Recipe catalog / audience-fit
Check audience fit
Does the level of explanation in document fit the knowledge and needs explicitly described in audience?
You need to check whether a document suits the stated audience knowledge and needs.
Explore this recipe interactively ยท Source and implementation guide
Use audience-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 { audienceFit } from 'jev-recipes/audience-fit';
const result = await audienceFit({
"document": "Rotate the OAuth refresh token and invalidate the active session grant.",
"audience": "A customer unfamiliar with authentication terminology who wants to sign out of all devices."
});
console.log(result);
Input contract
| Field | Type | Needed |
|---|---|---|
| document | string | Required |
| audience | string | Required |
| minConfidence | number | Optional |
Full input and result schemas
{
"input": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"document": {
"type": "string"
},
"audience": {
"type": "string"
},
"minConfidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"document",
"audience"
]
},
"result": {
"$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": [
"appropriate",
"too_technical",
"too_basic",
"unclear"
]
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"probabilities": {
"type": "object",
"propertyNames": {
"type": "string",
"enum": [
"appropriate",
"too_technical",
"too_basic",
"unclear"
]
},
"additionalProperties": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"required": [
"appropriate",
"too_technical",
"too_basic",
"unclear"
]
}
},
"required": [
"model",
"usage",
"status",
"verdict",
"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 audience-fit.
{
"model": "demo-fixture",
"usage": {
"input_tokens": 0,
"output_tokens": 0
},
"status": "ready",
"verdict": "too_technical",
"confidence": 0.96,
"probabilities": {
"appropriate": 0,
"too_technical": 1,
"too_basic": 0,
"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
- Uses only the supplied audience description. It does not infer ability from identity or rewrite the document.
Related recipes
- tone-check: Use tone-check to evaluate specific writing criteria.