System Prompt Is Not a Blob of Text
A production-grade System Prompt is not written by stream of consciousness. It is layered: Identity, Environment, Tool, and Behavior — each layer handles its own domain so changing one doesn't affect the others.
Common Chaotic Writing Style
Click each layer to see what it's responsible for
Identity Layer
Who am I? Personality, role, basic persona
- Name, role definition
- Personality traits (friendly / rigorous / humorous…)
- Basic capability boundaries (what it can and can't do)
Environment Layer
What's the current situation? System state, user context
- User basics (language preference, timezone…)
- Current OS, app state
- Session context (which page, what was done before)
Tool Layer
What can be used? Available tools and APIs
- Tool name and description
- Parameter format
- Usage restrictions and notes
Behavior Layer
How to act? Output format, decision rules
- Answer style and format requirements
- Decision priority (what to do first, what to do next)
- Safety guardrails (what it can't do, what needs confirmation)
Change One Layer Without Affecting Others
Adding a new tool? Only touch the Tool layer. Adjusting answer style? Only modify the Behavior layer. No ripple effects.
Multi-Person Collaboration Without Conflicts
Product updates behavior, engineers add tools, operators adjust persona — everyone edits their own file, no Git merge conflicts.
More Precise A/B Testing
Want to test different answer strategies? Only swap the Behavior layer — the other three layers remain unchanged, isolating the variable.
Easier Troubleshooting
Unexpected AI behavior? Check layer by layer: wrong identity? Outdated environment info? Incorrect tool description? Rule conflict?