Field reference:
monitoring — every field, type, default, and tier for this page.Health snapshot
The Health section at the top of the page summarises traffic for a window you pick from the dropdown (1h, 6h, 24h, 72h, 7d). Click the refresh icon to re-fetch.
The four headline cards show:
Below the cards:
- Queries per hour — a bar chart over the window with errored queries layered in red.
- Top tools called — the most-invoked tools, sized by call count.
- Recent errors — the latest errored queries with timestamp, the access surface (web, API, MCP, etc.), and error message.
In practice
Catch a regression fast. Glance at the Error rate card after a config change. If it’s gone yellow (>2%) or red (>10%), check Recent errors for the message and surface, and the Queries per hour chart to see when the spike started — usually right after the change you just made. Find your cost drivers. The Top tools called panel shows where the agent spends its effort. A tool you expected to be rare dominating the list often means the agent is over-reaching for it — tighten that tool’s description or add a rule. Pair with the Spend card to watch cost per window. Go deep on one conversation. When the health snapshot isn’t enough — you need to see exactly what one bad conversation did — open it on the Conversations page and flip to the harness view for the full step-by-step record. See Observability and debugging.Manage via the Management MCP
The eval criteria and alert rules behind this page can be managed via the Management MCP.
See the
monitoring field reference for the criteria and alertRules shapes.