Recipe catalog / answerability
Check answerability
Decide whether supplied evidence can answer an entire question.
You need to know if you have enough evidence and can answer a question.
Explore this recipe interactively ยท Source and implementation guide
Use answerability 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 { answerability } from 'jev-recipes/answerability';
const result = await answerability({
"question": "How do I reset my password, and when does the link expire?",
"evidence": [
{
"id": "reset",
"text": "Select Forgot password on the sign-in page. Reset links expire after 30 minutes."
}
]
});
console.log(result);
Input contract
| Field | Type | Needed |
|---|---|---|
| question | string | Required |
| evidence | array | Required |
| minConfidence | number | Optional |
Full input and result schemas
{
"input": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"question": {
"type": "string"
},
"evidence": {
"minItems": 1,
"maxItems": 50,
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"text": {
"type": "string"
}
},
"required": [
"id",
"text"
]
}
},
"minConfidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"question",
"evidence"
]
},
"result": {
"$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": [
"sufficient",
"partial",
"insufficient",
"conflicting"
]
},
"canAnswer": {
"type": "boolean"
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"probabilities": {
"type": "object",
"propertyNames": {
"type": "string",
"enum": [
"sufficient",
"partial",
"insufficient",
"conflicting"
]
},
"additionalProperties": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"required": [
"sufficient",
"partial",
"insufficient",
"conflicting"
]
}
},
"required": [
"model",
"usage",
"status",
"verdict",
"canAnswer",
"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 answerability.
{
"model": "demo-fixture",
"usage": {
"input_tokens": 0,
"output_tokens": 0
},
"status": "ready",
"verdict": "sufficient",
"canAnswer": true,
"confidence": 0.96,
"probabilities": {
"sufficient": 0.97,
"partial": 0.01,
"insufficient": 0.01,
"conflicting": 0.01
}
}
Evaluation evidence
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
- Does not generate an answer or establish source truth.
- Provide 1 to 50 evidence passages with unique IDs; handle empty retrieval in application code.
Related recipes
- answer-coverage: Use answer-coverage after drafting to check whether each question was addressed.