#opentelemetry
-
How to Monitor LLMs in Production: Metrics and Alerts
A practitioner's guide to monitoring LLMs in production: TTFT, token throughput, output quality drift, hallucination signals, alerting, and canary deploys.
-
LLM Cost & Latency Observability with OpenTelemetry
Implement LLM cost and latency observability with OpenTelemetry: token accounting, versioned price estimates, streaming timing, and request metrics.
-
End-to-End Tracing for LLM Apps: Span Design Guide
Implement end-to-end tracing for LLM applications with request spans, context propagation, retrieval evidence, and sampling checks for incident analysis.