{
  "title": "RAG Chunking Strategy Designer",
  "description": "Recommends a chunking strategy (size, overlap, splitting rule) for a given document type and retrieval goal.",
  "category": "RAG and Retrieval",
  "tags": [
    "rag",
    "retrieval",
    "chunking"
  ],
  "templateContent": "You are a RAG ingestion specialist. Document type: {{document_type}}.\nTypical structure notes: {{structure_notes}}\nRetrieval goal: {{retrieval_goal}}\nEmbedding model context window (tokens): {{context_window}}\n\nRecommend:\n1. A chunk size (tokens) and overlap, with the reasoning.\n2. A splitting rule (by heading, paragraph, sentence, fixed-size, or a hybrid), and why it fits this document type.\n3. What metadata to attach to each chunk (e.g. source, heading path, page number) and why it helps retrieval or citation.\n4. One risk this strategy does NOT solve, and what would.",
  "variables": [
    {
      "name": "document_type",
      "label": "Document type",
      "type": "text",
      "required": true,
      "default": null,
      "allowedValues": null
    },
    {
      "name": "structure_notes",
      "label": "Structure notes",
      "type": "multiline",
      "required": false,
      "default": null,
      "allowedValues": null
    },
    {
      "name": "retrieval_goal",
      "label": "Retrieval goal",
      "type": "text",
      "required": true,
      "default": null,
      "allowedValues": null
    },
    {
      "name": "context_window",
      "label": "Embedding model context window",
      "type": "number",
      "required": false,
      "default": 8192,
      "allowedValues": null
    }
  ],
  "usageInstructions": "Fill in your document type and what you need retrieval to be good at (exact clause lookup vs. broad thematic summarization); the answer differs a lot between the two.",
  "limitations": "This is a starting heuristic; validate with the evaluation plan from the companion RAG Evaluation Plan prompt rather than assuming it's correct."
}