BACK TO GLOSSARY
AI & LLM Glossary

What is System Prompt?

System Prompt — A set of instructions given to an AI model before the user conversation begins, shaping its behavior, tone, and capabilities.

Definition & Explanation

A system prompt is a special type of instruction given to a large language model (LLM) at the start of a conversation session. Unlike user messages, system prompts are typically invisible to end users and are used by developers and companies to configure how the AI behaves. They can define the AI's persona, set boundaries on what it can and cannot do, establish its tone and communication style, and provide background context. System prompts are the primary way AI coding tools like Cursor, Claude Code, and GitHub Copilot define their specialized behaviors.

AI Tools Using System Prompt

Cursor

AI Code Editor

Claude Code

AI Coding Assistant

GitHub Copilot

IDE Extension

v0

AI Platform

Frequently Asked Questions

What is a system prompt?

A system prompt is a set of instructions given to an AI model at the start of a session, defining its behavior, persona, and constraints before any user interaction begins.

Why are system prompts important?

System prompts are critical because they define the AI's behavior, safety boundaries, and capabilities. For AI coding tools, they determine how the model approaches coding tasks, what languages it supports, and how it interacts with developers.

Can I see a tool's system prompt?

Most companies keep their system prompts confidential, but many have been reverse-engineered by the developer community. SystemPrompts.fun is a database of verified system prompts from popular AI tools.

How long can a system prompt be?

System prompts can range from a few sentences to tens of thousands of tokens. AI coding tools often have very long system prompts (10,000–50,000+ tokens) to define complex behaviors.

Related Terms

Large Language Model (LLM)

A type of AI model trained on massive amounts of text data, capable of understanding and generating human-like text across a wide range of tasks.

Prompt Engineering

The practice of designing and optimizing text inputs (prompts) to get the best possible outputs from AI language models.

AI Agent

An AI system that can autonomously plan and execute multi-step tasks, using tools and making decisions to achieve a goal.

Context Window

The maximum amount of text (measured in tokens) that an AI model can process at one time, including both input and output.

EXPLORE MORE

Browse All AI & LLM Terms

Explore our complete glossary of AI, LLM, and system prompt terminology.

View Full Glossary