Recipe catalog / defect-report-facets
Label the facets of a defect report
Which of these does report state: the part or lot identifier, a description of the defect, where it was detected, the quantity affected, a containment action?
You need to check an incoming nonconformance or defect report for the facts a quality process expects before it is accepted, or to tell the reporter which facts are missing.
Explore this recipe interactively ยท Source and implementation guide
Use defect-report-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 { defectReportFacets } from 'jev-recipes/defect-report-facets';
const result = await defectReportFacets({
"report": "NCR-2041. Part 88-3312-B mounting bracket, supplier lot L26091 from Kestrel Metalworks. Flange thickness measured 2.68 to 2.74 mm on all 6 sampled pieces against the drawing callout of 3.0 mm +/- 0.1 mm. Found at incoming inspection, receiving dock 2, during the standard AQL sample on 2026-09-22. Lot quantity received: 1,200 pieces; the whole lot is suspect since every sample failed. Requesting disposition from engineering.",
"minConfidence": 0.8
});
console.log(result);Input contract
| Field | Type | Needed |
|---|---|---|
| report | string | Required |
| minConfidence | number | Optional |
Full input and result schemas
{
"input": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"report": {
"type": "string"
},
"minConfidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"report"
]
},
"result": {
"$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": [
"statesPartId",
"statesDefect",
"statesDetectionPoint",
"statesQuantity",
"statesContainment"
]
}
},
"labels": {
"type": "object",
"properties": {
"statesPartId": {
"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
},
"statesDefect": {
"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
},
"statesDetectionPoint": {
"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
},
"statesQuantity": {
"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
},
"statesContainment": {
"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": [
"statesPartId",
"statesDefect",
"statesDetectionPoint",
"statesQuantity",
"statesContainment"
],
"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 defect-report-facets.
{
"model": "demo-fixture",
"usage": {
"input_tokens": 0,
"output_tokens": 0
},
"status": "ready",
"detected": [
"statesPartId",
"statesDefect",
"statesDetectionPoint",
"statesQuantity"
],
"labels": {
"statesPartId": {
"status": "ready",
"verdict": "present",
"probability": 0.96,
"confidence": 0.96
},
"statesDefect": {
"status": "ready",
"verdict": "present",
"probability": 0.95,
"confidence": 0.95
},
"statesDetectionPoint": {
"status": "ready",
"verdict": "present",
"probability": 0.92,
"confidence": 0.92
},
"statesQuantity": {
"status": "ready",
"verdict": "present",
"probability": 0.93,
"confidence": 0.93
},
"statesContainment": {
"status": "ready",
"verdict": "absent",
"probability": 0.07,
"confidence": 0.9299999999999999
}
}
}
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 a report can carry several or none.
- Detects that a fact is stated, not that it is correct. A part number can be mistyped and a stated quantity can be wrong.
- Does not check the report against part masters, lot records, or your nonconformance form. Validate identifiers and quantities in application code.
Related recipes
- bug-report-completeness: Use bug-report-completeness for software bug reports, where the expected parts are reproduction steps, expected and actual behavior, and environment.
- clarify: Use clarify to phrase the follow-up question once a report is known to be missing a facet.