jevrecipes

Recipe catalog / followup-timing

Recognize requested follow-up timing

When does the sender want another contact, if any?

You need to distinguish immediate contact, a later time, an event condition, and no follow-up request.

Explore this recipe interactively ยท Source and implementation guide

Use followup-timing 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 { followupTiming } from 'jev-recipes/followup-timing';

const result = await followupTiming({
  "message": "Please check back after our finance team approves the budget.",
  "minConfidence": 0.8
});
console.log(result);

Input contract

FieldTypeNeeded
messagestringRequired
contextstringOptional
minConfidencenumberOptional
Full input and result schemas
{
  "input": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "message": {
        "type": "string"
      },
      "context": {
        "type": "string"
      },
      "minConfidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      }
    },
    "required": [
      "message"
    ]
  },
  "result": {
    "$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": [
          "now",
          "later",
          "after_event",
          "not_requested",
          "declined",
          "unclear"
        ]
      },
      "confidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      },
      "probabilities": {
        "type": "object",
        "propertyNames": {
          "type": "string",
          "enum": [
            "now",
            "later",
            "after_event",
            "not_requested",
            "declined",
            "unclear"
          ]
        },
        "additionalProperties": {
          "type": "number",
          "minimum": 0,
          "maximum": 1
        },
        "required": [
          "now",
          "later",
          "after_event",
          "not_requested",
          "declined",
          "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 followup-timing.

{
  "model": "demo-fixture",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0
  },
  "status": "ready",
  "verdict": "after_event",
  "confidence": 0.93,
  "probabilities": {
    "now": 0.01,
    "later": 0.02,
    "after_event": 0.93,
    "not_requested": 0.01,
    "declined": 0.01,
    "unclear": 0.02
  }
}

Evaluation evidence

Earlier-evaluator measurement

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

Scoring revision 1.

100%All-case accuracy
3Sent for review
0Failed calls / cases

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

95% case-level interval: 91% 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