Large Language Model

Definition

A large language model (LLM) is a type of artificial intelligence model trained on massive datasets of text to understand, generate, and reason about human language. These models contain billions of parameters — numerical values adjusted during training — that encode patterns of language, knowledge, and reasoning capabilities.

Prominent examples include OpenAI's GPT-4, Anthropic's Claude, Google's Gemini, and Meta's LLaMA. LLMs power most modern AI automation tools, enabling workflows that can read documents, draft emails, summarize meetings, classify data, and generate content with human-level fluency.

How It Works

LLMs are built using a deep learning architecture called the transformer. During training, the model processes billions of text samples from books, websites, code repositories, and other sources. It learns to predict the next word in a sequence, and through this process, it develops an understanding of grammar, facts, reasoning patterns, and context.

When you send a prompt to an LLM, the model generates a response token by token, with each token influenced by the full context of the conversation. The quality of the output depends on the model's size, training data, and the specificity of your prompt. Techniques like fine-tuning, retrieval-augmented generation (RAG), and prompt engineering are used to improve outputs for specific use cases.

In AI automation, LLMs are integrated as processing nodes within workflows. For example, an n8n workflow might use an LLM to analyze incoming support tickets, classify their urgency, draft a response, and route them to the appropriate team — all without human intervention.

Related Terms

• AI Automation — Using AI including LLMs to automate business processes
• Prompt Engineering — The practice of writing effective prompts to get optimal LLM outputs
• Agentic AI — Autonomous AI systems built on top of LLMs
• n8n — An automation platform with native LLM integration nodes