>Advanced
What is Retrieval-Augmented Generation (RAG)?
Retrieval-Augmented Generation (RAG) is a technique that lets an AI model answer using your own documents and data, retrieving relevant information before generating a response.
RAG grounds the model in trusted sources — your policies, knowledge base or files — so answers are accurate and specific instead of generic or invented.
It's how organisations safely put AI on top of their own knowledge, and kenai covers it for teams ready to move beyond off-the-shelf chat.
Related terms
Large Language Model (LLM) →
A Large Language Model (LLM) is an AI system trained on vast amounts of text to understand and generate human language, powering tools like Claude and ChatGPT.
Hallucination →
A hallucination is when an AI model produces information that sounds confident and plausible but is actually false or made up.
AI Agent →
An AI agent is an AI system that can take actions to achieve a goal — using tools, calling other systems and working through multi-step tasks with limited human input.