jevrecipes

Recipe catalog / callback-responsibility

Identify who should initiate a callback

Which party is expected to initiate the next call?

You need to decide whether the business or customer is expected to initiate the next call.

Explore this recipe interactively ยท Source and implementation guide

Use callback-responsibility in TypeScript

Install with npm install jev-recipes. Requires Node.js 22.9 or newer and ES modules. Set TYPESAFE_API_KEY in your server environment for live calls, which send input to TypeSafe and use API quota. See the installation guide.

import { callbackResponsibility } from 'jev-recipes/callback-responsibility';

const result = await callbackResponsibility({
  "conversation": "Avery: I will call you when the replacement arrives. Sam: Thanks, I will wait for your call.",
  "roles": "Avery is the business representative. Sam is the customer.",
  "minConfidence": 0.8
});
console.log(result);

Input contract

FieldTypeNeeded
conversationstringRequired
rolesstringRequired
minConfidencenumberOptional
Full input and result schemas
{
  "input": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "conversation": {
        "type": "string"
      },
      "roles": {
        "type": "string"
      },
      "minConfidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      }
    },
    "required": [
      "conversation",
      "roles"
    ]
  },
  "result": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "model": {
        "type": "string"
      },
      "usage": {
        "type": "object",
        "properties": {
          "input_tokens": {
            "type": "integer",
            "minimum": 0,
            "maximum": 9007199254740991
          },
          "output_tokens": {
            "type": "integer",
            "minimum": 0,
            "maximum": 9007199254740991
          }
        },
        "required": [
          "input_tokens",
          "output_tokens"
        ],
        "additionalProperties": false
      },
      "status": {
        "type": "string",
        "enum": [
          "ready",
          "review"
        ]
      },
      "verdict": {
        "type": "string",
        "enum": [
          "business",
          "customer",
          "either",
          "none",
          "unclear"
        ]
      },
      "confidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      },
      "probabilities": {
        "type": "object",
        "propertyNames": {
          "type": "string",
          "enum": [
            "business",
            "customer",
            "either",
            "none",
            "unclear"
          ]
        },
        "additionalProperties": {
          "type": "number",
          "minimum": 0,
          "maximum": 1
        },
        "required": [
          "business",
          "customer",
          "either",
          "none",
          "unclear"
        ]
      }
    },
    "required": [
      "model",
      "usage",
      "status",
      "verdict",
      "confidence",
      "probabilities"
    ],
    "additionalProperties": false
  }
}

Saved example result

This hand-authored response demonstrates the contract. It is not a model accuracy measurement. Run it without an API key: npx jev-recipes demo callback-responsibility.

{
  "model": "demo-fixture",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0
  },
  "status": "ready",
  "verdict": "business",
  "confidence": 0.94,
  "probabilities": {
    "business": 0.94,
    "customer": 0.01,
    "either": 0.01,
    "none": 0.01,
    "unclear": 0.03
  }
}

Evaluation evidence

Earlier-evaluator measurement

jev-1.13.0 / 2026-09-27 / 40 held-out cases

Scoring revision 1.

98%All-case accuracy
16Sent for review
0Failed calls / cases

24 ready decisions, with 100% accuracy among those decisions.

95% case-level interval: 87% to 100%. Related synthetic cases are correlated.

Measured on these synthetic cases

This measurement uses an earlier or unverified recipe or evaluator version. Rerun with the current recipe and evaluator before treating these numbers as current.

Full report and missesDataset and labels

Use the evaluation guide to measure this decision on your own labeled cases.

Limitations

Related recipes