{
  "id": "prompt",
  "code": "PTL-0001",
  "term": "Prompt",
  "aliases": [
    "input",
    "context"
  ],
  "category": "foundations",
  "definition": "A prompt is the complete input text, and optionally other media, that is given to a language model to condition its output, including instructions, context, examples, and the user's request.",
  "description": "In chat-based systems the prompt is assembled from several parts, such as a system prompt, the prior conversation turns, retrieved documents, and tool results. The model produces its output by predicting tokens conditioned on this entire input, so every part of the prompt can influence the response, not only the final question.",
  "example": null,
  "broader": [],
  "narrower": [
    "system-prompt",
    "prompt-template"
  ],
  "related": [
    "context-window",
    "context-engineering"
  ],
  "introduced": null,
  "sources": [
    {
      "title": "Language Models are Few-Shot Learners",
      "authors": "Brown et al.",
      "year": 2020,
      "url": "https://arxiv.org/abs/2005.14165"
    },
    {
      "title": "The Prompt Report: A Systematic Survey of Prompt Engineering Techniques",
      "authors": "Schulhoff et al.",
      "year": 2024,
      "url": "https://arxiv.org/abs/2406.06608"
    }
  ],
  "url": "https://protologue.com/t/prompt/",
  "citation": "Protologue. (2026). Prompt. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0001). https://protologue.com/t/prompt/"
}