Agentic AI Device Attributes Analysis Demo
A comprehensive demonstration of an Agentic AI system for device behavior analysis and fraud prevention. This package provides an interactive web-based demo that showcases how AI agents can analyze device attributes to detect suspicious behavior and potential fraud.
Features
- Interactive Web Interface: Clean, modern UI for device analysis demonstration
- Real-time Analysis: Simulated AI-powered device attribute analysis
- Multiple Risk Levels: Supports normal, suspicious, and fraudulent device scenarios
- Agentic AI Simulation: Demonstrates multi-agent decision-making processes
- Zero Dependencies: Uses only Python standard library for maximum compatibility
- Easy Deployment: Simple installation and deployment options
Installation
From PyPI (when published)
pip install agentic-ai-device-analysis
From Source
git clone https://github.com/deviceanalysis/agentic-ai-device-analysis.git
cd agentic-ai-device-analysis
pip install -e .
Development Installation
git clone https://github.com/deviceanalysis/agentic-ai-device-analysis.git
cd agentic-ai-device-analysis
pip install -e ".[dev]"
Quick Start
Command Line
After installation, you can start the demo server using:
# Using the main command
agentic-demo
# Alternative command
device-analysis-demo
# With custom host and port
agentic-demo --host 0.0.0.0 --port 8080
Python Module
# Run as module
python -m agentic_ai_demo
# With arguments
python -m agentic_ai_demo --host localhost --port 8000
Direct Script Execution
python agentic_ai_demo/server.py
Usage
- Start the server using any of the methods above
- Open your web browser and navigate to
http://localhost:8000 - Use the interactive interface to analyze different device scenarios:
- Normal Device: Simulates a legitimate user device
- Suspicious Device: Shows elevated risk indicators
- Fraudulent Device: Demonstrates high-risk fraud patterns
API Endpoints
GET /- Main demo interfaceGET /api/analyze?type={normal|suspicious|fraud}- Device analysis APIGET /health- Health check endpoint
Demo Features
Device Analysis Types
-
Normal Device Analysis
- Low risk score (0.1-0.3)
- Standard device fingerprinting
- Typical user behavior patterns
-
Suspicious Device Analysis
- Medium risk score (0.4-0.7)
- Anomalous behavior detection
- Enhanced monitoring recommendations
-
Fraudulent Device Analysis
- High risk score (0.8-0.95)
- Multiple fraud indicators
- Immediate action recommendations
AI Agent Simulation
The demo simulates various AI agents working together:
- Device Fingerprint Agent: Analyzes hardware and software characteristics
- Behavior Analysis Agent: Monitors user interaction patterns
- Risk Assessment Agent: Calculates overall fraud probability
- Decision Engine: Coordinates agent findings and recommendations
Architecture
Metadata
Release files for agentic-ai-device-analysis 1.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentic_ai_device_analysis-1.0.1.tar.gz | 19.7 kB | Without provenance | Details for agentic_ai_device_analysis-1.0.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentic_ai_device_analysis-1.0.1-py3-none-any.whl | Python 3 | none | any | Details for agentic_ai_device_analysis-1.0.1-py3-none-any.whl |
Total release size: 30.6 kB
Release files / agentic_ai_device_analysis-1.0.1.tar.gz
| Download URL | agentic_ai_device_analysis-1.0.1.tar.gz |
|---|---|
| Size | 19.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c5decb2718b97ca5a3d3dbd010a4ca69d0c7bef55f812c329e26ef2dab4938f3
|
|
BLAKE2b-256 checksum How to use checksums |
850bbffc18481dc57bb9b860d5736325f09b460db1c9bf18bd82d04d5b5ff7ac
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.1
|
Release files / agentic_ai_device_analysis-1.0.1-py3-none-any.whl
| Download URL | agentic_ai_device_analysis-1.0.1-py3-none-any.whl |
|---|---|
| Size | 11.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1e708aaa6e0bc7ed492afaa89b2f15208cf7c8d3f9374c54731a9483ccae57fe
|
|
BLAKE2b-256 checksum How to use checksums |
774a3279e511fac10caa7c3f3347632ae3d75dbb67c951dc30ef9c2f8771333a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.1
|
Security for agentic-ai-device-analysis 1.0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.