Recipe catalog / commitment-strength
Grade commitment strength
How firmly does statement commit its speaker to an action or outcome, on a five-level rubric?
You need to grade how strongly a message commits someone to act before tracking it as a promise or follow-up.
Explore this recipe interactively ยท Source and implementation guide
Use commitment-strength 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 { commitmentStrength } from 'jev-recipes/commitment-strength';
const result = await commitmentStrength({
"statement": "I will have the revised contract in your inbox by 5pm Thursday, and I will call you as soon as it is sent.",
"minConfidence": 0.8
});
console.log(result);
Input contract
| Field | Type | Needed |
|---|---|---|
| statement | string | Required |
| context | string | Optional |
| minConfidence | number | Optional |
Full input and result schemas
{
"input": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"statement": {
"type": "string"
},
"context": {
"type": "string"
},
"minConfidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"statement"
]
},
"result": {
"$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
}
},
"commitment": {
"type": "string",
"enum": [
"none",
"vague",
"conditional",
"firm",
"binding"
]
}
},
"required": [
"model",
"usage",
"status",
"score",
"level",
"confidence",
"probabilities",
"commitment"
],
"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 commitment-strength.
{
"model": "demo-fixture",
"usage": {
"input_tokens": 0,
"output_tokens": 0
},
"status": "ready",
"score": 3.85,
"level": 4,
"confidence": 0.87,
"probabilities": {
"0": 0,
"1": 0,
"2": 0.02,
"3": 0.11,
"4": 0.87
},
"commitment": "binding"
}
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 speaker's sincerity, authority, or likelihood of following through.
- The score is an expected value over rubric levels. Application code chooses cutoffs.
Related recipes
- promise-check: Use promise-check to detect whether a message contains a promise at all.
- certainty-match: Use certainty-match to compare expressed certainty with the evidence rather than commitment to act.