LangChain traces could become training data for open-source models

hwchase17 · x · 2026-07-26

The thread suggests an attractive workflow: training or fine-tuning open-source models on LangSmith traces inside an ADLC setup, potentially with support from LangChain.

It is a short but concrete product/workflow idea for agent developers: reuse trace data to improve model behavior, rather than treating traces as only observability data.

Original post →

More from coding & agent

coding & agent channel →