RAG

RAG (Retrieval-Augmented Generation) is a technique where an AI looks up relevant documents from a knowledge base and includes them in its prompt, instead of relying only on what it learned during training.

An LLM's training data has a cutoff and doesn't know your specific business. RAG is the common fix: keep your real information in a searchable store, and pull the relevant pieces into the prompt at the moment they're needed.

Masterforce doesn't chunk and embed your content into a separate vector store the way most RAG setups do. A Skill is reference knowledge an agent reads directly, on demand, from the real file — the same document you'd open yourself, not a re-indexed copy.