AI agent glossary
Large language model (LLM)
An AI model trained on vast amounts of text to predict what comes next, which lets it write, summarize, reason, and follow instructions.
A large language model is trained on a huge collection of text to predict the next token, a small chunk of a word. Doing that well across so much material forces the model to learn grammar, facts, patterns of reasoning, and how to follow instructions.
On its own, an LLM only reads text and writes text. It cannot browse the web, run code, or remember past conversations. Those abilities come from the software around it, which is exactly what an agent adds.
LLMs vary in capability, speed, and cost. Examples include Anthropic's Claude models, OpenAI's GPT models, and Google's Gemini models. Choosing the right one for each job is a core skill for agent builders.
Learn more in the course
Related terms
Go from definitions to doing
Learn to use and build AI agents in 65 practical lessons.