Observability overview
See every execution across your project — health metrics, per-agent and per-workflow rollups, and what's running now.
Observability is where you watch and understand everything your AI does at runtime. Every dispatch — deployed or not, triggered any way — produces an execution, and an execution is a trace: a complete, step-by-step record of what happened. Observability gathers all of them in one place, under Console → Observability.
Project metrics
The top of the page summarizes the whole project's recent health:
- Executions · 30d — how many executions in the last 30 days.
- Success rate — the share that completed successfully.
- p95 latency — how long executions take at the 95th percentile, with the average alongside.
- Active now — how many executions are in flight right this moment.
By agent and workflow
Below the metrics, a table rolls up activity per agent and per workflow that has run:
- total executions,
- success rate (highlighted when it dips below 90%),
- average duration,
- total tokens used,
- and last execution time.
The table is sortable, so you can quickly find the busiest, slowest, or most error-prone piece of work. Select any row to drill in.
Drilling into one agent or workflow
Opening a row focuses on that single agent or workflow: a header with its rollup metrics (total executions, success rate, average duration, total tokens, last execution) and how many are running right now, followed by an executions list filtered to just its executions.
Watching live
Executions in progress show up immediately — the Active now count and a live indicator mark anything currently running, and you can open an in-flight execution to watch it stream in real time.