AI Prompt Engineering · Lesson

System vs User Role Distinction

How system and user messages differ in model behavior and priority.

Two Roles, Two Purposes

Modern LLM APIs expose two primary message roles: system and user. Understanding the distinction is foundational to building well-behaved AI applications.

System message: Written by the developer. Defines how the model behaves, what persona it adopts, what rules it follows.
User message: The runtime input — from the end user or from an automated process.

This separation allows developers to lock in behavior without exposing control logic to users.

System Message = Developer-Defined Behavior

The system message is where you define the model's identity, rules, and constraints. It is set once (per session or per call) and persists across all turns of a conversation.

import anthropic

client = anthropic.Anthropic(api_key='YOUR_API_KEY')

response = client.messages.create(
    model='claude-opus-4-5',
    max_tokens=500,
    system='You are a customer support agent for TechCorp. '
           'Only answer questions about TechCorp products. '
           'Never discuss competitor products. '
           'Always be professional and concise.',
    messages=[
        {'role': 'user', 'content': 'What is your best laptop?'}
    ]
)

print(response.content[0].text)

All lessons in this course

← Back to AI Prompt Engineering