Function Review
Hand off to an LLM
Analyzes function performance and estimate human review requirements. Calculates sample sizes needed to achieve target accuracy with statistical confidence, finds optimal confidence thresholds within a configurable range, and estimates review effort. Supports custom threshold ranges for focused analysis (e.g., analyze only 0.7-0.9 range).
Authorization
API Key x-api-key<token>
Authenticate using API Key in request header
In: header
Request Body
application/json
TypeScript Definitions
Use the request body type in TypeScript.
Response Body
application/json
application/json
application/json
curl -X POST "https://api.bem.ai/v2/functions/review" \ -H "Content-Type: application/json" \ -d '{ "functionName": "invoice-transformer", "marginOfError": 0.05 }'{
"functionName": "invoice-transformer",
"functionVersionNum": 3,
"estimate": {
"totalTransformations": 1000,
"labeledTransformations": 200,
"unlabeledTransformations": 800,
"missingEvaluations": 50,
"confidenceDistribution": {
"high": 500,
"medium": 350,
"low": 150
},
"thresholdMatrix": [
{
"threshold": 0.8,
"tp": 85,
"fp": 12,
"fn": 15,
"tn": 88,
"accuracyAboveThreshold": {
"95": {
"ciLower": 0.8456,
"mid": 0.875,
"ciUpper": 0.9044,
"currentSample": 120,
"sampleNeeded": 30
}
}
}
]
},
"metrics": {
"fieldMetrics": [
{
"fieldPath": "/invoice/number",
"metrics": {
"accuracy": 0.95,
"precision": 0.98,
"recall": 0.92,
"f1Score": 0.95,
"tp": 92,
"fp": 2,
"tn": 0,
"fn": 8
}
},
{
"fieldPath": "/invoice/amount",
"metrics": {
"accuracy": 0.88,
"precision": 0.9,
"recall": 0.85,
"f1Score": 0.87,
"tp": 85,
"fp": 9,
"tn": 0,
"fn": 15
}
}
],
"precisionRecallAuc": 0.8542,
"aggregateMetrics": {
"accuracy": 0.7407,
"precision": 0.9524,
"recall": 0.7692,
"f1Score": 0.8511,
"tp": 40,
"fp": 2,
"tn": 0,
"fn": 12
}
}
}{
"message": "string",
"code": 0,
"details": {}
}{
"message": "string",
"code": 0,
"details": {}
}