Learn AI / Compare /Prompt engineering vs fine-tuning

Prompt engineering vs fine-tuning

Both are called "customising the model". Only one changes it.

The short answer

Prompt engineering changes what you ask, not the model. Fine-tuning changes the model itself by training it further on new examples, which costs money, needs data and creates something you then have to maintain. Try the first before paying for the second.

Prompt engineering

Large Language Models · Starter

In one sentence: The practice of writing and refining instructions so a language model is more likely to produce a useful, safe and well-structured reply.
Why it matters: Non-specialists do not need to become engineers, but they do need to know that results depend heavily on the instructions given. A vague request can waste time, while a clear prompt can produce output that is easier to review, compare and reuse. This matters for decisions about efficiency, quality control and risk. It also helps people recognise the limits: if the model gives a polished answer, that does not mean the answer is correct. Good prompting improves usefulness, but it does not replace evidence, policy checks or human judgement.
The everyday version: It means telling the AI tool clearly what you want, what rules to follow and what shape the answer should have.
The one thing to remember: Prompt engineering refines the instructions and context that steer a model's reply. It can improve consistency and structure, but it neither changes the model's weights nor verifies the result.
The commonest misconception: Prompt engineering is a way to make the model always tell the truth. Clear prompts can reduce confusion and ask for sources or uncertainty statements, but they do not guarantee factual accuracy. The model still generates likely text and can produce errors or invented details, so checking remains necessary.

Read the full page

Fine-tuning

Training and Model Adaptation · Starter

In one sentence: Updating a pre-trained model's parameters with additional examples to improve performance on a narrower task, style or domain.
Why it matters: Fine-tuning matters because organisations often need more than a general model. They may want a model that follows a specific format, works better in a specialist domain, or uses approved terminology more consistently. For leaders and policy staff, this affects cost, risk, procurement and governance: what data can be used, who checks quality, how a new model version is evaluated, and whether changing the model is even necessary. In many cases, a prompt or document retrieval system is enough. In other cases, fine-tuning can improve reliability on a narrow task. Knowing the difference helps you ask better questions before spending money or exposing data.
The everyday version: Fine-tuning means taking a general AI model and giving it extra practice on a narrower job so it performs that job more consistently.
The one thing to remember: Fine-tuning updates a pre-trained model's parameters using additional examples and produces a new version for a narrower job. It is not prompting, and it still requires authorised data, evaluation and human review.
The commonest misconception: Fine-tuning simply means the model has read our documents. Not exactly. Fine-tuning is a training process that changes model parameters using curated examples. Giving documents at use time is different; that is closer to retrieval-augmented generation or context prompting, where the model itself may remain unchanged.

Read the full page