# BRAINIAC Manufacturing Quality Root Cause Evidence Analyzer

> BRAINIAC Manufacturing Quality Root Cause Evidence Analyzer 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).

Analyzes manufacturing quality evidence records against batch, inspection, and standard data to surface root cause signals and nonconformance findings.

## Facts

- Endpoint: POST https://www.brainiac.software/api/v1/manufacturing-quality/root-cause-evidence-analyze?utm_source=zero.xyz
- Price: $0.04/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/brainiac-manufacturing-quality-root-cause-evidence-analyzer-eed8cdc8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_rks7VN1jDAqA5wlwAqYkH

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability brainiac-manufacturing-quality-root-cause-evidence-analyzer-eed8cdc8 -d '<json body>'
```

Example prompt: I have inspection records, batch data, and a set of evidence items — including material certs and crack photos — from our production line last week. Can you run a root cause evidence analysis on them and tell me which evidence is linked to failed inspections, what signals stand out, and whether any tolerance thresholds were breached?

## When to prefer this

Use this endpoint when you have structured manufacturing quality data — evidence records, inspection results, batch metadata, and optional standards or thresholds — and need to systematically surface root cause signals and link failure evidence to specific batches and inspections. It is purpose-built for nonconformance triage and quality investigation workflows where transparency about what was and was not asserted is required. Prefer it over generic LLM analysis when you need structured signal outputs, explicit limitation disclosures, and reproducible results at a fixed low cost per call without an account.

## Known failure modes

- Insufficient evidence items or inspections provided — signals will be sparse or empty
- Batch IDs in evidence do not match supplied batch records — linkedBatch will be false for unmatched rows
- Minimum sample count not met — SPC limits will not be computed
- Malformed or oversized CSV/JSON input — request rejected with validation error
- No standards supplied — tolerance analysis will be skipped entirely
- Evidence text exceeds per-item maxLength — truncation or rejection possible

## How this service works

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.

## Output

Returns a JSON object with: a list of evidence items annotated with linkedBatch and linkedInspection flags; an array of signals each with a code, kind, count, and plain-English detail; a findings array for nonconformances; metadata flags (productCertified, standardInvented, toleranceInvented, regulatoryComplianceClaimed); a checkedAt timestamp; and a limitations list explaining what the analysis did and did not assert.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "csv": {
   "type": "string",
   "maxLength": 200000
  },
  "file": {
   "type": "object",
   "required": [
    "mediaType",
    "fileBase64"
   ],
   "properties": {
    "filename": {
     "type": "string",
     "maxLength": 180,
     "minLength": 1
    },
    "mediaType": {
     "enum": [
      "text/plain",
      "text/csv",
      "application/json"
     ],
     "type": "string"
    },
    "fileBase64": {
     "type": "string",
     "maxLength": 12000000,
     "minLength": 1
    }
   },
   "additionalProperties": false
  },
  "json": {
   "type": "string",
   "maxLength": 200000
  },
  "text": {
   "type": "string",
   "maxLength": 200000
  },
  "batches": {
   "type": "array",
   "items": {
    "type": "object",
    "properties": {
     "id": {
      "type": "string",
      "maxLength": 80
     },
     "ended": {
      "type": "string",
      "maxLength": 40
     },
     "product": {
      "type": "string",
      "maxLength": 160
     },
     "started": {
      "type": "string",
      "maxLength": 40
     },
     "produced": {
      "type": "number",
      "maximum": 1000000000,
      "minimum": 0
     }
    },
    "additionalProperties": false
   },
   "maxItems": 80
  },
  "evidence": {
   "type": "array",
   "items": {
    "type": "object",
    "properties": {
     "at": {
      "type": "string",
      "maxLength": 40
     },
     "id": {
      "type": "string",
      "maxLength": 80
     },
     "kind": {
      "type": "string",
      "maxLength": 80
     },
     "text": {
      "type": "string",
      "maxLength": 1000
     },
     "batchId": {
      "type": "string",
      "maxLength": 80
     },
     "inspectionId": {
      "type": "string",
      "maxLength": 80
     }
    },
    "additionalProperties": false
   },
   "maxItems": 200
  },
  "minSample": {
   "type": "integer",
   "maximum": 100000,
   "minimum": 1
  },
  "standards": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "characteristic"
    ],
    "properties": {
     "unit": {
      "type": "string",
      "maxLength": 40
     },
     "lower": {
      "type": "number",
      "maximum": 1000000000,
      "minimum": -1000000000
     },
     "upper": {
      "type": "number",
      "maximum": 1000000000,
      "minimum": -1000000000
     },
     "target": {
      "type": "number",
      "maximum": 1000000000,
      "minimum": -1000000000
     },
     "characteristic": {
      "type": "string",
      "maxLength": 1
… (truncated)
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "items": [
   {
    "at": "2026-11-04T09:00:00.000Z",
    "id": "E-1",
    "kind": "material-cert",
    "text": "heat lot note",
    "batchId": "B-1",
    "linkedBatch": true,
    "inspectionId": "I-1",
    "linkedInspection": true
   },
   {
    "at": "2026-11-04T10:00:00.000Z",
    "id": "E-2",
    "kind": "photo",
    "text": "crack photo",
    "batchId": "B-1",
    "linkedBatch": true,
    "inspectionId": "I-1",
    "linkedInspection": true
   }
  ],
  "status": "analyzed",
  "signals": [
   {
    "code": "evidence_kind",
    "kind": "material-cert",
    "count": 1,
    "detail": "1 evidence row(s) labeled material-cert. This is a count of supplied notes, not a proven root cause."
   },
   {
    "code": "evidence_kind",
    "kind": "photo",
    "count": 1,
    "detail": "1 evidence row(s) labeled photo. This is a count of supplied notes, not a proven root cause."
   },
   {
    "code": "linked_failure_evidence",
    "kind": "link",
    "count": 2,
    "detail": "Inspection I-1 has 2 linked evidence row(s). Association is by id only."
   }
  ],
  "findings": [],
  "checkedAt": "2026-11-04T20:00:00.000Z",
  "limitations": [
   "Inspections, measurements, batches, standards, and evidence are copied only from labeled fields supplied by the caller.",
   "Tolerances and defect-rate thresholds are used only when explicitly supplied. Manufacturing standards are never invented.",
   "Statistical process control limits are computed only when the disclosed minimum observation count is met.",
   "A nonconformance report organizes supplied evidence. It does not certify a product or assert regulatory compliance.",
   "Defect classes use transparent token rules on supplied defect text and codes."
  ],
  "evidenceCount": 2,
  "productCertified": false,
  "standardInvented": false,
  "toleranceInvented": false,
  "linkedFailureCount": 1,
  "regulatoryComplianceClaimed": false
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/brainiac-manufacturing-quality-root-cause-evidence-analyzer-eed8cdc8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from www.brainiac.software](https://www.zero.xyz/host/www.brainiac.software/llms.txt)
