Fine-tuning
Further training a base model on your own examples to specialise its behaviour — a heavier alternative to prompting.
Fine-tuning adjusts a model's weights by training it on a dataset of your own examples, baking a behaviour or style into the model itself rather than describing it in every prompt. It can help for consistent formatting, a specific tone, or narrow classification at scale.
It is more work and less flexible than prompting: it needs curated data, costs time and money, and has to be redone to change behaviour. For most needs, prompting and retrieval get you there faster, which is why the usual advice is to exhaust good prompting before reaching for fine-tuning.