← Glossary

Glossary · LLM

Large Language Model (LLM)

A large language model (LLM) is an AI model trained on vast amounts of text to predict and generate language. LLMs are the reasoning engine behind most generative and agentic AI systems.


An LLM's knowledge is fixed at training time and bounded by its context window, which is why techniques like RAG (to supply current, proprietary knowledge) and tool use (to take actions) are layered on top.

LLMs are powerful but imperfect: they can hallucinate, so production systems add grounding, guardrails, and evaluation.

Related terms

Learn more