# BRAINIAC Conversion Fraud Detection API

> BRAINIAC Conversion Fraud Detection API 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 click and conversion event pairs to detect ad fraud patterns such as conversions timestamped before clicks, campaign ID mismatches, and other suspicious attribution anomalies.

## Facts

- Endpoint: POST https://www.brainiac.software/api/v1/ad-fraud/conversion-fraud-detect?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-conversion-fraud-detection-api-dbf622ee
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_iPjTFoLbk70ZDJ4LDHMH1

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-conversion-fraud-detection-api-dbf622ee -d '<json body>'
```

Example prompt: Check these 50 click events and 20 conversions from our Google Ads campaign 'summer-sale-2024' for ad fraud — I'm seeing some conversions that might have happened before the clicks, and I want a risk score and verdict on whether to flag them for review.

## When to prefer this

Choose this endpoint when you need a lightweight, pay-per-call fraud check on batches of click and conversion events without setting up an account or long-term contract — ideal for AI agents running periodic ad audits, affiliate payout validation, or one-off campaign integrity checks. It is particularly useful when you have both click and conversion records with timestamps and campaign IDs and want to detect logical inconsistencies like temporal inversions or attribution mismatches. Prefer dedicated fraud platforms with persistent user profiles and device graphs if you need historical cross-session analysis beyond what a single request batch can provide.

## Known failure modes

- Missing required 'id' field on click or conversion objects returns a validation error
- Empty conversions array (minItems:1 not satisfied) causes request rejection
- Timestamps in unrecognized formats may prevent accurate chronological comparison
- Batch sizes exceeding 200 items per array are rejected
- Mismatched or absent clickId fields reduce confidence and may lower signal quality
- Payment failure via x402 returns HTTP 402 and no analysis is performed

## 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 containing: a list of fraud signals (each with type, basis, affected fields, severity, and explanation), an overall verdict (e.g. 'review', 'clean', 'fraud'), a confidence level, a numeric risk score (0–100), a summary analysis string, an evidence array, and a limitations array noting caveats about the analysis scope.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "clicks": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "id"
    ],
    "properties": {
     "x": {
      "type": "number",
      "maximum": 20000,
      "minimum": 0
     },
     "y": {
      "type": "number",
      "maximum": 20000,
      "minimum": 0
     },
     "at": {
      "type": "string",
      "maxLength": 40,
      "minLength": 8
     },
     "id": {
      "type": "string",
      "maxLength": 120,
      "minLength": 1
     },
     "gclid": {
      "type": "string",
      "maxLength": 200
     },
     "fbclid": {
      "type": "string",
      "maxLength": 200
     },
     "clickId": {
      "type": "string",
      "maxLength": 160
     },
     "dwellMs": {
      "type": "integer",
      "maximum": 86400000,
      "minimum": -1000000
     },
     "referrer": {
      "type": "string",
      "maxLength": 500
     },
     "campaignId": {
      "type": "string",
      "maxLength": 80
     },
     "landingUrl": {
      "type": "string",
      "maxLength": 500
     },
     "pageLoadAt": {
      "type": "string",
      "maxLength": 40,
      "minLength": 8
     },
     "fingerprintId": {
      "type": "string",
      "maxLength": 120
     },
     "timeToClickMs": {
      "type": "integer",
      "maximum": 86400000,
      "minimum": -1000000
     }
    },
    "additionalProperties": false
   },
   "maxItems": 200
  },
  "conversions": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "id"
    ],
    "properties": {
     "at": {
      "type": "string",
      "maxLength": 40,
      "minLength": 8
     },
     "id": {
      "type": "string",
      "maxLength": 120,
      "minLength": 1
     },
     "value": {
      "type": "number",
      "maximum": 1000000000,
      "minimum": 0
     },
     "clickId": {
      "type": "string",
      "maxLength": 160
     },
     "campaignId": {
      "type": "string",
      "maxLength": 80
     }
    },
    "additionalProperties": false
   },
   "maxItems": 200,
   "minItems": 1
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "signals": [
   {
    "type": "conversion_before_click",
    "basis": "fact",
    "fields": [
     "conversions[0].at",
     "clicks[0].at"
    ],
    "severity": "high",
    "explanation": "Conversion V1 is timestamped before click C1."
   },
   {
    "type": "campaign_mismatch",
    "basis": "fact",
    "fields": [
     "conversions[0].campaignId",
     "clicks[0].campaignId"
    ],
    "severity": "medium",
    "explanation": "Conversion V1 and its click name different campaigns."
   }
  ],
  "success": true,
  "verdict": "review",
  "analysis": "Some supplied click and conversion records disagree or repeat.",
  "evidence": [],
  "confidence": "high",
  "risk_score": 42,
  "limitations": [
   "Click and conversion records are compared only inside this request.",
   "An unmatched conversion is a missing link in the supplied batch, not proof the click never happened.",
   "A conversion a few seconds after a click can be legitimate. It is a weak timing indicator.",
   "Missing click history lowers confidence and is not treated as fraud."
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/brainiac-conversion-fraud-detection-api-dbf622ee/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)
