What are the three message roles in a chat-style LLM prompt and what does each represent?

Chat-style LLM APIs (OpenAI Chat Completions, Anthropic Messages, Gemini, most open-source servers) take a list of messages. Each message has a **role**: `system`, `user`, or `assistant`. The system role carries instructions that should hold across the whole call: who the model is, how it should respond, what format to use, what it must refuse. You typically write this once per session and reuse it. The user role carries the actual question or task for this turn. In a chatbot it is whatever the human typed. In an internal pipeline it is whatever your code is asking the model to do. The assistant role holds the model's earlier replies in this conversation. Your code passes them back in on each new call so the model can see what it has already said. This is how multi-turn memory works on a stateless API: you build the running transcript on your side and resend it each time.

Three roles. The **system** role is the model's standing orders for the call: persona, output format, refusal behavior, tone, schema. It is set once and stays stable across turns. The user role is the current turn's input. In a customer-facing product it is whatever the user typed; in a backend pipeline it is whatever your application is asking. Retrieved RAG context and dynamic facts usually live here too, close to the question that needs them. The assistant role replays the model's previous responses in this conversation. The chat APIs are stateless: nothing is remembered between calls. To get coherent multi-turn behavior, your application stores the transcript and resends user + assistant messages on every new request so the model has full context. The practical discipline is to keep stable rules in system and per-turn content in user. Mixing the two is the most common message-role mistake.