Launch HN: Laminar (YC S24) – We trained a model to catch silent agent failures

By skull8888888 · 2026-10-19 · 19 points · 4 comments

Hi HN, we’re Robert and Din from Laminar ( https://laminar.sh ). We’ve been building open-source observability for AI agents since 2024. Recently, we released flow-1, a model trained with RL to find errors in agent traces. On our benchmark ( https://laminar.s…

Open the full discussion on BetterNews