{
  "hint": {
    "prompt": "TASK: Generate guidance for single selection from dropdown options.\n\nINPUT DETAILS:\n- Text to annotate: \"${text}\"\n- Annotation task: ${description}\n- Available labels: ${labels}\n\nINSTRUCTIONS:\n1. Analyze text features that distinguish between dropdown options\n2. Generate guidance for selecting the most appropriate single option\n3. Focus on decision criteria between available choices\n\nHINT REQUIREMENTS:\n- Identify key distinguishing features between label options\n- Point out decision-making criteria for selection\n- Guide toward systematic evaluation of options\n- Highlight most relevant textual evidence",
    "output_format": "default_hint",
    "img": "/static/ai_assistant_img/blub.svg"
  },
  "keyword": {
    "prompt": "TASK: Extract words/phrases that indicate the correct dropdown selection.\n\nINPUT DETAILS:\n- Text: \"${text}\"\n- Annotation task: ${description}\n- Available labels: ${labels}\n\nOBJECTIVE: Identify terms that point toward the most appropriate label selection.\n\nSELECTION CRITERIA:\n- Strong indicators for specific label options\n- Discriminating features between choices\n- Context clues that favor one option over others\n- Classification markers\n- Decision-supporting evidence",
    "output_format": "default_keyword",
    "img": "/static/ai_assistant_img/highlight.svg"
  },
  "rationale": {
    "name": "Rationale",
    "prompt": "TASK: Generate rationales explaining why each label might apply to this text.\n\nINPUT DETAILS:\n- Text to annotate: \"${text}\"\n- Annotation task: ${description}\n- Available labels: ${labels}\n\nCRITICAL REQUIREMENT:\nYou MUST provide a rationale for EVERY label listed above. Your output must have exactly one entry per label.\n\nINSTRUCTIONS:\nFor EACH available label (ALL of them), provide a brief rationale explaining what evidence in the text could support choosing that label. Be balanced and objective - present the case for each label fairly. If a label doesn't apply well, explain why.\n\nOUTPUT FORMAT:\nReturn a JSON object with \"rationales\" array containing one object per label, each with \"label\" and \"reasoning\" fields.\n\nEXAMPLE OUTPUT:\n{\"rationales\": [{\"label\": \"option1\", \"reasoning\": \"Evidence supporting this choice...\"}, {\"label\": \"option2\", \"reasoning\": \"Evidence supporting this choice...\"}, {\"label\": \"option3\", \"reasoning\": \"This label is less applicable because...\"}]}",
    "output_format": "default_rationale",
    "img": "/static/ai_assistant_img/question.svg"
  }
}