Compare · Building · Research notes

Prompting vs RAG vs fine-tuning — scored

Teams skip the cheap lever. Score the job before you buy a training run.

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

How do you pick among the three?

  1. Name the artifact and the decision.
  2. If context fits, prompt first.
  3. If facts live in documents that change, add RAG.
  4. If style/format is stable and you have a holdout, consider fine-tuning.

What is the scoring rubric?

CriterionWeightHow to score
Fits in contextGateIf yes, stay on prompts.
Corpus freshness1–5RAG wins when documents move.
Holdout qualityGateNo holdout, no fine-tune.
Ops complexity1–5Each lever adds failure modes.

Which lever is the default?

ToolBest fitDefaultNext leverNote
PromptingMost jobsStart hereAdd RAG if facts overflowCheapest to evaluate.
RAGDocument Q&ARetrieve then answerAdd fine-tune for format lockCite chunks.
Fine-tuningStable behaviorStyle/formatDo not use as a knowledge dumpNeeds evals.

Learn the craft, not just the tool

Practice the transferable habit in Fine-tuning vs RAG, then RAG vs fine-tuning, Evals.

FAQ

What should I try first, RAG or fine-tuning?

Prompts, then RAG for changing facts, then fine-tuning if style/format is still wrong.

Can I do all three?

Yes. Prompt + retrieve + a small tune is common. Evaluate each layer.