Observability

Monitor workflow health with run history, logs, and metrics designed for debugging and performance tuning.

Run insights

Step-by-step execution history with inputs and outputs.

Stack traces, retries, and failure snapshots per block.

Token, provider cost, and time spent per workflow.

Human ratings, eval scores, and regression tracking.

Latency p50/p95 per block and per workflow.

Failure rate by dependency and provider.

Token usage, cache hit ratio, and cost budgets.

Queue depth, concurrency saturation, and timeouts.

Set success, latency, and cost budgets per workflow.

Send alerts to Slack, PagerDuty, or email escalation paths.

Track early-run quality for new deployments.

Replay executions with the same inputs.

Compare outputs across versions or providers.

Inspect intermediate state and block payloads.

Export logs and evidence for incident review.