Recipe catalog / answer-coverage
Check answer coverage
Check whether a draft answers each supplied question.
You have a draft and need to check whether it answers each supplied question.
Explore this recipe interactively ยท Source and implementation guide
Use answer-coverage 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 { answerCoverage } from 'jev-recipes/answer-coverage';
const result = await answerCoverage({
"draft": "Select Forgot password on the sign-in page.",
"questions": [
{
"id": "reset",
"text": "How do I reset my password?"
},
{
"id": "expiry",
"text": "When does the link expire?"
}
]
});
console.log(result);
Input contract
| Field | Type | Needed |
|---|---|---|
| draft | string | Required |
| questions | array | Required |
| minConfidence | number | Optional |
Full input and result schemas
{
"input": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"draft": {
"type": "string"
},
"questions": {
"minItems": 1,
"maxItems": 50,
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"text": {
"type": "string"
}
},
"required": [
"id",
"text"
]
}
},
"minConfidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"draft",
"questions"
]
},
"result": {
"$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"
]
},
"allAnswered": {
"type": "boolean"
},
"checks": {
"minItems": 1,
"maxItems": 50,
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"answered",
"partial",
"missing",
"unclear"
]
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"probabilities": {
"type": "object",
"propertyNames": {
"type": "string",
"enum": [
"answered",
"partial",
"missing",
"unclear"
]
},
"additionalProperties": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"required": [
"answered",
"partial",
"missing",
"unclear"
]
}
},
"required": [
"id",
"status",
"verdict",
"confidence",
"probabilities"
],
"additionalProperties": false
}
}
},
"required": [
"model",
"usage",
"status",
"allAnswered",
"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 answer-coverage.
{
"model": "demo-fixture",
"usage": {
"input_tokens": 0,
"output_tokens": 0
},
"status": "ready",
"allAnswered": false,
"checks": [
{
"id": "reset",
"status": "ready",
"verdict": "answered",
"confidence": 0.96,
"probabilities": {
"answered": 1,
"partial": 0,
"missing": 0,
"unclear": 0
}
},
{
"id": "expiry",
"status": "ready",
"verdict": "missing",
"confidence": 0.96,
"probabilities": {
"answered": 0,
"partial": 0,
"missing": 1,
"unclear": 0
}
}
]
}
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
- Checks supplied question IDs only. It does not extract questions or verify the draft against sources.
- Supply 1 to 50 items per list, each with a unique non-empty ID and non-empty text.
Related recipes
- answer-relevance: Use answer-relevance to assess how directly the draft addresses the overall request.