Technical
Retrieval-Augmented Generation (RAG)
A technique that combines AI text generation with real-time information retrieval from a knowledge base.
Retrieval-augmented generation (RAG) is an AI architecture pattern where a language model retrieves relevant information from a knowledge base (documents, databases, APIs) before generating a response. Instead of relying solely on what the model learned during training, RAG grounds the output in specific, current data.
In enterprise contexts, RAG is commonly used for:
- Internal knowledge assistants that answer questions from company documents
- Customer support chatbots that reference product documentation
- Code assistants that understand a specific codebase
- Research tools that synthesize information from proprietary databases
RAG introduces governance considerations around the knowledge base: what data is indexed, who has access, and whether the retrieval layer properly enforces permissions.
Why it matters
RAG-powered tools access your organization's data directly. If permissions aren't properly configured, a RAG system can surface confidential information to unauthorized users — not through a hack, but through normal operation.