BRAINIAC Inventory Intelligence Data Normalize is a paid API for AI agents from www.brainiac.software, paid per call via x402, $0.04/call, status unknown (last checked 2026-11-12).
Normalizes messy inventory, sales, purchase, and supplier data into a clean, structured format ready for inventory intelligence computations
Pay-per-call APIs for AI agents: OFAC sanctions screening, compliance checks, token security, and Base chain data via x402. No account. Fixed USDC price. MCP-ready.
Returns a normalized JSON object containing cleaned arrays of products, sales, purchases, and suppliers with per-record flags indicating which fields were supplied vs inferred. Also includes a list of findings (warnings, ignored lines), assumptions made during normalization (history window, forecast horizon, z-score, etc.), and explicit limitations. Boolean flags confirm that no prices, demand figures, or lead times were invented and that no purchase orders were created or external inventory systems accessed.
POSThttps://www.brainiac.software/api/v1/inventory-intelligence/data-normalize?utm_source=zero.xyzUse this endpoint as the first step in any inventory intelligence pipeline when your raw data is messy, mixed-format, or unvalidated. It is specifically designed to accept CSV, JSON, plain text, or structured arrays and return a clean normalized payload with explicit provenance flags — ideal before calling reorder-point or safety-stock computation endpoints. Prefer this over generic data cleaning tools when you need inventory-domain-aware normalization that understands SKUs, lead times, MOQs, and sales history semantics.
| Field | Type | Description |
|---|---|---|
| csv | string | |
| asOf | string | |
| file | object | |
| json | string | |
| text | string | |
| sales | array | |
| products | array | |
| slowDays | number | |
| purchases | array | |
| slowUnits | number | |
| suppliers | array | |
| reviewDays | number | |
| historyDays | integer | |
| forecastDays | integer | |
| serviceLevelZ | number | |
| excessDaysCover | number |
{
"type": "json",
"example": {
"sales": [
{
"sku": "SKU-1",
"date": "2026-11-01",
"units": 8,
"unitsSupplied": true
}
],
"status": "normalized",
"findings": [
{
"code": "unlabeled_line",
"kind": "ignored",
"detail": "Lines without a recognized label were not read and their text was not copied.",
"subject": ""
}
],
"products": [
{
"sku": "SKU-1",
"name": "Widget",
"onHand": 40,
"onOrder": 10,
"unitCost": 2.5,
"saleCount": 1,
"purchaseCount": 1,
"onHandSupplied": true,
"onOrderSupplied": true,
"unitCostSupplied": true,
"leadTimeDaysSupplied": true
}
],
"checkedAt": "2026-11-04T19:00:00.000Z",
"purchases": [
{
"sku": "SKU-1",
"date": "2026-10-20",
"units": 50,
"unitPrice": 2.1,
"unitsSupplied": true,
"unitPriceSupplied": true
}
],
"suppliers": [
{
"moq": 20,
"sku": "SKU-1",
"supplierId": "SUP-1",
"moqSupplied": true,
"leadTimeDays": 7,
"leadTimeDaysSupplied": true
}
],
"assumptions": [
"serviceLevelZ=1.65 (explicit normal z factor for safety stock)",
"reviewDays=0",
"historyDays=90",
"forecastDays=30",
"excessDaysCover=90",
"slowUnits=5 over slowDays=90",
"Daily demand average fills missing days in the history window with zero when a history end date exists.",
"Seasonality is not added. Only variation already present in the supplied history affects the standard deviation."
],
"limitations": [
"Products, sales, supplier lead times, and purchases are copied only from labeled fields supplied by the caller.",
"Reorder point = average daily demand × (lead time days + review days) + safety stock.",
"Safety stock = service-level z × daily demand standard deviation × square root of lead time days.",
"Demand forecasts use a simple average of available history only. Seasonality is not modeled unless present in that history.",
"Lead times, demand, and purchase prices are never invented. No purchase order is created and no inventory system is accessed."
],
"priceInvented": false,
"demandInvented": false,
"leadTimeInvented": false,
"purchaseOrderCreated": false,
"inventorySystemAccessed": false
}
}No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"