← Field Notes
MAY 25 · Clipped · via Langfuse changelog Comparison ViewProduction DriftRelease Decision

Langfuse puts the verdict on the release check in three words

Three words on the release check beat a dashboard that goes unopened. The open question is who decides: failing the job on a regression is a setting, and a person still owns the call.

Read the source ↗ attached to Comparison View →
watching

watching → emerging → established

A candidate behavior, not yet a published pattern. Early signal — worth tracking, not yet worth standardizing on.

10 documented sightings since Jul 2024 — every one traces to a dated source.

See the evidence →

Machine summary of the source

Langfuse rebuilt experiments as a top-level object in April 2026. Score, cost and speed appear as changes against a baseline run, with a filter for cases that crossed a threshold. In May a GitHub Action began posting the result on the change under review as passed, regressed, or failed to run. Failing the job on a regression is an option the team turns on. A weighted rollout then tracks each prompt version while it takes a share of traffic.

The summary above is generated; the note at the top is the editorial judgment. Primary source ↗