Compare · Building · Research notes

RAG vs fine-tuning — scored

Fine-tuning is the heavier lever. Start with prompts, add RAG for changing facts, fine-tune for stable style or format.

Last reviewed: 2026-08-15. Re-run the protocol after major model or pricing changes.

How do you choose RAG vs fine-tuning?

  1. Write whether the facts change weekly.
  2. Write whether you need a stable voice/format.
  3. Price retrieval ops vs a training run and eval set.
  4. Keep a holdout. Do not trust a single demo.

What is the scoring rubric?

CriterionWeightHow to score
Facts changeGateIf yes, RAG (or search) before fine-tune.
Style/format lock1–5Fine-tune or a strong prompt pack.
Eval set existsGateFail fine-tunes without a holdout.
Cost to update1–5Re-index vs re-train.

Which lever should I pull?

ToolBest fitUse whenAvoid whenNote
PromptingFirst leverThe job fits in contextFacts are long or changingAlways start here.
RAGChanging documentsYou can retrieve and citeYou only needed a tone changeEvaluate groundedness.
Fine-tuningStable style/formatYou have a clean train/holdout setFacts go stale weeklyCombine with RAG when both apply.

Learn the craft, not just the tool

Practice the transferable habit in Fine-tuning vs RAG, then Three-way decision, Fine-tune guide.

FAQ

Should I fine-tune or use RAG?

RAG for changing facts. Fine-tune for stable style or format. Many products need both.

Can prompts replace both?

Often for a first version. They fail when the corpus is large or the format must be locked.