Playground:判断モデルを体験する

同じ入力に対して、左は生成モデルの典型的な出力、右はJevが返す型付きの判断です。すべての応答は録画済みの実際のAPI結果(jev-1.13.0)で、実際のトークン使用量付きです。入力を編集してみてください。応答は固定で、録画時の元の入力に対するものです。

プリミティブ・Noul

このサポートメッセージは緊急ですか?

NoulはYes/Noの質問を評価し、「Yes」の確率(0〜1の数値そのもの)を返します。

questions(送信されるリクエスト)
{
  "urgency": {
    "type": "noul",
    "instructions": "Does this message express urgency?"
  }
}
生成モデルの出力

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の返答録画済み応答・リアルタイム推論ではない
noul = 0.98
  • Yes・緊急0.98
{
  "model": "jev-1.13.0",
  "answers": {
    "urgency": {
      "type": "noul",
      "noul": 0.98
    }
  }
}
この呼び出し: 301 入力トークン(出力は無料) · 21 output
プリミティブ・Choice

このメールは何を求めていますか?

Choiceは固定の選択肢から1つを選び、各選択肢の確率と全体の信頼度を返します。

questions(送信されるリクエスト)
{
  "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"
    }
  }
}
生成モデルの出力

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の返答録画済み応答・リアルタイム推論ではない
choice = bug_report · 信頼度 0.97
  • バグ報告1.00
  • 使い方の質問0.02
  • その他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
      }
    }
  }
}
この呼び出し: 389 入力トークン(出力は無料) · 50 output
プリミティブ・Score

この問題はどのくらい深刻ですか?

Scoreは順序付きの基準で評価し、値は2つのレベルの間になることもあり、レベルごとの確率と信頼度を返します。

questions(送信されるリクエスト)
{
  "severity": {
    "type": "score",
    "instructions": "How severe is the issue?",
    "criteria": [
      "Minor",
      "Moderate",
      "Critical"
    ]
  }
}
生成モデルの出力

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の返答録画済み応答・リアルタイム推論ではない
score = 1.87(中程度と重大の間)・信頼度 0.81
  • 軽微0.00
  • 中程度0.13
  • 重大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
      }
    }
  }
}
この呼び出し: 321 入力トークン(出力は無料) · 36 output
パイプラインパターン

複合スコアリング:どれだけ早く対応すべきか?

「感情の強さ」と「ビジネス影響」という2つの独立したスコアを重み付きで合成し、対応優先度を導きます。すべて型付きで説明可能です。

questions(送信されるリクエスト)
{
  "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"
    ]
  }
}
生成モデルの出力

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の返答録画済み応答・リアルタイム推論ではない
priority = 0.6×2.0 + 0.4×1.82 = 1.93 → 即時対応
  • 感情・激化0.82
  • 影響・収益遮断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
      }
    }
  }
}
この呼び出し: 397 入力トークン(出力は無料) · 37 output
パイプラインパターン

ファンアウト:すべての判断を1回の呼び出しで

「分類してから質問」は不要。必要になる可能性のある質問をすべて一度に送ります。回答は独立しており、どれを使うかはコードが決めます。出力トークンは無料です。

questions(送信されるリクエスト)
{
  "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"
    ]
  }
}
生成モデルの出力

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の返答録画済み応答・リアルタイム推論ではない
choice=sales_question (conf 0.25) ・ noul=0.86 ・ score=1.74 ― 1回の呼び出しで3つの独立した判断
  • 種別・営業 0.500.50
  • 既存顧客・はい 0.860.86
  • トーン・温厚 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
      }
    }
  }
}
この呼び出し: 459 入力トークン(出力は無料) · 78 output