Retrieval-augmented generation (rag)RAG
RAG is an AI technique where a language model first retrieves relevant information from a knowledge base before generating an answer.
Detailed explanation
One of the biggest limitations of standard LLMs is that they only have knowledge up to their training date. RAG solves this by giving the model access to an external knowledge source, such as your product documentation, customer data, or company information, at the moment it answers a question.
How does it work? The user's question is first converted into a vector (mathematical representation of meaning), after which a vector database retrieves the most relevant documents. Those documents are passed to the LLM along with the question, which then generates an answer based on both its trained knowledge and the specific, current context.
For sales and marketing, RAG has enormous applications. Imagine AI-agent having access not just to general knowledge, but also to your complete product catalog, price lists, case studies, and previous customer conversations.
Synonyms
Examples
A software company implements RAG for their sales agent: the agent has access to all 200+ product features, customer case studies, and competitive comparisons. For a prospect question about integrations, the agent automatically retrieves the most relevant technical documentation.
When to use this?
RAG is essential when AI systems need to use accurate, current, and company-specific information. Perfect for sales assistants, customer service bots, and internal knowledge systems.
Sources & further reading
Your Company OS approach
Your Company OS connects your own sources, such as documentation, quotes and manuals, to your AI colleagues. That way they answer based on what your company has recorded itself.
Related terms
Want to know more about Retrieval-augmented generation (rag)?
Want to know how to put Retrieval-augmented generation (rag) to work in your organisation? Get in touch with Your Company OS.