Large Language Models (LLMs)

A large language model (LLM) is an AI model trained on very large volumes of text that predicts and generates language one token at a time. It can reason over text, summarize, classify, translate, and hold a conversation, which makes it the reasoning engine behind AI assistants and agents. It does not hold an organization’s own facts; those come from knowledge sources and tools supplied separately.

An LLM is a transformer neural network: given some text, it repeatedly predicts the most likely next piece, and everything it produces is generated this way. Model choice is a real decision when building an agent, since different models behave differently on the same instructions and vary in quality, speed, and cost.

A common misconception is that the model "knows" your company. Out of the box, it only knows general patterns from training data with a cutoff date, and it has no access to your systems.