← Platform
Observability
Every agent action, tool call, decision — auditable.
Debug failures, prove compliance, and catch regressions on one trace pane.
Trace
wf-2847-trace-9f1e
4.8s total
workflow.execute
4800ms
activity.extract_documents
1200ms
tool.pdf_parse
400ms
llm.classify · claude-sonnet-4-6 · 1,284 tok · $0.009
800ms
activity.validate · retry · 1
2000ms
activity.request_approval · pending
—
Structured run evidence Tokens · cost · eval
One run, every span · 4.8s total · LLM, tool, activity spans
What you can see
If it happened in a run, it's in the trace.
Nested spans, no gaps
Workflow, activity, tool call, model response — one trace, every level.
Details
Catch regressions before deploy
Golden test sets flag quality regressions before an agent ships.
Details
Per run, per agent, per version
Token cost, wall time, retries — aggregated by policy version.
Details
Exports to your stack
Your SRE and compliance teams keep their tools.
AI traces
Prompts, tool use, costs, model responses.
Details
Telemetry export
Send traces to existing APM and SIEM.
Details
Operations metrics
Run health alongside agent performance.
Details
Compliance feed
Ship raw spans into audit pipelines.
Details
Observability for auditors and engineers.
See end-to-end tracing on a real workflow.