Prompting vs RAG vs fine-tuning template

A decision tree for choosing prompt engineering, RAG, fine-tuning or an agent, with a cost and speed comparison.

Use this templateFree, opens in your browser. No sign-up.

Prompting vs RAG vs fine-tuning template
Good results with a good prompt?
Prompt engineering + few-shot examples. Ship in days.
Needs private or fresh knowledge?
RAG: retrieve your docs at query time
Needs a narrow skill or format at scale?
Fine-tune (e.g. LoRA) on 1k+ good examples
Must take multi-step actions?
Agent with tool calling + guardrails
Rethink the task or use classic ML
Approach
Setup cost
Time to ship
Fresh knowledge
Prompting
Low
Days
No
RAG
Medium
Weeks
Yes
Fine-tuning
High
Weeks–months
No (retrain)
Agent
Medium–high
Weeks
Via tools
Start with prompting + an eval set; add RAG or fine-tuning only when evals show the gap.
They combine: RAG over a fine-tuned small model is common.
Prompting vs RAG vs fine-tuning
yes
no
yes
no
yes
no
yes
no
The prompting vs RAG vs fine-tuning template as it opens in Kelvo: 9 boxes, 4 decisions among them, 2 sticky notes, 1 table and 8 links.

What's on the board

Table columns: Approach, Setup cost, Time to ship, Fresh knowledge.

  • Good results with a good prompt?
  • Prompt engineering + few-shot examples. Ship in days.
  • Needs private or fresh knowledge?
  • Start with prompting + an eval set; add RAG or fine-tuning only when evals show the gap.
  • They combine: RAG over a fine-tuned small model is common.
  • Needs a narrow skill or format at scale?
  • RAG: retrieve your docs at query time
  • Must take multi-step actions?
  • Fine-tune (e.g. LoRA) on 1k+ good examples
  • Agent with tool calling + guardrails
  • Rethink the task or use classic ML

How to use this template

  1. Click Use this template. It opens in the Kelvo app as a new board, saved in your browser.
  2. Double-click any box to change its text. Replace the examples with your own content.
  3. Sketch, then convert. Draw boxes and arrows with the pen, select the strokes and click Convert sketch: they become real boxes and links.
  4. Ask Kelvo right on the board (Pro). With Pro, type @kelvo and what you want in any box or text, for example “@kelvo add error handling”, and press Enter. The change is made there and the request disappears; ⌘Z undoes it.
  5. Keep the prompt next to the diagram. Add a code block from the Insert (+) menu for prompts, schemas or config, right beside the boxes they belong to.

Good for

  • ai
  • llm
  • rag
  • fine-tuning
  • decision
  • Explaining an LLM feature's architecture to engineers and stakeholders
  • Deciding between prompting, retrieval and fine-tuning
  • Planning evaluations and risks before launch

Related templates

  • RAG pipeline template previewRAG pipeline

    Retrieval-augmented generation end to end: ingest and embed documents offline, then retrieve, rerank and answer with citations.

  • LLM fine-tuning workflow template previewLLM fine-tuning workflow

    Fine-tune a model step by step: define the task, build a clean dataset, train a LoRA adapter, evaluate against the baseline and ship.

  • LLM agent loop template previewLLM agent loop

    How a tool-using agent plans, calls tools, observes results and updates memory until the goal is met, with guardrails.

  • Prompt design canvas template previewPrompt design canvas

    Design a production prompt piece by piece — role, context, task, constraints, examples, output format — plus test cases.

  • Basic flowchart template previewBasic flowchart

    Start, steps, a decision with yes/no branches, and an end — the classic shape to build from.

  • Architecture decision record (ADR) template previewArchitecture decision record (ADR)

    Record one decision: status, context, the decision, consequences and the options you considered.

All ai and machine learning diagram templates · All templates

Use the prompting vs RAG vs fine-tuning template