Don't approve the model, approve the app
How Langfuse helped a top-five bank put deployment gates on AI agents: golden datasets, traces as evidence, multi-dimension scoring and thresholds set by domain experts.
DIGEST / YOUTUBE
YouTube digest
Long-form write-ups of talks and videos: what the speaker argued, the architecture behind it, and how to try it yourself. Also see the observability digest ↗
All write-ups / 01
RSS ↗↗