LLM (Large Language Model)
A large language model like Claude, GPT, or Gemini. The "brain" that understands and generates language.
Why it matters
LLMs are what make modern AI agents possible. They understand natural language and generate human-quality text.
In practice
We use two LLMs: Ollama (local llama3.2, handles 80-95% for free) and Claude (API, for complex reasoning). Routing is automatic and cost-tracked.
Related terms
Ollama
A tool for running AI models locally. Free, private, fast.
Inference
The process of an AI model generating a response or prediction from input data.
Token
The unit of text an AI model processes. Approximately 3/4 of a word.
Context Window
The AI model's "working memory" — how much information it can process at once (e.g., 1 million tokens for Claude Opus 4.6).