Prompting, RAG or fine-tuning: which one do you need?

    People often ask for a fine-tuned model when they really need better instructions, or a search step. The three approaches solve different problems, and the cheapest one often does the job. Here’s how we think about the order.

    Try them in this order

    Figure 1 · A sensible sequence

    Write a clear promptwith examplesAdd retrievalif it needs your documentsConsider fine-tuningif behaviour stays inconsistent
    Move right only when the step before has been tried properly and measured.

    What each one is for

    Figure 2 · Choosing an approach

    ApproachGood forWeak atEffort
    PromptingTone, format, task instructions, examplesFacts the model doesn’t knowLow
    RAGAnswers from your own, changing documentsChanging how the model writes or reasonsMedium
    Fine-tuningA consistent style or format at scaleTeaching new facts reliablyHigh
    A rule of thumb from how these tend to behave, not a hard law.

    The common mix-ups

    • Fine-tuning to add knowledge. It shapes behaviour better than it stores facts. For facts that change, retrieval is the more reliable route, as in our RAG explainer.
    • RAG to fix style. Retrieval won’t change how the model writes. A better prompt will.
    • Skipping measurement. Without a test set, you can’t tell whether a more complex approach helped. Start with twenty real examples.

    A quick way to decide

    Ask what is actually failing. If the answers are in the wrong format, fix the prompt. If they’re wrong about your own data, add retrieval. If they’re right but inconsistent in style or structure across thousands of calls, then look at fine-tuning. Most projects never need the last step.

    Want help putting this into practice?

    Book a free consultation and tell us about your team or school.

    Book a free consultation