AI Detections

WebDecoy provides comprehensive detection of AI-related activity on your website, including server-side AI crawlers, client-side browser extensions, LLM referral tracking, and suspicious signals that indicate AI-assisted browsing.

For the crawl-to-referral model and reporting capabilities, see the AI Traffic product overview.

Overview

AI activity falls into six main categories:

Category	Detection Method	Needs a server-side sensor?	Examples
AI Scrapers	User-Agent analysis	Yes	GPTBot, ClaudeBot, CCBot
AI Browser Plugins	DOM/JavaScript analysis	No	Claude extension, ChatGPT sidebar
Vision AI Bots	Form behavior analysis	No	Claude Computer Use, Stagehand, Browser Use
LLM Referrals	Referrer header analysis	No	Visitors clicking links shared by ChatGPT, Perplexity, Claude
AI Tools	Behavioral signals	No	Automated form filling, content extraction
Suspicious Signals	API monitoring	No	Wrapped fetch, modified observers

AI scraper detection requires a server-side sensor

“User-Agent analysis” happens on WebDecoy’s servers, but the user agent only reaches us if something reports it. GPTBot, ClaudeBot, CCBot and PerplexityBot do not execute JavaScript, so a detection script never runs for them and never reports anything.

If your property has only a detection script installed, the AI Scrapers category and the Citation Monitor will be empty regardless of how many AI crawlers visit you. Install the WordPress plugin, Node SDK, or an edge sensor to see them.

See Detection Coverage for the full matrix.

┌─────────────────────────────────────────────────────────────────┐
│                    AI DETECTION LAYERS                          │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│   SERVER-SIDE                    CLIENT-SIDE (Pro)              │
│   ───────────                    ─────────────────              │
│                                                                  │
│   ┌─────────────────┐            ┌─────────────────┐           │
│   │  AI Scrapers    │            │  Browser Plugins │           │
│   │  (User-Agent)   │            │  (DOM Detection) │           │
│   └────────┬────────┘            └────────┬────────┘           │
│            │                              │                     │
│            │                     ┌────────┴────────┐           │
│            │                     │  Vision AI Bots │           │
│            │                     │  (Form Behavior)│           │
│            │                     └────────┬────────┘           │
│            ▼                              ▼                     │
│   ┌─────────────────┐            ┌─────────────────┐           │
│   │  AI Scraper     │            │  AI Plugin +    │           │
│   │  Score (0-100)  │            │  Vision Flags   │           │
│   └────────┬────────┘            └────────┬────────┘           │
│            │                              │                     │
│            └──────────────┬───────────────┘                     │
│                           ▼                                     │
│                  ┌─────────────────┐                           │
│                  │  Detection      │                           │
│                  │  Record         │                           │
│                  └─────────────────┘                           │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

---

AI Scrapers (Server-Side)

AI scrapers are bots that crawl websites to collect content for training AI models. WebDecoy detects these through User-Agent analysis and assigns an AI Scraper Score.

Training Crawlers (High Score)

These crawlers explicitly collect content for AI/ML model training:

Crawler	Company	Score	User-Agent Pattern	Purpose
GPTBot	OpenAI	85	GPTBot/1.0	Training ChatGPT and GPT models
ChatGPT-User	OpenAI	85	ChatGPT-User	ChatGPT plugins and browsing
OAI-SearchBot	OpenAI	80	OAI-SearchBot	SearchGPT content retrieval
ClaudeBot	Anthropic	85	ClaudeBot	Training Claude models
Anthropic	Anthropic	85	anthropic-ai	Anthropic’s general crawler
CCBot	Common Crawl	80	CCBot/2.0	Open dataset for AI training
Google-Extended	Google	80	Google-Extended	Gemini/Bard AI training
PerplexityBot	Perplexity	80	PerplexityBot	Perplexity AI search
Cohere	Cohere	80	cohere-ai	Cohere model training
ByteSpider	ByteDance	75	Bytespider	TikTok/Douyin AI features
Meta-ExternalAgent	Meta	75	Meta-ExternalAgent	Meta AI training
Applebot-Extended	Apple	75	Applebot-Extended	Apple Intelligence training
YouBot	You.com	75	YouBot	You.com AI search
Amazonbot	Amazon	70	Amazonbot	Alexa and Amazon AI
FacebookBot	Meta	70	facebookexternalhit	Facebook AI features
Diffbot	Diffbot	70	Diffbot	Knowledge graph extraction

Search Crawlers (Lower Score)

Traditional search engines that may also feed AI features:

Crawler	Company	Score	User-Agent Pattern	Note
Googlebot	Google	30	Googlebot	Primary search indexing
Bingbot	Microsoft	30	bingbot	Bing search + Copilot
DuckDuckBot	DuckDuckGo	30	DuckDuckBot	Privacy-focused search
Applebot	Apple	30	Applebot	Siri and Spotlight
YandexBot	Yandex	35	YandexBot	Russian search + AI
Baiduspider	Baidu	40	Baiduspider	Chinese search + AI

SEO and Analytics Crawlers

Crawler	Company	Score	User-Agent Pattern
Semrush	Semrush	35	SemrushBot
Ahrefs	Ahrefs	35	AhrefsBot
MJ12bot	Majestic	30	MJ12bot
DotBot	Moz	30	DotBot

HTTP Client Libraries

Detected when used for scraping:

Library	Pattern	Score
Python Requests	python-requests	25
Go HTTP Client	Go-http-client	25
Java HTTP Client	Apache-HttpClient	25
cURL	curl/	20
Wget	Wget/	20
Scrapy	Scrapy	40

AI Scraper Scoring

For detailed information on how AI Scraper scores are calculated and how they differ from attack scoring, see AI Scraper Scoring.

Where crawler activity is reported

Individual crawler hits land in the Detections table like anything else, but the report built for them is AI Crawlers & Agents (AI Crawlers in the sidebar, at /verified-agents). It answers a question a score alone cannot: whether the crawler was who it said it was.

Requests that claimed a known agent are split three ways, at the request level:

Bucket	Meaning
Proven	a Web Bot Auth signature verified, or the address matched the operator’s published ranges with forward-confirmed reverse DNS
Unproven	the claim stands alone, with nothing corroborating it either way
Forged	the claim was made and the proof failed, which is an impersonation attempt

The report’s Overview carries those totals for the whole property, its Agents tab breaks them down per crawler, and its Handshakes tab reports clients whose TLS handshake contradicts the identity they claimed. See Verified Agents for how each proof is produced.

A GPTBot row with a high AI scraper score therefore means two different things depending on which bucket it fell into, and only the report tells you which.

---

AI Browser Plugins (Client-Side)

WebDecoy’s Detection Script detects AI browser extensions installed by visitors. These extensions inject DOM elements, global variables, and content scripts that can be identified.

Primary AI Assistants

High-confidence detection of major AI assistant extensions:

Extension	Detection Flags	Score Impact
Claude Extension	claude_extension	+15 points
ChatGPT Extension	chatgpt_extension	+15 points
GitHub Copilot	copilot_extension	+15 points
Gemini/Bard Extension	gemini_extension	+15 points
Perplexity Extension	perplexity_extension	+15 points

Secondary AI Tools

Other AI-powered browser extensions:

Extension	Detection Flags	Score Impact
Monica AI	monica_extension	+10 points
Jasper AI	jasper_extension	+10 points
WriteSonic	writesonic_extension	+10 points
Merlin AI	merlin_extension	+10 points
Sider AI	sider_extension	+10 points
MaxAI	maxai_extension	+10 points

Detection Methods

WebDecoy uses multiple techniques to detect AI browser plugins:

1. DOM Element Detection

AI extensions inject UI elements with identifiable patterns:

// Claude extension patterns
'[class*="claude"]'
'[data-claude]'
'[data-anthropic]'
'[id*="claude-"]'
'claude-extension'

// ChatGPT extension patterns
'[class*="chatgpt"]'
'[class*="openai"]'
'[data-chatgpt]'
'chatgpt-sidebar'

// Copilot patterns
'[class*="copilot"]'
'[data-copilot]'
'github-copilot'

2. Global Variable Detection

Extensions often expose global objects:

// Claude
window.__claude__
window.__CLAUDE__
window.__anthropic__

// ChatGPT/OpenAI
window.__chatgpt__
window.__openai__
window.chatGPTExtension

// Copilot
window.__copilot__
window.githubCopilot

// Generic AI
window.__aiAssistant__
window.__AI_EXTENSION__

3. Shadow DOM Detection

Modern extensions use Shadow DOM for isolation. WebDecoy inspects:

• Custom element tag names (<claude-assistant>, <chatgpt-sidebar>)
• Shadow root content for AI-related patterns
• Nested shadow DOM structures

4. Custom Element Registry

Extensions register custom HTML elements:

// Checked custom elements
'claude-assistant'
'claude-sidebar'
'claude-popup'
'chatgpt-assistant'
'chatgpt-sidebar'
'gpt-popup'
'copilot-assistant'
'copilot-suggestion'
'perplexity-assistant'
'gemini-assistant'
'monica-assistant'
'merlin-assistant'
'sider-assistant'

---

Vision AI Detection (Pro)

Vision AI bots represent a new category of AI-assisted browsing where AI agents directly control browser interactions. Unlike traditional browser extensions that assist users, Vision AI bots operate the browser autonomously by manipulating the DOM directly.

Detection Script Pro Required

Vision AI detection requires Detection Script Pro. The behavioral analysis features that detect DOM manipulation patterns are only available in the Pro detection script.

What are Vision AI Bots?

Vision AI bots are AI systems that:

• See the page visually using screenshots or DOM snapshots
• Interact programmatically by setting form values directly via JavaScript
• Skip human input patterns by not generating keyboard/mouse events
• Operate autonomously to fill forms, click buttons, and navigate sites

┌─────────────────────────────────────────────────────────────────┐
│                 VISION AI BOT INTERACTION                        │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│   Human User                      Vision AI Bot                  │
│   ──────────                      ──────────────                 │
│                                                                  │
│   Keyboard → keydown event        DOM Manipulation               │
│            → keyup event          element.value = "text"         │
│            → input event          ↓                              │
│            → value changes        input event only               │
│                                   (no keyboard events!)          │
│                                                                  │
│   ┌─────────────────────────────────────────────────────────┐   │
│   │  Detection: Field has content but ZERO keyboard events  │   │
│   │  Confidence: 90%  |  Score Impact: +40 points           │   │
│   └─────────────────────────────────────────────────────────┘   │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

Known Vision AI Bots

Bot/Tool	Type	Detection Method
Claude Computer Use	AI Agent	DOM manipulation, no keyboard events
Stagehand	Browser Automation	DOM manipulation, synthetic events
Browserbase Agents	Cloud Browser	DOM manipulation, headless signals
Playwright AI	Testing Framework	DOM manipulation, automation flags
Browser Use	AI Agent Framework	DOM manipulation, programmatic clicks

How Detection Works

WebDecoy uses two complementary techniques to detect Vision AI bots:

1. Ghost Click Detection - Clicks at positions where the mouse was never near
2. FormAnalyzer - Form fields with content but no keyboard events

---

Ghost Click Detection

Real users must move their mouse to a position before clicking there. Vision AI bots using element.click() or browser automation APIs can click anywhere without prior mouse movement.

┌─────────────────────────────────────────────────────────────────┐
│                    GHOST CLICK DETECTION                         │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│   Human User                      Vision AI Bot                  │
│   ──────────                      ──────────────                 │
│                                                                  │
│   1. Move mouse to button         1. Find element via DOM       │
│   2. Hover over button            2. Call element.click()       │
│   3. Click button                 3. No mouse movement at all!  │
│                                                                  │
│   Mouse path recorded:            Mouse path recorded:           │
│   ▸ (100,50) → (150,80) → click   ▸ click at (150,80)           │
│                                     (no prior movements!)        │
│                                                                  │
│   ┌─────────────────────────────────────────────────────────┐   │
│   │  Detection: Click with NO mouse activity within 100px   │   │
│   │  Confidence: 95%  |  Score Impact: +45 points            │   │
│   └─────────────────────────────────────────────────────────┘   │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

Key features:

• Tracks mouse position history with timestamps
• Checks if mouse was within 100px of click position in the 2 seconds before click
• Immediate detection: Sends alert instantly when 2+ ghost clicks detected (doesn’t wait for behavioral phase)
• Works even if page navigates away immediately after click

---

FormAnalyzer (DOM Manipulation Detection)

WebDecoy’s FormAnalyzer tracks keyboard events per form field and compares them against actual content:

1. Event Tracking

// FormAnalyzer tracks per-field keyboard activity
{
  "email_field": {
    keydownCount: 0,      // No keydown events
    keyupCount: 0,        // No keyup events
    inputCount: 1,        // One input event (from DOM manipulation)
    pasteCount: 0,        // No paste events
    contentLength: 25     // But field has 25 characters!
  }
}

2. Pattern Detection

Pattern	Detection	Confidence	Score
Content without keyboard	Field has content but zero keydown/keyup events	90%	+40
High DOM manipulation ratio	More input events than keyboard events	75%	+25
Abnormal keydown/keyup ratio	Ratio outside 0.5-2.0 range	60%	+15
Multiple DOM manipulations	3+ fields with suspicious patterns	n/a	+20

3. Typing Rhythm Analysis

Real humans have variable typing rhythms. Bots often have:

• Zero variance in keystroke timing
• Superhuman speed (< 30ms between keystrokes)
• Perfect consistency across all fields

Detection Flags

When Vision AI activity is detected, these flags are added:

Flag	Meaning	Score Impact	Confidence
ghost_clicks	Clicks at positions with no prior mouse activity	+45	95%
form_dom_manipulation	Field content set via DOM, not keyboard	+40	90%
high_dom_manipulation_ratio	Mixed DOM/keyboard with suspicious ratio	+25	75%
instant_clicks	Clicks with no delay after mouse stops	+30	85%
clicks_no_pre_movement	Clicks without preceding mouse movement	+20	80%
multiple_dom_manipulations	3+ fields showing DOM manipulation	+20	n/a
abnormal_key_ratio	Keydown/keyup ratio outside normal range	+15	60%

Strongest Signal

ghost_clicks is the strongest Vision AI indicator. It fires immediately when detected (doesn’t wait for the 5-second behavioral phase), making it effective even when bots navigate away quickly after clicking.

Example Detection Record

{
  "id": "det_xyz789",
  "source": "bot_scanner",
  "unified_score": 85,
  "threat_level": "HIGH",

  "flags": [
    "ghost_clicks",
    "form_dom_manipulation",
    "multiple_dom_manipulations"
  ],

  "metadata": {
    "behavior": {
      "clickAnalysis": {
        "ghostClicks": true,
        "ghostClickRatio": 0.67,
        "instantClicks": false,
        "noPreMovement": true
      },
      "formAnalysis": {
        "suspiciousFields": [
          {
            "id": "email",
            "reason": "content_without_keyboard",
            "contentLength": 24,
            "confidence": 0.9
          },
          {
            "id": "message",
            "reason": "content_without_keyboard",
            "contentLength": 156,
            "confidence": 0.9
          }
        ],
        "totalDomManipulations": 2,
        "fields": {
          "email": {
            "contentLength": 24,
            "keyCount": 0,
            "noKeyboardEvents": true
          },
          "message": {
            "contentLength": 156,
            "keyCount": 0,
            "noKeyboardEvents": true
          }
        }
      }
    }
  }
}

Distinguishing from Legitimate Use Cases

Not all DOM manipulation is malicious. WebDecoy accounts for:

Scenario	How We Handle It
Password managers	Usually trigger paste events (tracked separately)
Autofill	Browser autofill fires input events with isTrusted: true
Copy/paste	Paste events are tracked and not flagged
Form pre-population	Only analyzed after user interaction begins

Use Cases

Detect Browser Automation (Ghost Clicks)

Alert Rule: Ghost Click Detection
Trigger:
  - flags contains 'ghost_clicks'
Action: Block immediately
Rationale: Strongest indicator of browser extension or automation

Protect High-Value Forms

Alert Rule: Vision AI on Signup
Trigger:
  - path matches '/signup' OR '/register'
  - formAnalysis.suspiciousFields.length > 0
Action: Require additional verification
Rationale: Prevent AI-automated account creation

Detect AI-Powered Scraping

Alert Rule: AI Form Probing
Trigger:
  - formAnalysis.totalDomManipulations >= 2
  - session duration < 10 seconds
Action: Block and log
Rationale: AI bot rapidly filling forms to test responses

Monitor for AI Agents

Dashboard Query: Vision AI Activity
Filter:
  - flags contains 'ghost_clicks' OR 'form_dom_manipulation'
Group by: path
Metric: Count per page

Filtering Vision AI Detections

In the Detections table, use these filters:

Filter	Value	What It Shows
Flags contain	ghost_clicks	All ghost click detections
Flags contain	form_dom_manipulation	All DOM manipulation detections
Unified Score ≥	70	High-confidence Vision AI activity
Source	bot_scanner	All client-side detections

API Example:

# Get all Vision AI detections
curl -H "Authorization: Bearer $TOKEN" \
  "https://api.webdecoy.com/v1/detections?flags_contain=ghost_clicks"

# Get all form manipulation detections
curl -H "Authorization: Bearer $TOKEN" \
  "https://api.webdecoy.com/v1/detections?flags_contain=form_dom_manipulation"

---

Suspicious Signals

These signals indicate potential AI-assisted or automated browsing but aren’t specific to a single extension:

API Wrapping

Signal	Flag	Score Impact	Meaning
Wrapped Fetch API	wrapped_fetch	+5 points	window.fetch has been modified
Wrapped XHR	wrapped_xhr	+5 points	XMLHttpRequest.open has been modified
Modified MutationObserver	modified_mutation_observer	+5 points	Observer constructor has been patched

API wrapping can indicate:

• AI extensions intercepting network requests
• Content extraction tools
• Automated form submission tools
• Browser automation frameworks

Detection Logic

// Check if fetch has been wrapped
var fetchStr = window.fetch.toString();
if (fetchStr.indexOf('[native code]') === -1) {
  // Fetch has been wrapped by an extension
  flags.push('wrapped_fetch');
}

// Check if XHR has been wrapped
var xhrStr = XMLHttpRequest.prototype.open.toString();
if (xhrStr.indexOf('[native code]') === -1) {
  // XHR has been wrapped
  flags.push('wrapped_xhr');
}

Context Menu Modifications

Signal	Flag	Meaning
AI Context Menu	ai_context_menu	Extension added AI options to right-click menu

---

Understanding Detection Flags

When AI activity is detected, flags are added to the detection record:

Flag Categories

┌─────────────────────────────────────────────────────────────────┐
│                    DETECTION FLAGS BREAKDOWN                     │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│   Primary AI Extensions (15 pts each)                           │
│   ────────────────────────────────────                          │
│   claude_extension, chatgpt_extension, copilot_extension,       │
│   gemini_extension, perplexity_extension                        │
│                                                                  │
│   Secondary AI Extensions (10 pts each)                         │
│   ─────────────────────────────────────                         │
│   monica_extension, jasper_extension, writesonic_extension,     │
│   merlin_extension, sider_extension, maxai_extension            │
│                                                                  │
│   Suspicious Signals (5 pts each)                               │
│   ───────────────────────────────                               │
│   wrapped_fetch, wrapped_xhr, modified_mutation_observer        │
│                                                                  │
│   Other Signals (8 pts each)                                    │
│   ─────────────────────────                                     │
│   generic_ai_extension, ai_context_menu                         │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

Example Detection Record

{
  "id": "det_abc123",
  "source": "bot_scanner",
  "ip_address": "192.168.1.100",

  "unified_score": 45,
  "threat_level": "MEDIUM",

  "ai_scraper_score": 0,
  "ai_scraper_category": "none",

  "flags": [
    "claude_extension",
    "wrapped_fetch"
  ],

  "metadata": {
    "aiBrowserPlugins": {
      "detected": true,
      "plugins": ["claude_extension"],
      "count": 1
    }
  }
}

---

Filtering AI Detections

In the Detections table, filter specifically for AI-related activity:

Filter Options

Filter	How to Use	Effect
AI Scraper Score	Set minimum score	Show only AI crawler activity
Flags contain	Search for flag name	Show detections with specific AI flags
Source = bot_scanner	Select source filter	Show client-side detections
Impersonation only	?agent_impersonation=true on the detections URL	Show only requests that claimed a known agent and failed the proof
One agent	?ai_scraper_name=GPTBot on the detections URL	Show every request that claimed that identity, proven or not

The forged counts in the agent trust report are links that set exactly these two parameters, so clicking a number lands you on the requests behind it rather than on a filter you have to rebuild.

Example Filters

Find all Claude extension users:

Flags contain: claude_extension

Find all AI training crawlers:

AI Scraper Score >= 70
AI Scraper Category = training_crawler

Find all AI browser plugin activity:

Flags contain: _extension
Source = bot_scanner

Find suspicious API wrapping:

Flags contain: wrapped_

---

Score Impact

AI browser plugin detection contributes to the overall bot score:

Scoring Breakdown

Detection	Points Added	Rationale
Single primary AI extension	+15	Strong indicator of AI-assisted browsing
Multiple primary AI extensions	+15 each	Compounding evidence
Secondary AI extension	+10	Common AI productivity tools
API wrapping	+5	Could be legitimate extensions too
Generic AI signals	+8	Unspecified AI activity

Score Examples

Scenario	Flags	Added Score
Claude extension only	claude_extension	+15
ChatGPT + wrapped fetch	chatgpt_extension, wrapped_fetch	+20
Multiple AI tools	claude_extension, monica_extension, copilot_extension	+40
Wrapped APIs only	wrapped_fetch, wrapped_xhr	+10

Score Ceiling

The total bot score is capped at 100. AI plugin detection contributes to this overall score alongside other bot detection signals (webdriver, headless, behavioral analysis, etc.).

---

Use Cases

Content Protection

Detect when AI tools might be used to extract or summarize your content:

Alert Rule: AI Content Extraction
Trigger:
  - flags contains 'claude_extension' OR 'chatgpt_extension'
  - path matches '/premium/*'
Action: Log and alert
Rationale: User may be using AI to summarize premium content

Form Protection

Identify AI-assisted form filling:

Alert Rule: AI Form Assistance
Trigger:
  - source = 'bot_scanner'
  - flags contains any '_extension'
  - path matches '/signup' OR '/checkout'
Action: Add CAPTCHA challenge
Rationale: AI tools may be automating form submissions

Research and Analytics

Track AI adoption among your visitors:

Dashboard Query: AI Tool Adoption
Group by: flags
Filter: flags contains '_extension'
Metric: Unique visitors per AI tool

---

API Access

Access AI detection data via the WebDecoy API:

Detection Response Fields

{
  "flags": ["claude_extension", "wrapped_fetch"],
  "metadata": {
    "aiBrowserPlugins": {
      "detected": true,
      "plugins": ["claude_extension"],
      "count": 1
    }
  },
  "ai_scraper_score": 0,
  "ai_scraper_category": "none",
  "ai_scraper_name": null
}

Filtering API Requests

# Get all detections with AI browser plugins
curl -H "Authorization: Bearer $TOKEN" \
  "https://api.webdecoy.com/v1/detections?flags_contain=_extension"

# Get Claude extension detections
curl -H "Authorization: Bearer $TOKEN" \
  "https://api.webdecoy.com/v1/detections?flags_contain=claude_extension"

# Get all AI scraper activity
curl -H "Authorization: Bearer $TOKEN" \
  "https://api.webdecoy.com/v1/detections?ai_scraper_score_gte=50"

---

Privacy Considerations

AI browser plugin detection is designed to be:

• Non-invasive: Only checks for presence, doesn’t read content
• Privacy-respecting: Doesn’t capture what users type into AI tools
• Transparent: Detection signals are clearly documented

User Privacy

AI browser plugins are legitimate tools used by many visitors. Consider whether blocking or challenging users based on AI extension presence aligns with your site’s purpose and user expectations.

---

LLM Referral Tracking

When a visitor arrives at your site by clicking a link shared by an AI platform (e.g., a ChatGPT conversation, a Perplexity search result, or a Claude response), WebDecoy’s detection script automatically detects this and sends a lightweight referral beacon.

How It Works

The detection script checks document.referrer against a list of known AI platform domains. If a match is found, it fires a beacon independently of bot detection (since these are human visitors, not bots).

Visitor clicks link in ChatGPT → Lands on your site
    │
    ├── document.referrer = "https://chatgpt.com/..."
    │
    ├── Detection script matches against LLM_DOMAINS
    │
    └── Lightweight beacon sent:
        { score: 0, flags: ['llm_referral'], src: 'llm_referral' }

Supported AI Platforms

Platform	Domains Tracked
ChatGPT	chat.openai.com, chatgpt.com
Perplexity	perplexity.ai, www.perplexity.ai
Google Gemini	gemini.google.com
Claude	claude.ai
DeepSeek	deepseek.com, www.deepseek.com, chat.deepseek.com
Microsoft Copilot	copilot.microsoft.com
You.com	you.com, www.you.com
Phind	phind.com, www.phind.com
Kagi	kagi.com, www.kagi.com
Meta AI	meta.ai, www.meta.ai
Grok	grok.com, www.grok.com

Key Characteristics

Aspect	Detail
Score	Always 0 (these are human visitors)
Source	llm_referral
Flag	llm_referral
Fires independently	Does not interfere with bot detection
Once per page load	Guarded to fire only once

Viewing LLM Referral Data

LLM referral detections appear in the AI Referrals dashboard, which shows:

• Top referring AI platforms
• Traffic trends over time
• Top landing pages receiving AI referral traffic
• Referral volume breakdown by platform

Example Detection Record

{
  "source": "llm_referral",
  "unified_score": 0,
  "threat_level": "NONE",
  "flags": ["llm_referral"],
  "metadata": {
    "page_url": "https://example.com/article/best-practices",
    "referrer": "https://chatgpt.com/c/abc123",
    "llm_referrer": "ChatGPT"
  }
}

Not a Threat Signal

LLM referrals have a score of 0 because they represent human visitors arriving from AI platforms. This data is for analytics (understanding how AI platforms drive traffic to your site), not for threat detection.

---

Future Detection Capabilities

WebDecoy continues to expand AI detection as the landscape evolves:

Planned Additions

• New AI Extensions: Detection for emerging AI browser tools
• AI Agent Detection: Identifying AI agents browsing on behalf of users
• Content Summarization Detection: Identifying AI summary extraction patterns

Community Contributions

If you discover new AI extension patterns, please report them to help improve detection coverage.

---

Related Documentation

• AI Scraper Scoring - Detailed AI crawler scoring methodology
• Verified Agents - Proven, unproven and forged agent claims, and the report that splits them
• Detection Script - JavaScript-based bot detection
• Threat Scoring - Overall threat assessment
• Viewing Detections - Working with detection data