Recipe catalog / intake-question-fit

Check an intake question against its purpose

Does question ask only for what purpose needs, avoiding unrelated personal detail?

You are drafting or reviewing intake form questions and want a check that each one collects only what its stated purpose requires.

Explore this recipe interactively · Source and implementation guide

Use intake-question-fit 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 { intakeQuestionFit } from 'jev-recipes/intake-question-fit';

const result = await intakeQuestionFit({
  "question": "To schedule your flu shot, please tell us your date of birth, your insurance provider and member ID, and whether you have ever been treated for depression or anxiety.",
  "purpose": "Schedule a routine flu shot appointment and verify insurance coverage for the visit.",
  "minConfidence": 0.8
});
console.log(result);

Input contract

{
  "input": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "question": {
        "type": "string"
      },
      "purpose": {
        "type": "string"
      },
      "minConfidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      }
    },
    "required": [
      "question",
      "purpose"
    ]
  },
  "result": {
    "$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"
        ]
      },
      "probability": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      },
      "confidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      },
      "verdict": {
        "type": "string",
        "enum": [
          "fits",
          "overreaches"
        ]
      }
    },
    "required": [
      "model",
      "usage",
      "status",
      "probability",
      "confidence",
      "verdict"
    ],
    "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 intake-question-fit.

{
  "model": "demo-fixture",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0
  },
  "status": "ready",
  "probability": 0.06,
  "confidence": 0.94,
  "verdict": "overreaches"
}

Evaluation evidence

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

Limitations

• Judges relevance to the stated purpose only, not legal permissibility, consent requirements, or minimum-necessary compliance under any regulation.
• Depends on how precisely purpose is described; a vague purpose makes almost any question fit.

Related recipes

• question-relevance: Use question-relevance to check whether a question is on topic for a conversation rather than scoped to a data-collection purpose.
• instruction-fit: Use instruction-fit to check whether a drafted question follows the form-writing instructions you gave.