> ## Documentation Index
> Fetch the complete documentation index at: https://docs.superline.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Feature Extraction

> Understanding how features are collected and processed for AI agent detection

# Feature Extraction System

The feature extraction system is a core component of Superline Agent Detection that collects and processes data from browser sessions to identify patterns that distinguish between human users and AI agents.

## Feature Extraction Architecture

The library uses a modular extraction system with multiple specialized extractors that each focus on different aspects of user behavior.

## Default Extractors

Superline Agent Detection comes with five built-in extractors:

<AccordionGroup>
  <Accordion title="Browser Metadata Extractor" icon="browser">
    Collects environment data such as:

    * User agent string
    * Screen dimensions and orientation
    * Device pixel ratio
    * Color depth
    * Browser language
    * Time zone information
    * Platform details

    These features help identify unusual or inconsistent browser configurations that may indicate an AI agent.
  </Accordion>

  <Accordion title="Mouse Event Extractor" icon="arrow-pointer">
    Analyzes mouse movements and patterns including:

    * Movement speed and acceleration
    * Direction changes and curvature
    * Hover behavior
    * Movement patterns and distribution
    * Start and stop characteristics

    Human mouse movements typically have natural irregularities and acceleration patterns, while AI agents often exhibit more uniform or simplified movement patterns.
  </Accordion>

  <Accordion title="Keyboard Event Extractor" icon="keyboard">
    Tracks keyboard patterns such as:

    * Typing speed and rhythm
    * Key press duration
    * Inter-key intervals
    * Common vs. uncommon key combinations
    * Correction patterns

    Humans typically have distinctive typing rhythms and error patterns, while AI agents may show unnatural consistency or irregularity.
  </Accordion>

  <Accordion title="Scroll Event Extractor" icon="arrows-up-down">
    Monitors scroll behavior including:

    * Scroll speed and acceleration
    * Scroll depth and direction changes
    * Pause patterns between scrolls
    * Scrollbar vs. wheel vs. touchpad scroll detection

    Human scroll patterns typically align with content consumption patterns, while AI agents may exhibit more mechanical or content-independent scroll behaviors.
  </Accordion>

  <Accordion title="Click Event Extractor" icon="hand-pointer">
    Captures click patterns such as:

    * Click timing and distribution
    * Click precision relative to targets
    * Double-click behavior
    * Click pressure and duration
    * Click location heatmap

    Humans typically click with slight imprecision and variability, while AI agents may show too-perfect precision or unnatural patterns.
  </Accordion>
</AccordionGroup>

## Feature Processing

Raw features collected by extractors undergo several processing steps:

<Steps>
  <Step title="Feature Collection">
    Extractors collect raw data from user interactions and browser environment
  </Step>

  <Step title="Statistical Aggregation">
    Raw events are aggregated into statistical features (e.g., mean, variance, distribution metrics)
  </Step>

  <Step title="Normalization">
    Features are normalized to comparable scales, often using standardization (z-scores) or min-max scaling
  </Step>

  <Step title="Transformation">
    Some features undergo non-linear transformations to improve their predictive power
  </Step>

  <Step title="Feature Selection">
    Only the most discriminative features are selected for the final model
  </Step>
</Steps>

## Custom Extractors

<Note>
  Documentation for creating custom feature extractors is currently under development.

  However, the library supports extending its capabilities by creating your own extractor classes. These classes should inherit from a base `FeatureExtractor` class (details forthcoming) and implement the required methods for initialization, data collection, and feature computation.

  You can then pass your custom extractor constructors in the `extractorClasses` array within the `AgentDetector.init()` options. Providing this array will replace the default set of extractors.

  ```javascript theme={null}
  // Conceptual example
  import { DEFAULT_EXTRACTORS } from '@superline-ai/agent-detection';
  import MyCustomExtractor from './my-custom-extractor';

  AgentDetector.init({
    // To add to defaults:
    // extractorClasses: [...DEFAULT_EXTRACTORS, MyCustomExtractor],
    
    // To replace defaults:
    extractorClasses: [MyCustomExtractor]
  });
  ```
</Note>

## Features Table

The following table shows some of the key features used by the detection model:

| Feature Category  | Example Features                  | Description                              |
| ----------------- | --------------------------------- | ---------------------------------------- |
| Browser Metadata  | User agent, Screen dimensions     | Identify unusual browser configurations  |
| Mouse Movements   | Movement speed, Curvature         | Analyze natural vs. artificial movements |
| Keyboard Patterns | Typing rhythm, Key press duration | Detect human typing patterns             |
| Scroll Behavior   | Scroll speed, Pause patterns      | Identify content consumption patterns    |
| Click Patterns    | Click precision, Click timing     | Detect natural click behavior            |

## Privacy Considerations

The feature extraction system is designed with privacy in mind:

* No personal information is collected or stored
* Raw data stays local to the browser
* Only aggregated statistical features are used for detection
* No cross-site tracking or fingerprinting for tracking purposes

<Callout type="info">
  All extracted features are used solely for the purpose of distinguishing between human users and AI agents, not for tracking users across sites or sessions.
</Callout>

## Next Steps

<CardGroup cols={2}>
  <Card title="Detection Model" icon="brain" href="/core-concepts/detection-model">
    Learn how extracted features are processed by the detection model
  </Card>

  <Card title="Custom Extractors" icon="puzzle-piece" href="/guides/custom-extractors">
    Learn how to create and use custom extractors
  </Card>
</CardGroup>