{
  "id": "system-prompt",
  "code": "PTL-0003",
  "term": "System Prompt",
  "aliases": [
    "system message",
    "developer message",
    "system instruction"
  ],
  "category": "foundations",
  "definition": "A system prompt is a privileged instruction block, placed before the conversation, that sets a model's role, rules, tone, and constraints for every subsequent turn.",
  "description": "Chat APIs typically expose the system prompt as a separate message role. Models trained with an instruction hierarchy are taught to give system instructions precedence over conflicting user or tool content, which makes the system prompt the main lever for operator control and a frequent target of prompt-leaking attacks.",
  "example": null,
  "broader": [
    "prompt"
  ],
  "narrower": [],
  "related": [
    "instruction-hierarchy",
    "role-prompting",
    "prompt-leaking"
  ],
  "introduced": null,
  "sources": [
    {
      "title": "Training language models to follow instructions with human feedback",
      "authors": "Ouyang et al.",
      "year": 2022,
      "url": "https://arxiv.org/abs/2203.02155"
    },
    {
      "title": "The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions",
      "authors": "Wallace et al.",
      "year": 2024,
      "url": "https://arxiv.org/abs/2404.13208"
    }
  ],
  "url": "https://protologue.com/t/system-prompt/",
  "citation": "Protologue. (2026). System Prompt. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0003). https://protologue.com/t/system-prompt/"
}