Check required information

Identify missing or ambiguous information before proceeding.

You need to check for missing or ambiguous requirements before proceeding.

Explore this recipe interactively · Source and implementation guide

Use clarify 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 { clarify } from 'jev-recipes/clarify';

const result = await clarify({
  "request": "Please cancel it.",
  "context": "The customer has a monthly storage subscription and a pending hardware order.",
  "requirements": [
    {
      "id": "target",
      "description": "Which product or order should be changed"
    },
    {
      "id": "action",
      "description": "What change the customer wants"
    }
  ]
});
console.log(result);

Input contract

Field	Type	Needed
request	string	Required
context	string	Optional
requirements	array	Required
minConfidence	number	Optional

Full input and result schemas

{
  "input": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "request": {
        "type": "string"
      },
      "context": {
        "type": "string"
      },
      "requirements": {
        "minItems": 1,
        "maxItems": 50,
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "id": {
              "type": "string"
            },
            "description": {
              "type": "string"
            }
          },
          "required": [
            "id",
            "description"
          ]
        }
      },
      "minConfidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      }
    },
    "required": [
      "request",
      "requirements"
    ]
  },
  "result": {
    "$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"
        ]
      },
      "canProceed": {
        "type": "boolean"
      },
      "missing": {
        "type": "array",
        "items": {
          "type": "string"
        }
      },
      "ambiguous": {
        "type": "array",
        "items": {
          "type": "string"
        }
      },
      "checks": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "id": {
              "type": "string"
            },
            "status": {
              "type": "string",
              "enum": [
                "ready",
                "review"
              ]
            },
            "verdict": {
              "type": "string",
              "enum": [
                "present",
                "missing",
                "ambiguous"
              ]
            },
            "confidence": {
              "type": "number",
              "minimum": 0,
              "maximum": 1
            },
            "probabilities": {
              "type": "object",
              "propertyNames": {
                "type": "string",
                "enum": [
                  "present",
                  "missing",
                  "ambiguous"
                ]
              },
              "additionalProperties": {
                "type": "number",
                "minimum": 0,
                "maximum": 1
              },
              "required": [
                "present",
                "missing",
                "ambiguous"
              ]
            }
          },
          "required": [
            "id",
            "status",
            "verdict",
            "confidence",
            "probabilities"
          ],
          "additionalProperties": false
        }
      }
    },
    "required": [
      "model",
      "usage",
      "status",
      "canProceed",
      "missing",
      "ambiguous",
      "checks"
    ],
    "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 clarify.

{
  "model": "demo-fixture",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0
  },
  "status": "ready",
  "canProceed": false,
  "missing": [],
  "ambiguous": [
    "target"
  ],
  "checks": [
    {
      "id": "target",
      "status": "ready",
      "verdict": "ambiguous",
      "confidence": 0.96,
      "probabilities": {
        "present": 0.015,
        "missing": 0.015,
        "ambiguous": 0.97
      }
    },
    {
      "id": "action",
      "status": "ready",
      "verdict": "present",
      "confidence": 0.96,
      "probabilities": {
        "present": 0.97,
        "missing": 0.015,
        "ambiguous": 0.015
      }
    }
  ]
}

Evaluation evidence

Unknown response origin

No verified live accuracy measurement is available. Evaluate representative cases before using this decision in your workflow.

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

Limitations

Checks only the requirements you supply; does not generate follow-up questions.
Provide 1 to 50 requirements with unique IDs.

Related recipes

query-specificity: Use query-specificity to assess how focused the question is, without a requirements list.