# Fine-tuning

> Fine-tuning adapts a pre-trained model to a specific task or domain by continuing training on a smaller, targeted dataset. It bakes behaviour and tone into the model itself, complementing prompting and RAG.

*Source: https://www.lazlosoftwaresolution.com/glossary/fine-tuning*

Fine-tuning is worth it when you need consistent style, structured output or specialised knowledge that prompting alone can't reliably deliver. For most enterprise use cases, RAG + good prompting is tried first; fine-tuning is added where it earns its keep.