# Fine-tuning vs. RAG

Fine-tuning re-trains a model on your examples (changes how it behaves). RAG — retrieval-augmented generation — feeds a model your documents at question time (changes what it knows). Most businesses need RAG first; it’s cheaper and always current.

Canonical: https://robauto.ai/learn/ai-101/13

_AI 101: The 2026 Foundation — lesson 13 of 20 (DEFINITION)_

Fine-tuning re-trains a model on your examples (changes how it behaves). RAG — retrieval-augmented generation — feeds a model your documents at question time (changes what it knows). Most businesses need RAG first; it’s cheaper and always current.

Source: [AWS — What is RAG?](https://aws.amazon.com/what-is/retrieval-augmented-generation/?utm_source=robauto)

[Previous lesson](/learn/ai-101/12) · [Next lesson](/learn/ai-101/14) · [Course overview](/learn/ai-101) · [All courses](/learn)

---

(c) 2026 Robauto, Inc. — support@robauto.ai
Machine surfaces: https://robauto.ai/llms.txt · https://robauto.ai/llms-full.txt · https://robauto.ai/.well-known/api-catalog