Large language model (LLM)

Definition

A large language model is a statistical model trained on very large text corpora that predicts likely continuations of text. It can classify, summarise, translate and draft, and it is the reasoning component inside most AI agents — but it holds no live company data by itself.

An LLM is a component, not a system. On its own it has no access to your orders, contracts or master data, and it has a knowledge cut-off. Business value appears when the model is connected to authoritative company data and to systems it can write to.

Model choice is an engineering decision: cost per token, latency, context window, language coverage and the hosting region all matter more than benchmark leaderboards.

In practice

  • Provides judgement, language and extraction — not facts about your business
  • Needs retrieval or tool access to work with current company data
  • Model selection is driven by cost, latency, language and data location

Related terms

Back to the glossary