Fine-tuning
Fine-tuning is further training a pre-trained AI model on a smaller, specific dataset so it adapts to a particular task, tone or domain. It is more involved than prompting or retrieval-augmented generation, and for most products those two solve the problem at lower cost and risk.
Fine-tuning takes a model that already knows language and nudges it toward your specific need by training it further on examples you provide. It can be the right tool for a narrow, repeated task where tone or format matters a lot.
The common mistake is reaching for it first. Fine-tuning costs data, time and ongoing maintenance, and it bakes knowledge in at a point in time. For most teams, good prompting plus retrieval-augmented generation gets there faster and stays easier to change. Knowing when fine-tuning actually pays off is exactly the kind of judgement worth hiring for.
