Recipe catalog / politeness-level
Grade expressed politeness
How polite is the wording of message toward its recipient, on a five-level rubric?
You need a graded politeness signal to adapt reply tone, flag hostile messages, or audit outgoing drafts.
Explore this recipe interactively ยท Source and implementation guide
Use politeness-level 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 { politenessLevel } from 'jev-recipes/politeness-level';
const result = await politenessLevel({
"message": "Hi Priya, thanks for turning this around so quickly. When you have a moment, could you also attach the updated invoice? No rush at all.",
"minConfidence": 0.8
});
console.log(result);
Input contract
| Field | Type | Needed |
|---|---|---|
| message | string | Required |
| context | string | Optional |
| minConfidence | number | Optional |
Full input and result schemas
{
"input": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"message": {
"type": "string"
},
"context": {
"type": "string"
},
"minConfidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"message"
]
},
"result": {
"$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"
]
},
"score": {
"type": "number",
"minimum": 0
},
"level": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"probabilities": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"politeness": {
"type": "string",
"enum": [
"hostile",
"curt",
"neutral",
"courteous",
"deferential"
]
}
},
"required": [
"model",
"usage",
"status",
"score",
"level",
"confidence",
"probabilities",
"politeness"
],
"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 politeness-level.
{
"model": "demo-fixture",
"usage": {
"input_tokens": 0,
"output_tokens": 0
},
"status": "ready",
"score": 3.13,
"level": 3,
"confidence": 0.81,
"probabilities": {
"0": 0,
"1": 0,
"2": 0.03,
"3": 0.81,
"4": 0.16
},
"politeness": "courteous"
}
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
- Grades expressed wording, not the writer's attitude or how the recipient will perceive it.
- Politeness norms vary by culture and register. The rubric reflects general written conventions.
Related recipes
- tone-check: Use tone-check to verify a draft matches a specified tone rather than grading politeness.
- frustration-signal: Use frustration-signal for a categorical read on expressed frustration.