What is System Prompt?
A system prompt is the initial set of instructions given to an AI model that defines its overall behavior, role, rules, and tone for the conversation.
It acts as the hidden foundation that guides how the model interprets and responds to all later user messages, without being visible to the end user.
Unlike user prompts, which change with each query, the system prompt stays constant and sets constraints such as style, safety rules, or persona.
Developers use it to customize model behavior for specific applications while keeping the underlying model weights unchanged.
Example
A system prompt might say: 'You are a friendly math tutor who explains concepts simply and never gives direct answers without showing steps.' This makes the AI respond consistently in that role.
Why it matters
System prompts let companies and developers control AI behavior reliably at scale, enabling safe, branded, and task-specific applications without retraining models.
Frequently asked questions
A system prompt sets permanent rules and persona at the start, while user messages are individual queries that follow those rules.
Related terms
Prompt engineering is the practice of designing and refining text inputs (prompts) to guide AI models like large language models toward producing accurate, relevant, or creative outputs.
Chain-of-Thought (CoT) is a prompting technique that asks an AI model to generate intermediate reasoning steps before giving a final answer, helping it solve complex problems more reliably.
Few-shot learning (in prompting) is a technique where a language model is given a handful of input-output examples directly in the prompt to guide it on a new task.
A prompt is the input text, question, or instruction given to an AI model (especially a large language model) to guide what it should generate or how it should respond.
Zero-shot learning (or zero-shot prompting) is when an AI model completes a task it has never seen examples of during training, relying only on a natural language description of what to do.