{
  "title": "Design a Plan for Evaluating Consistency across Repeated Runs",
  "description": "Helps you design a plan for evaluating consistency across repeated runs quickly, while still surfacing the open questions a real version of this work would need answered.",
  "category": "AI Evaluation and Testing",
  "tags": [
    "ai-evaluation",
    "plan-evaluating"
  ],
  "templateContent": "Act as an AI evaluation designer. Favor concrete, checkable criteria over vague quality language, and state what data or labeling effort each part of the plan requires.\n\nTask: Design a plan for evaluating consistency across repeated runs.\n\nContext to use:\n- Feature description: {{feature_description}}\n- Primary risk to guard against: {{primary_risk}}\n- Number of test cases: {{test_case_count}}\n\nResponse format:\n1. Brief recommendation or approach\n2. Main deliverable, organized into clear sections\n3. Assumptions and unresolved questions\n4. Validation or quality checklist",
  "variables": [
    {
      "name": "feature_description",
      "label": "Feature description",
      "type": "multiline",
      "required": true,
      "default": null,
      "allowedValues": null
    },
    {
      "name": "primary_risk",
      "label": "Primary risk to guard against",
      "type": "text",
      "required": true,
      "default": null,
      "allowedValues": null
    },
    {
      "name": "test_case_count",
      "label": "Number of test cases",
      "type": "number",
      "required": false,
      "default": 10,
      "allowedValues": null
    }
  ],
  "usageInstructions": "Fill in the context fields with your real project details, then review the assumptions section before acting on the output.",
  "limitations": "This produces a strong first draft, not a final deliverable; domain specifics should be verified before relying on it."
}