Tutorials · Chapter D (4/4) · ~10 min
Production monitoring lab
Try it → see it → read → next
Watch **latency, quality, and cost** after deploy — alert, rollback, or investigate with traces.
On paths: Builder
Optional on: Professional · Optional on: Student
Try tools: Code & developers
Try yourself
Playground
Production alert desk
Monitor quality, latency, and cost — alert vs rollback vs watch.
p95 latency 3× baseline
Recap
What you just did
You chose alert vs rollback vs watch for live signals.
Read
Minimum dashboard
| Metric | Action |
|--------|--------|
| [p95 latency](/reference/p95-latency) | Page if > 2× baseline |
| Citation / groundedness rate | Rollback if −30% day-over-day |
| Error rate on /api/chat | Alert on 5xx spike |
| Token spend | Budget alert |