Back to Skills Library

The model lacks domain knowledge - do you fix the prompt, build RAG, or fine-tune?

Decide between Prompting, RAG, or Fine-tuning for your AI feature

Recommended AI Agent Skills

Battle-tested prompt engineering patterns including few-shot demonstrations, role calibration, and schema constraints.

Prompt EngineeringLLMContext
2026-07-1920.2k

Guidance for designing a RAG (Retrieval-Augmented Generation) pipeline - chunking, embeddings, hybrid search - and when RAG is actually the right call.

RAGRetrievalLLM
2026-07-182.3k

Advises when fine-tuning a model is actually warranted, which method to use (full fine-tune, LoRA, PEFT), and the ongoing maintenance cost.

Fine-tuningModel TrainingLLM
2026-06-303.4k

Action framework

  1. Ask: Is the issue missing knowledge or wrong format/style? New knowledge → Prompt/RAG; Format/tone → Few-shot or Fine-tuning.
  2. Ask: Does the data change frequently? If yes → RAG is required; fine-tuning will go stale immediately.
  3. Check document size: If under 10 pages, inject directly into the context window before engineering a RAG pipeline.
  4. Evaluate engineering cost: Prompting (1 day) → RAG (1-2 weeks) → Fine-tuning (1-2 months + continuous retraining).
  5. Always prototype cheapest-first: Optimize system prompt → Build RAG when exceeding context → Fine-tune only if RAG fails on specialized formatting.

Before

"Let's just collect all data and fine-tune a model for maximum accuracy."

After

"Docs change weekly → Use RAG with hybrid search. Injected 3 few-shot examples into the system prompt to hit 80% quality without expensive fine-tuning."

Go deeper: Lesson 06 - AI PM