What is RAG?

Retrieval-Augmented Generation — fetching relevant documents at query time and feeding them into the prompt so the model answers from your data, not just its training.

How it works

Instead of fine-tuning, you embed your documents into a vector store, retrieve the top matches for a question, and stuff them into context. It's how you give an agent long-term, domain-specific knowledge without retraining.

Example

In practiceA support agent embeds your docs; when a user asks a question it retrieves the three most relevant passages and answers grounded in them, with citations.

RAG or fine-tuning?

Start with RAG — cheaper, updatable, and citable. Fine-tune only for style/format, not facts.

Go deeper: Deploy Your First AI Agent

The complete, step-by-step guide — every command, config, and the reasoning behind it.

Get the guide