LangSmith Fine-Tuning and smithtune Turn Agent Trajectories Into Custom Models

LangChain launched LangSmith Fine-Tuning and smithtune, a CLI that turns LangSmith agent trajectories into fine-tuned models through dataset creation, training with Fireworks or Baseten, and evaluation in LangSmith. smithtune currently supports supervised fine-tuning, training models on recorded examples of good agent behavior by updating model weights.

The tool lets teams train specialized models without building the data pipeline by hand.