Formatting and Structure Instructions
You'll learn: How to explicitly guide your chatbot's output format so responses are clean, scannable, and perfectly structured for your users.
Why Format Matters
When building conversational AI, how information is presented is just as important as what is presented. A chatbot that dumps walls of unformatted text feels clunky and unprofessional. Formatting instructions in your system prompt tell the model exactly how to structure responses—using markdown, lists, headings, and other formatting conventions.
Core Formatting Directives
Think of these instructions as your chatbot's style guide:
Markdown usage: Tell your bot when to use bold (**text**), italics (*text*), code blocks (```code```), or inline code (`variable`). For example: "Use bold for key terms. Wrap code in triple backticks."
Lists and structure: Specify when to use bullet points (- or *) versus numbered lists (1., 2.). Example: "Present options as numbered lists. Use bullet points for feature descriptions."
Headings: Guide section organization with ## or ###. "Start each topic with a level-2 heading."
Response length: "Keep responses under 300 words" or "Provide concise, 1-2 sentence answers unless more detail is requested."
Practical Application
In your system prompt:
Format all responses using markdown.
- Use bullet points for lists of items
- Use numbered lists for sequential steps
- Bold important concepts
- Keep paragraphs short (2-3 sentences max)
This transforms messy output into professional, user-friendly conversations.
Key Takeaway: Formatting instructions ensure consistent, readable responses—specify markdown conventions, list types, heading structure, and response length directly in your system prompt to control how information appears to users.