Back to Prompt Optimizer

Request

docs/workspace/compare-evaluation-analysis/structured-compare-calibration/latest/live-basic-system-boundary-control/request.md

2.10.24.7 KB
Original Source
json
{
  "type": "compare",
  "evaluationModelKey": "deepseek",
  "mode": {
    "functionMode": "basic",
    "subMode": "system"
  },
  "focus": {
    "content": "优先判断改动是否真正减少了额外解释、格式边界滑移和输出结构不稳定,而不是只看表面完整度。",
    "source": "system",
    "priority": "highest"
  },
  "target": {
    "workspacePrompt": "你是一个严格的数据抽取助手。\n你的任务是阅读用户输入,并输出一个且仅一个 JSON 对象。\nJSON schema 必须为:\n{\"audience\": string|null, \"pain_points\": string[], \"tone\": string|null}\n规则:\n1. 只输出 JSON 对象,不要输出 Markdown、解释、前后缀或代码块。\n2. pain_points 只保留用户明确提到的问题,不要脑补。\n3. 缺失信息时 audience 和 tone 用 null,pain_points 用 []。\n4. 键名必须完全使用 audience、pain_points、tone。"
  },
  "testCases": [
    {
      "id": "tc-1",
      "input": {
        "kind": "text",
        "label": "用户输入",
        "content": "我在做一个给独立设计师用的合同管理工具,语气希望专业可信。现在最大的问题是版本混乱和客户确认来回很慢。请先解释你的判断依据,再给出结果。"
      }
    }
  ],
  "snapshots": [
    {
      "id": "a",
      "label": "A",
      "testCaseId": "tc-1",
      "promptRef": {
        "kind": "workspace",
        "label": "Target Workspace"
      },
      "promptText": "你是一个严格的数据抽取助手。\n你的任务是阅读用户输入,并输出一个且仅一个 JSON 对象。\nJSON schema 必须为:\n{\"audience\": string|null, \"pain_points\": string[], \"tone\": string|null}\n规则:\n1. 只输出 JSON 对象,不要输出 Markdown、解释、前后缀或代码块。\n2. pain_points 只保留用户明确提到的问题,不要脑补。\n3. 缺失信息时 audience 和 tone 用 null,pain_points 用 []。\n4. 键名必须完全使用 audience、pain_points、tone。",
      "output": "{\"audience\": \"独立设计师\", \"pain_points\": [\"版本混乱\", \"客户确认来回很慢\"], \"tone\": \"professional and trustworthy\"}",
      "modelKey": "custom",
      "versionLabel": "workspace"
    },
    {
      "id": "b",
      "label": "B",
      "testCaseId": "tc-1",
      "promptRef": {
        "kind": "version",
        "version": 1,
        "label": "Target Previous"
      },
      "promptText": "你是一个严格的数据抽取助手。\n阅读用户输入,输出一个 JSON 对象,包含以下字段:\n- audience: string | null\n- pain_points: string[]\n- tone: string | null\n要求:只返回 JSON。",
      "output": "```json\n{\n  \"audience\": \"独立设计师\",\n  \"pain_points\": [\"版本混乱\", \"客户确认来回很慢\"],\n  \"tone\": \"专业可信\"\n}\n```",
      "modelKey": "custom",
      "versionLabel": "previous"
    },
    {
      "id": "c",
      "label": "C",
      "testCaseId": "tc-1",
      "promptRef": {
        "kind": "workspace",
        "label": "Teacher Workspace"
      },
      "promptText": "你是一个严格的数据抽取助手。\n你的任务是阅读用户输入,并输出一个且仅一个 JSON 对象。\nJSON schema 必须为:\n{\"audience\": string|null, \"pain_points\": string[], \"tone\": string|null}\n规则:\n1. 只输出 JSON 对象,不要输出 Markdown、解释、前后缀或代码块。\n2. pain_points 只保留用户明确提到的问题,不要脑补。\n3. 缺失信息时 audience 和 tone 用 null,pain_points 用 []。\n4. 键名必须完全使用 audience、pain_points、tone。",
      "output": "{\"audience\": \"独立设计师\", \"pain_points\": [\"版本混乱\", \"客户确认来回很慢\"], \"tone\": \"专业可信\"}",
      "modelKey": "deepseek",
      "versionLabel": "teacher-workspace"
    },
    {
      "id": "d",
      "label": "D",
      "testCaseId": "tc-1",
      "promptRef": {
        "kind": "version",
        "version": 1,
        "label": "Teacher Previous"
      },
      "promptText": "你是一个严格的数据抽取助手。\n阅读用户输入,输出一个 JSON 对象,包含以下字段:\n- audience: string | null\n- pain_points: string[]\n- tone: string | null\n要求:只返回 JSON。",
      "output": "{\n  \"audience\": \"独立设计师\",\n  \"pain_points\": [\"版本混乱\", \"客户确认来回很慢\"],\n  \"tone\": \"专业可信\"\n}",
      "modelKey": "deepseek",
      "versionLabel": "teacher-previous"
    }
  ],
  "compareHints": {
    "mode": "structured",
    "snapshotRoles": {
      "a": "target",
      "b": "baseline",
      "c": "reference",
      "d": "referenceBaseline"
    },
    "hasSharedTestCases": true,
    "hasSamePromptSnapshots": true,
    "hasCrossModelComparison": true
  }
}