Skip to content
Back to full roadmap
topiccore

Production Observability Stack

Langfuse / LangSmith / Helicone / Phoenix — real-time monitor + trace + alert for agents.

3 hours3 resources1 prereqs

You must monitor production agents. Stack layers:

  1. Tracing: OpenTelemetry (vendor-agnostic) or OpenLLMetry (LLM-specific)
  2. Visualization: Langfuse / LangSmith / Phoenix dashboards
  3. Metrics: Prometheus → Grafana (token/cost/latency time series)
  4. Alerting: Datadog / Sentry / PagerDuty (P95 spike, error rate, cost anomaly)
  5. User feedback: thumbs up/down, comments → auto-added to eval dataset

Pro: every agent run = traceId; for support you can say "review this trace".

Prerequisites

Resources(3)