traces from the terminal.
traceroot Agent
Investigate traces and detector findings with an assistant that can work with your source code.
Evaluations
Run your AI system against a dataset and score every case.
Datasets
Build, version, and publish the cases you evaluate against.
Dashboards
Track your project’s latency, cost, errors, and other metrics with widgets.
Alerts
Notify your team when a metric crosses a threshold.