Glossary
RAG (Retrieval-Augmented Generation)
An AI architecture that retrieves relevant documents from a knowledge base before generating a response, grounding outputs in specific source material rather than relying solely on training data.
Retrieval-Augmented Generation (RAG) is the architecture that powers most enterprise AI systems designed for professional use. Instead of generating answers from training data alone, a RAG system first retrieves relevant documents from a knowledge base — your firm's files, precedents, or legal databases — and uses those documents as context for generating a response.
Why it matters for legal AI
For legal practice, RAG is what separates a professionally useful AI from a general chatbot. When Ask Scout answers a research question, it retrieves from your uploaded matter documents and firm knowledge base before composing a response. When the Composer drafts a document, it retrieves from your approved precedents. The answer is grounded — not fabricated from statistical patterns in generic training data.