Last week, we launched LangSmith Fine-Tuning and the smithtune CLI.

Turn your agent’s own trajectories into a fine-tuned model without building a training pipeline by hand.

Your traces already show your agent doing the job well. Now, that signal becomes training data.

Quick… pic.twitter.com/kfpOcNiCXL

— LangChain (@LangChain) 1 octobre 2026

Last week, we launched LangSmith Fine-Tuning and the smithtune CLI. Turn your agent’s own trajectories into a fine-tuned model without building a training pipeline by hand. Your traces already show your agent doing the job well. Now, that signal becomes training data. Quick

→ View original post on X — @langchain