AIRouter24 logoAIRouter24
Docs/Integrations

Jev

TypeSafe's structured evaluation model

AIRouter24 adaptation

native

Use AIRouter24's dedicated /typesafe endpoint with your AIRouter24 API key.

Jev is TypeSafe's structured evaluation model. It evaluates one state against typed Noul, Choice, and Score questions and returns calibrated answers with probabilities and confidence.

Usage

const response = await fetch('https://airouter24.com/typesafe/v1/systemone', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.AIROUTER24_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'jev-latest',
    state: 'Help! My payouts have been failing for 3 days.',
    questions: {
      is_urgent: {
        type: 'noul',
        instructions: 'Does this convey urgency?',
        criteria: { true: 'Explicitly time-sensitive', false: 'No urgency expressed' },
      },
      department: {
        type: 'choice',
        instructions: 'Which team should handle this?',
        criteria: {
          billing: 'Payments, invoicing, refunds',
          technical: 'Bugs, outages, integrations',
          sales: 'Pricing, upgrades, new accounts',
        },
      },
      frustration: {
        type: 'score',
        instructions: 'How frustrated is the customer?',
        criteria: ['Calm', 'Frustrated', 'Very angry'],
      },
    },
  }),
})

console.log(await response.json())

Examples

Structured refund review

Evaluate a refund request against a structured order and policy.

const response = await fetch('https://airouter24.com/typesafe/v1/systemone', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.AIROUTER24_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'jev-latest',
    state: {
      ticket: {
        subject: 'Duplicate charge',
        message: 'I was charged twice for order A-104. Please refund the duplicate.',
      },
      order: {
        id: 'A-104',
        charges: [
          { amount_usd: 49, status: 'captured' },
          { amount_usd: 49, status: 'captured' },
        ],
      },
      refund_policy: 'Duplicate charges are eligible for a refund.',
    },
    questions: {
      refund_requested: {
        type: 'noul',
        instructions: 'Does `ticket.message` request a refund?',
      },
      policy_supports_refund: {
        type: 'noul',
        instructions:
          'Does `refund_policy` support the refund requested in `ticket.message`, given `order.charges`?',
      },
    },
  }),
})

console.log(await response.json())

Support department routing

Route a support request to the right department.

const response = await fetch('https://airouter24.com/typesafe/v1/systemone', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.AIROUTER24_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'jev-latest',
    state: 'I cannot log in after changing my password, and the reset email never arrives.',
    questions: {
      department: {
        type: 'choice',
        instructions: 'Which team should handle this support request?',
        criteria: {
          account: 'Login, password, profile, or security issues',
          billing: 'Charges, invoices, refunds, or subscriptions',
          technical: 'Product bugs, outages, or integrations',
          other: 'Requests that do not fit the other departments',
        },
      },
    },
  }),
})

console.log(await response.json())

Account risk assessment

Score account risk and determine whether escalation is needed.

const response = await fetch('https://airouter24.com/typesafe/v1/systemone', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.AIROUTER24_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'jev-latest',
    state: {
      account_age_days: 12,
      recent_events: [
        'Five failed login attempts',
        'Password reset requested from a new country',
        'Successful login from the usual device',
      ],
      account_verified: true,
    },
    questions: {
      risk_level: {
        type: 'score',
        instructions: 'How risky does this account activity appear?',
        criteria: [
          'Low risk: activity is consistent with the account history',
          'Moderate risk: some unusual activity needs monitoring',
          'High risk: multiple strong indicators of account compromise',
        ],
      },
      escalate: {
        type: 'noul',
        instructions: 'Should this account be escalated for manual security review?',
        criteria: {
          true: 'The activity warrants immediate human review',
          false: 'The activity can be handled with normal automated controls',
        },
      },
    },
  }),
})

console.log(await response.json())