Comparison
MetricvsObservability
Metric
you record a number over time so you can see the shape of the whole system at once without reading a single log line.
An aggregated numeric time series: counters, gauges, histograms. Metrics are cheap, bounded in volume and ideal for alerting and dashboards. They cannot tell you about one specific request, which is where logs and traces take over.
Full entry →Observability
the incident came in and you had every prompt, output, model version, latency and cost to look at instead of guesses.
Logging, tracing and metrics for LLM features: every call's prompt, output, tokens, latency, cost, model version and outcome. Without it, production incidents reduce to guessing. It is the same discipline you apply to services, with prompts and completions as the payload.
Full entry →