---
term: "Large language model"
category: "Agents and autonomy"
url: https://agenticopenfinance.com/glossary/large-language-model
source: AgenticOpenFinance glossary
---

# Large language model

> A model trained on very large amounts of text to predict likely text, used by most agents to interpret instructions and choose steps.

A large language model is a machine-learning model trained on very large amounts of text to predict likely continuations of text, which lets it summarise, classify, draft and answer questions. Most AI agents use one as the component that interprets instructions and proposes the next step. Its outputs are probabilistic, so they can be fluent and wrong at the same time, which is why agent designs surround the model with deterministic checks.

Related terms: [AI agent](https://agenticopenfinance.com/glossary/ai-agent.md), [Confabulation](https://agenticopenfinance.com/glossary/confabulation.md), [System prompt](https://agenticopenfinance.com/glossary/system-prompt.md), [Retrieval-augmented generation](https://agenticopenfinance.com/glossary/retrieval-augmented-generation.md)