---
title: "What Is Fine-Tuning?"
description: "Fine-tuning means further training a pretrained AI model on your own examples so it learns a specific style, format or task. Meaning, how it differs from RAG and prompting, and when it is worth it."
type: "glossary"
locale: "en"
term: "Fine-Tuning"
canonical: "https://agenticschool.dev/glossary/fine-tuning"
dateModified: "2026-07-03"
---

# What Is Fine-Tuning?

- Definition: Fine-Tuning
- Updated: 2026-07-03
- Keywords: fine-tuning, what is fine-tuning, fine-tuning meaning, fine-tuning vs rag, model fine-tuning
- Canonical URL: https://agenticschool.dev/glossary/fine-tuning
- Locale: en

> Fine-tuning means further training a pretrained AI model on your own examples so it learns a specific style, format or task. Meaning, how it differs from RAG and prompting, and when it is worth it.

Fine-tuning is the process of taking a pretrained AI model and training it further on a focused set of your own examples, so it reliably adopts a specific style, format, or skill without being told every time in the prompt. The base model already knows language broadly; fine-tuning nudges its weights toward your narrow use case, whether that is answering in your brand voice, always returning a certain JSON shape, or handling a specialised domain. It is a heavier tool than prompting or RAG because it changes the model itself, so it pays off when you need consistent behaviour at scale and you have good example data to teach from.

## How fine-tuning works

Fine-tuning trains an existing model on labelled examples of the behaviour you want. You prepare pairs of input and ideal output, run a training job, and get back a customised version of the model.

- Collect examples: gather high-quality input-to-output pairs that show the behaviour you want.
- Train: run a fine-tuning job that adjusts the model weights toward those examples.
- Use: call your customised model, which now leans toward that style or task by default.

## Fine-tuning vs RAG vs prompting

These three ways to adapt a model solve different problems. Prompting shapes one response with instructions. RAG adds fresh knowledge at query time by retrieving documents. Fine-tuning bakes in behaviour by changing the weights. A simple rule: prompt first, add RAG when the model needs to know your facts, and fine-tune when you need consistent style or format that prompting cannot hold. Knowledge belongs in RAG; behaviour belongs in fine-tuning.

## When fine-tuning is worth it

Fine-tuning is worth the effort when a task repeats at scale, the desired output is narrow and consistent, and you can supply enough clean examples to teach it. It is usually not the first move: it costs time and money, it must be redone when the base model updates, and it does not add live knowledge. For most builders, a sharp system prompt plus RAG gets you most of the way, and fine-tuning is the last step for the cases where consistency really matters.

## FAQ

### What is fine-tuning in AI?

Fine-tuning is further training a pretrained model on your own examples so it reliably adopts a specific style, format or task. It adjusts the model weights toward your use case, so you do not have to spell out that behaviour in every prompt.

### What is the difference between fine-tuning and RAG?

Fine-tuning changes the model weights to shape behaviour and is costly to update. RAG leaves the model unchanged and feeds it relevant knowledge at query time. Use fine-tuning for consistent style or format, and RAG for facts that change or must be cited.

### Is fine-tuning better than prompting?

Not usually as a first step. Prompting is instant and free to change, so start there. Fine-tuning only wins when a task repeats at scale and you need consistency that prompting cannot hold, and when you have enough clean examples to train on.

### How much data do I need to fine-tune a model?

It depends on the task, but quality matters more than raw volume. A few hundred to a few thousand clean, representative examples is a common starting range for style or format tasks. Messy or inconsistent examples hurt more than they help.