LLM (Large Language Model)
An AI model trained on huge amounts of text that can understand and generate human like language. It's the engine behind tools like chat assistants.
Prompt
The instruction or question you give an AI model. Better prompts produce better outputs, learning to prompt well is a core generalist skill.
Token
The small chunks of text (roughly word pieces) that models read and write. Usage and pricing are usually measured in tokens.
RAG (Retrieval Augmented Generation)
A technique that lets a model pull in your own documents or data before answering, so responses are grounded in real, up to date information.
Agent
An AI system that can take actions, calling tools, browsing, or running steps on its own, to complete a goal rather than just replying once.
Vibe coding
Building working software by describing what you want in plain language and letting AI write the code, then steering it, no traditional coding background required.