Recipe catalog / consent-request
Detect an explicit consent request
Does text explicitly ask the reader for agreement or permission before something proceeds?
You need a yes/no check that a message, prompt, or notice actually asks for consent instead of announcing or assuming it before an action proceeds.
Explore this recipe interactively ยท Source and implementation guide
Use consent-request 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 { consentRequest } from 'jev-recipes/consent-request';
const result = await consentRequest({
"text": "Before we enable call recording on your account, we need your permission. Do you agree to have your support calls recorded for quality review? Reply YES to agree or NO to keep recording off.",
"minConfidence": 0.8
});
console.log(result);
Input contract
| Field | Type | Needed |
|---|---|---|
| text | string | Required |
| minConfidence | number | Optional |
Full input and result schemas
{
"input": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"text": {
"type": "string"
},
"minConfidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"text"
]
},
"result": {
"$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": [
"requested",
"absent"
]
}
},
"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 consent-request.
{
"model": "demo-fixture",
"usage": {
"input_tokens": 0,
"output_tokens": 0
},
"status": "ready",
"probability": 0.95,
"confidence": 0.95,
"verdict": "requested"
}
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
- Detects that agreement is asked for, not whether the request is clear, specific, or freely given enough to count as valid consent under any law.
- Judges the supplied text alone. It does not know whether the action was in fact gated on the answer.
Related recipes
- confirmation-match: Use confirmation-match to check whether a reply actually grants the consent that was requested.
- promise-check: Use promise-check to detect commitments the text makes to the reader rather than permission it asks of them.