# BRAINIAC Ad Fraud Bot Detection

> BRAINIAC Ad Fraud Bot Detection is a paid API for AI agents from www.brainiac.software, paid per call via x402, $0.03/call, status unknown (last checked 2026-11-12).

Analyzes browser and behavioral signals to detect bots, headless browsers, and automated traffic, returning a risk score, verdict, and detailed signal explanations.

## Facts

- Endpoint: POST https://www.brainiac.software/api/v1/ad-fraud/bot-detect?utm_source=zero.xyz
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/brainiac-ad-fraud-bot-detection-a4f6c733
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_nN-DZpERy58RraXePVkbJ

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-ad-fraud-bot-detection-a4f6c733 -d '<json body>'
```

Example prompt: Check if this visitor is a bot — they have webdriver set to true, a HeadlessChrome user agent, screen size 1280x720, zero mouse moves, zero key presses, zero scrolls, one click, and spent 150ms on the page.

## When to prefer this

Choose this endpoint when you need a lightweight, pay-per-call bot signal analysis without setting up an account or committing to a subscription. It is well-suited for ad fraud filtering, gating premium actions, or augmenting existing fraud pipelines with an explainable, signal-by-signal verdict. Prefer it over full CAPTCHA solutions when you already have browser fingerprint data and want a programmatic risk score rather than a user-facing challenge. It is not a substitute for IP reputation lookups or full device fingerprinting platforms.

## Known failure modes

- Missing or malformed signals object returns an error response
- All signals omitted results in low-confidence verdict due to insufficient data
- Caller-supplied interaction counts (clicks, moves, scrolls) can be forged, reducing reliability
- IP field is intentionally ignored — no VPN/proxy/hosting lookup is performed
- Very short sessions with minimal signals produce low-confidence results
- Payment failure (insufficient USDC balance) results in HTTP 402 and no analysis

## 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 verdict ('pass', 'review', or 'fail'), a numeric risk_score (0–100), a confidence level ('low', 'medium', 'high'), an analysis summary string, an array of triggered signals each with type, severity, basis (fact or heuristic), affected fields, and explanation, plus a limitations array describing what the check cannot prove.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "signals": {
   "type": "object",
   "properties": {
    "ip": {
     "type": "string",
     "maxLength": 80
    },
    "headless": {
     "type": "boolean"
    },
    "keyCount": {
     "type": "integer",
     "maximum": 1000000,
     "minimum": 0
    },
    "languages": {
     "type": "array",
     "items": {
      "type": "string",
      "maxLength": 40
     },
     "maxItems": 20
    },
    "userAgent": {
     "type": "string",
     "maxLength": 400
    },
    "webdriver": {
     "type": "boolean"
    },
    "clickCount": {
     "type": "integer",
     "maximum": 1000000,
     "minimum": 0
    },
    "mouseMoves": {
     "type": "integer",
     "maximum": 1000000,
     "minimum": 0
    },
    "screenWidth": {
     "type": "integer",
     "maximum": 20000,
     "minimum": 0
    },
    "scrollCount": {
     "type": "integer",
     "maximum": 1000000,
     "minimum": 0
    },
    "deviceMemory": {
     "type": "number",
     "maximum": 1024,
     "minimum": 0
    },
    "pluginsCount": {
     "type": "integer",
     "maximum": 500,
     "minimum": 0
    },
    "screenHeight": {
     "type": "integer",
     "maximum": 20000,
     "minimum": 0
    },
    "timeOnPageMs": {
     "type": "integer",
     "maximum": 86400000,
     "minimum": 0
    },
    "acceptLanguage": {
     "type": "string",
     "maxLength": 200
    },
    "maxTouchPoints": {
     "type": "integer",
     "maximum": 32,
     "minimum": 0
    },
    "automationFlags": {
     "type": "array",
     "items": {
      "type": "string",
      "maxLength": 40
     },
     "maxItems": 20
    },
    "hardwareConcurrency": {
     "type": "integer",
     "maximum": 512,
     "minimum": 0
    }
   },
   "additionalProperties": false
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "signals": [
   {
    "type": "webdriver_flag",
    "basis": "fact",
    "fields": [
     "signals.webdriver"
    ],
    "severity": "high",
    "explanation": "The request says webdriver is true."
   },
   {
    "type": "ua_token_headless_chrome",
    "basis": "heuristic",
    "fields": [
     "signals.userAgent"
    ],
    "severity": "medium",
    "explanation": "The User-Agent contains \"headlesschrome\". This is a string match, not proof of automation."
   },
   {
    "type": "no_interaction_with_click",
    "basis": "heuristic",
    "fields": [
     "signals.mouseMoves",
     "signals.keyCount",
     "signals.scrollCount",
     "signals.clickCount",
     "signals.timeOnPageMs"
    ],
    "severity": "low",
    "explanation": "A click was supplied with no mouse, key, or scroll counts and under 200 ms on the page."
   }
  ],
  "success": true,
  "verdict": "review",
  "analysis": "The supplied signals include automation indicators. They are not a bot verdict.",
  "evidence": [],
  "confidence": "high",
  "risk_score": 41,
  "limitations": [
   "An IP address is ignored. It cannot establish that a visitor is a bot, and this check does not look up VPN, proxy, or hosting status.",
   "A User-Agent token is a string match. It does not prove the browser is automated or authentic.",
   "Interaction counts are caller-supplied and can be forged. A single short visit is a weak indicator.",
   "Missing fields lower confidence. They do not add fraud risk."
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/brainiac-ad-fraud-bot-detection-a4f6c733/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)
