Tracing, cost, and quality signals from production — where the real eval set comes from.
11 articles
Listed inLLM ObservabilityObservabilityon
Chip Huyen assembles the whole reference architecture step by step — context, guardrails, routing, caching, observability.
Listed inTracing & LoggingObservabilityon
Spans across retrieval, tool calls, and generations in one trace.
Listed inPostHogObservabilityon
Product analytics alongside LLM traces, so quality ties back to behaviour.
Listed inLangfuseObservabilityon
Open-source tracing, prompt management, and evaluation — including the data model behind a trace.
Listed inArize AIObservabilityon
ML and LLM observability with drift and embedding analysis.
Listed inLangSmithObservabilityon
Tracing, datasets, and evals from the LangChain team.
Listed inCost & Latency MonitoringObservabilityon
Per-request token accounting and the p95 that users actually feel.
Listed inLLM ObservabilityObservabilityon
Seeing what your system actually did, not what you assumed it did.
Listed inHeliconeObservabilityon
A proxy that adds logging, caching, and rate limiting with one URL change.
Listed inLangfuseObservabilityon
Open-source tracing, prompt management, and evals.
Listed inProduction MonitoringObservabilityon
Drift, failure rates, and alerting on quality instead of just uptime.