System Prompt Design
System prompt design defines the assistant's role, responsibilities, boundaries, and output behavior. It is the behavior contract for an AI application.
Intermediate Architecture
When to use
Use it when building AI assistants, chatbots, domain-specific tools, and systems that need consistent behavior over many turns.
Prompt example
Task: Apply System Prompt Design to the user's request. Context: describe the input, constraints, target audience, and desired format. Instruction: be explicit, keep the output structured, and state any assumptions.
Output example
Structured answer based on the requested technique. Key result: the model follows the stated task and format. Notes: validate the output before using it in production.
Best practices
- Separate role, responsibilities, constraints, and output format.
- Use short headings and explicit priorities.
- Test boundary cases and prompt injection attempts.
- Keep critical instructions concise and unambiguous.
Common pitfalls
- Very long system prompts dilute key rules.
- Conflicting constraints produce unstable behavior.
- Users may try to override the system behavior.