Recipe catalog / performance-feedback-facets
Label the aspects performance feedback addresses
Which aspects of a musical performance does feedback address: rhythm, pitch or intonation, dynamics, technique, and expression or phrasing?
You are building a practice app or lesson tool and want to know which musical aspects a piece of teacher or automated feedback covers, so you can track what a student hears about over time or flag feedback that neglects an aspect.
Explore this recipe interactively ยท Source and implementation guide
Use performance-feedback-facets 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 { performanceFeedbackFacets } from 'jev-recipes/performance-feedback-facets';
const result = await performanceFeedbackFacets({
"feedback": "Good work this week. The dotted eighths in bars 9 to 12 are still rushing, so put the metronome on and count the sixteenth underneath. The high F-sharp in bar 14 was flat every time; check it against the open E before you start. The forte at the return of the theme was too loud next to the quiet opening; bring it down one level.",
"minConfidence": 0.8
});
console.log(result);Input contract
| Field | Type | Needed |
|---|---|---|
| feedback | string | Required |
| minConfidence | number | Optional |
Full input and result schemas
{
"input": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"feedback": {
"type": "string"
},
"minConfidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"feedback"
]
},
"result": {
"$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"
]
},
"detected": {
"type": "array",
"items": {
"type": "string",
"enum": [
"mentionsRhythm",
"mentionsPitch",
"mentionsDynamics",
"mentionsTechnique",
"mentionsExpression"
]
}
},
"labels": {
"type": "object",
"properties": {
"mentionsRhythm": {
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"present",
"absent"
]
},
"probability": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"status",
"verdict",
"probability",
"confidence"
],
"additionalProperties": false
},
"mentionsPitch": {
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"present",
"absent"
]
},
"probability": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"status",
"verdict",
"probability",
"confidence"
],
"additionalProperties": false
},
"mentionsDynamics": {
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"present",
"absent"
]
},
"probability": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"status",
"verdict",
"probability",
"confidence"
],
"additionalProperties": false
},
"mentionsTechnique": {
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"present",
"absent"
]
},
"probability": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"status",
"verdict",
"probability",
"confidence"
],
"additionalProperties": false
},
"mentionsExpression": {
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"present",
"absent"
]
},
"probability": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"status",
"verdict",
"probability",
"confidence"
],
"additionalProperties": false
}
},
"required": [
"mentionsRhythm",
"mentionsPitch",
"mentionsDynamics",
"mentionsTechnique",
"mentionsExpression"
],
"additionalProperties": false
}
},
"required": [
"model",
"usage",
"status",
"detected",
"labels"
],
"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 performance-feedback-facets.
{
"model": "demo-fixture",
"usage": {
"input_tokens": 0,
"output_tokens": 0
},
"status": "ready",
"detected": [
"mentionsRhythm",
"mentionsPitch",
"mentionsDynamics"
],
"labels": {
"mentionsRhythm": {
"status": "ready",
"verdict": "present",
"probability": 0.96,
"confidence": 0.96
},
"mentionsPitch": {
"status": "ready",
"verdict": "present",
"probability": 0.95,
"confidence": 0.95
},
"mentionsDynamics": {
"status": "ready",
"verdict": "present",
"probability": 0.91,
"confidence": 0.91
},
"mentionsTechnique": {
"status": "ready",
"verdict": "absent",
"probability": 0.06,
"confidence": 0.94
},
"mentionsExpression": {
"status": "ready",
"verdict": "absent",
"probability": 0.08,
"confidence": 0.92
}
}
}
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
- Labels are independent, so feedback can address several aspects or none.
- Detects that an aspect is addressed, not whether the comment is correct, fair, or useful.
- Does not measure the performance itself. Deciding which aspects a lesson should cover belongs in application code or with the teacher.
Related recipes
- feedback-actionability: Use feedback-actionability to grade whether the feedback tells the student what to do, rather than which aspects it covers.
- tone-check: Use tone-check to judge whether feedback meets a tone requirement such as encouraging or direct.