Core Concepts

What is LLM (Large Language Model)?

A deep learning model trained on large text corpora that can generate, understand, and reason with language.

Definition

A Large Language Model (LLM) is a neural network trained on vast quantities of text that has learned to generate coherent, contextually relevant language. LLMs like GPT-4, Claude, and Gemini underpin most modern AI applications. They can write, summarize, translate, answer questions, write code, and reason — though they operate turn-by-turn without inherent memory or the ability to take real-world actions on their own.

Example

GPT-4o is an LLM. It answers questions impressively but can't check your calendar, send a Slack message, or run on a schedule. AI agents use LLMs as their reasoning core but add tools, memory, and scheduling on top.

LLM (Large Language Model) vs ai-agent: What's the difference?

LLM (Large Language Model)

A deep learning model trained on large text corpora that can generate, understand, and reason with language.

ai-agent

An LLM is the reasoning engine. An AI agent wraps an LLM with tools, memory, and scheduling to take autonomous action.

Related terms

Back to glossary