Browsing Tag
Sampling
4 posts
LLM-as-judge in production: keeping the budget under control
LLM-as-judge in production: sample, target, calibrate the judge on human examples and monitor its cost to keep the evaluation budget under control.
Datadog APM ingestion: retention filters and indexed spans
Datadog APM ingestion explained: separate ingestion, indexing and metrics, then tune sampling and retention filters to keep the traces that matter.
APM Server tail-based sampling: tune TTL and storage
APM Server tail-based sampling: tune interval, TTL and storage_limit, and choose what happens when storage saturates, based on the Elastic docs.
Datadog trace metrics: RED without depending on sampling
Datadog trace metrics: hits, errors and latency computed on 100% of traffic, plus their limits with OpenTelemetry and sampling, checked in the docs.