System prompt
Also called System instructions, System message
A system prompt is a set of instructions given to a language model before the conversation starts, which sets its role, tone, rules and limits. Users usually can't see it. The model weighs it alongside every message, so it shapes how the assistant behaves throughout the whole conversation.
Example
"You are the support assistant for Acme Plumbing. Answer only from the provided information. Keep replies under four sentences. If you don't know, offer to take the visitor's email."
Why it matters for a website chatbot
The system prompt decides whether a chatbot stays on topic, admits uncertainty and hands off politely. ChatBento writes a careful system prompt for you, and its Instructions field lets you add your own rules, such as tone or topics to avoid, on top of it.
See it in practice: FAQ automation
Related terms
- Prompt injectionPrompt injection is an attack in which someone hides instructions in text that an AI model reads, such as a chat message, web page or document, to make it ignore its original instructions. Attackers use it to extract hidden prompts, produce unwanted content or trigger actions the system's owner never intended.
- GuardrailsGuardrails are rules and checks placed around an AI system to keep its behavior within safe, intended limits. They can restrict topics, block harmful or off-brand output, require answers to come from approved sources, filter inputs for attacks, and send uncertain or sensitive cases to a person.
- Large language model (LLM)A large language model (LLM) is an AI model trained on very large amounts of text to predict and generate language. It can answer questions, summarize, translate and write. Its general knowledge comes from training data with a cutoff date, so it needs supplied documents to answer accurately about a specific business.
- Context windowA context window is the maximum amount of text, measured in tokens, that a language model can take into account at once. It covers the instructions, the conversation so far, any retrieved documents and the reply being written. Anything outside the window is invisible to the model when it generates its answer.