Playground：亲手感受判断模型

同一个输入，左边是生成式模型的典型输出，右边是 Jev 返回的类型化判定。所有响应均为预录的真实 API 结果（jev-1.13.0），标注了真实的 token 用量。修改输入试试——响应不会变，它属于录制时的原始输入。

原语 · Noul

这条客服消息紧急吗？

Noul 评估一个是/否问题，返回「是」的概率——它本身就是 0–1 的数值。

state（输入，可编辑）

questions（发出的请求）

{
  "urgency": {
    "type": "noul",
    "instructions": "Does this message express urgency?"
  }
}

生成式模型会输出

I'm really sorry to hear you've been having trouble connecting your Stripe account. I understand how frustrating that must be, especially when it affects your sales. Let me help you look into this. Could you tell me a bit more about...

Jev 返回预录响应 · 非实时推理

noul = 0.98

是 · urgent0.98

{
  "model": "jev-1.13.0",
  "answers": {
    "urgency": {
      "type": "noul",
      "noul": 0.98
    }
  }
}

本次调用: 301 input tokens（输出免费） · 21 output

Noul 原语文档 →置信度路由模式 →

原语 · Choice

这封邮件想要什么？

Choice 从一组固定选项中选一个，附带每个选项的概率与整体置信度。

state（输入，可编辑）

questions（发出的请求）

{
  "intent": {
    "type": "choice",
    "instructions": "What is the primary intent of this message?",
    "criteria": {
      "bug_report": "Reporting something broken",
      "feature_request": "Asking for new functionality",
      "how_to_question": "Asking how to do something",
      "other": "None of the above"
    }
  }
}

生成式模型会输出

Thanks for reaching out! It sounds like you are experiencing an error with the export functionality on the reports page when using Safari. This could be related to browser compatibility. Have you tried...

Jev 返回预录响应 · 非实时推理

choice = bug_report · confidence 1.0

bug 报告1.00
使用提问0.02
其他0.01

{
  "model": "jev-1.13.0",
  "answers": {
    "intent": {
      "type": "choice",
      "choice": "bug_report",
      "confidence": 1,
      "probabilities": {
        "bug_report": 1,
        "feature_request": 0,
        "how_to_question": 0,
        "other": 0
      }
    }
  }
}

本次调用: 389 input tokens（输出免费） · 50 output

Choice 原语文档 →意图路由模式 →

原语 · Score

这个问题有多严重？

Score 按有序档位打分，分数可落在两档之间，附每档概率与置信度。

state（输入，可编辑）

questions（发出的请求）

{
  "severity": {
    "type": "score",
    "instructions": "How severe is the issue?",
    "criteria": [
      "Minor",
      "Moderate",
      "Critical"
    ]
  }
}

生成式模型会输出

I'm so sorry to hear that your payouts have been failing for three days. That sounds really stressful. Payout failures can have several causes, such as... (510 more words)

Jev 返回预录响应 · 非实时推理

score = 1.87（介于中等与严重之间）· confidence 0.81

轻微0.00
中等0.13
严重0.87

{
  "model": "jev-1.13.0",
  "answers": {
    "severity": {
      "type": "score",
      "score": 1.87,
      "confidence": 0.81,
      "legend": {
        "0": "Minor",
        "1": "Moderate",
        "2": "Critical"
      },
      "probabilities": {
        "0": 0,
        "1": 0.13,
        "2": 0.87
      }
    }
  }
}

本次调用: 321 input tokens（输出免费） · 36 output

Score 原语文档 →复合评分模式 →

管线模式

复合评分：一张工单该多快响应？

把「情绪激动度」与「业务影响」两个独立评分加权合成一个响应优先级，全部类型化、可解释。

state（输入，可编辑）

questions（发出的请求）

{
  "emotional_intensity": {
    "type": "score",
    "instructions": "How emotionally intense is this message?",
    "criteria": [
      "Calm and factual",
      "Frustrated but professional",
      "Angry or escalating"
    ]
  },
  "business_impact": {
    "type": "score",
    "instructions": "How severe is the business impact described?",
    "criteria": [
      "No material impact",
      "Degraded operations",
      "Revenue-blocking outage"
    ]
  }
}

生成式模型会输出

Dear valued customer, thank you for bringing this to our attention. We sincerely apologize for the inconvenience caused by the API errors. Our engineering team is investigating the issue with the highest priority...

Jev 返回预录响应 · 非实时推理

priority = 0.6×2.0 + 0.4×1.82 = 1.93 → 立即响应

情绪 · 激愤0.82
影响 · 营收阻断1.00

{
  "model": "jev-1.13.0",
  "answers": {
    "emotional_intensity": {
      "type": "score",
      "score": 1.82,
      "confidence": 0.74,
      "legend": {
        "0": "Calm and factual",
        "1": "Frustrated but professional",
        "2": "Angry or escalating"
      },
      "probabilities": {
        "0": 0,
        "1": 0.18,
        "2": 0.82
      }
    },
    "business_impact": {
      "type": "score",
      "score": 2,
      "confidence": 1,
      "legend": {
        "0": "No material impact",
        "1": "Degraded operations",
        "2": "Revenue-blocking outage"
      },
      "probabilities": {
        "0": 0,
        "1": 0,
        "2": 1
      }
    }
  }
}

本次调用: 397 input tokens（输出免费） · 37 output

复合评分模式 →LLM 护栏案例 →

管线模式

扇出并行：一次调用问完所有判断

不用「先分类再追问」。把所有可能用到的问题一次发出，答案相互独立，代码再决定用哪些。输出 tokens 免费。

state（输入，可编辑）

questions（发出的请求）

{
  "request_type": {
    "type": "choice",
    "instructions": "What kind of request is this?",
    "criteria": {
      "sales_question": "Asking about plans, pricing, compliance, or contracts",
      "billing_issue": "Payment, invoice, or refund matters",
      "technical_support": "Something is broken or needs troubleshooting"
    }
  },
  "is_existing_customer": {
    "type": "noul",
    "instructions": "Does the writer appear to be an existing customer?"
  },
  "tone_politeness": {
    "type": "score",
    "instructions": "How courteous is the tone overall?",
    "criteria": [
      "Blunt or rude",
      "Neutral",
      "Warm and appreciative"
    ]
  }
}

生成式模型会输出

Thank you for reaching out! To answer your questions: regarding SOC 2 report access, our enterprise plan does include... (the answer continues for 300+ words, mixing both topics with no typed structure to route on)

Jev 返回预录响应 · 非实时推理

choice=sales_question (conf 0.25) · noul=0.86 · score=1.74 —— 一次调用，三个独立判断

类型 · 售前咨询 0.500.50
老客户 · 是 0.860.86
语气 · 温和 0.740.74

{
  "model": "jev-1.13.0",
  "answers": {
    "request_type": {
      "type": "choice",
      "choice": "sales_question",
      "confidence": 0.25,
      "probabilities": {
        "sales_question": 0.5,
        "billing_issue": 0.5,
        "technical_support": 0
      }
    },
    "is_existing_customer": {
      "type": "noul",
      "noul": 0.86
    },
    "tone_politeness": {
      "type": "score",
      "score": 1.74,
      "confidence": 0.61,
      "legend": {
        "0": "Blunt or rude",
        "1": "Neutral",
        "2": "Warm and appreciative"
      },
      "probabilities": {
        "0": 0,
        "1": 0.26,
        "2": 0.74
      }
    }
  }
}

本次调用: 459 input tokens（输出免费） · 78 output

扇出并行模式 →并行问题案例 →