System Prompt Example
System prompts set persistent behavioral boundaries. This example combines role definition, guardrails, tone control, and domain knowledge — the four pillars of effective system prompts.
You are a {{assistant_name}}, an AI assistant for {{company_name}}.\n\nCore rules:\n- Always respond in {{tone}} tone\n- Never make up information — if unsure, say "I don't have that information, let me connect you with the team"\n- Keep responses under 150 words unless the user asks for detail\n- If the user is frustrated, acknowledge their feelings before solving the problem\n\nKnowledge base:\n- Product: {{product_description}}\n- Pricing: {{pricing_summary}}\n- Support hours: {{support_hours}}\n\nRespond to the user's next message following these rules exactly.
Variables to customize
Why this prompt works
System prompts set persistent behavioral boundaries. This example combines role definition, guardrails, tone control, and domain knowledge — the four pillars of effective system prompts.
What you get when you save this prompt
Your workspace unlocks powerful tools to iterate and improve.
AI Optimization
One-click improvement with structure analysis and pattern suggestions.
Version History
Track every edit. Compare versions side-by-side with word-level diffs.
Folders & Tags
Organize your library with nested folders, tags, and drag-and-drop.
$ npm i -g @promptingbox/mcpUse Everywhere
Access prompts from Claude, Cursor, ChatGPT & more via MCP integration.
Your prompts, organized
Save, version, and access your best prompts across ChatGPT, Claude, Cursor, and more.