Website Testing Agentic AI

A proof of concept for website testing software using Playwright and OpenAI's LLM. This tool automates testing of video converter websites and provides detailed reports with AI-powered analysis.

Features

• Automated testing of video converter websites
• AI-powered analysis of test results
• Screenshot capture at each testing step
• Detailed HTML reports with visual feedback
• RESTful API endpoints for test execution and results

Prerequisites

• Node.js (v16 or higher)
• npm or yarn
• OpenAI API key

Installation

1. Clone the repository:

git clone https://github.com/tvalentius/WebTestAgenticAI.git
cd WebTestAgenticAI

2. Install dependencies:

npm install

3. Create a .env file in the root directory and add your OpenAI API key:

OPENAI_API_KEY=your_openai_api_key_here

Usage

1. Start the server:

node server.js

2. Run a test:

curl -X POST http://localhost:3001/api/run-test

API Endpoints

POST /api/run-test

Executes a website test and returns both JSON results and generates an HTML report.

Response:

{
  "testName": "YouTube URL Upload Test - video-converter.com",
  "status": "pass/fail",
  "timestamp": "ISO timestamp",
  "steps": ["array of test steps"],
  "failedSteps": ["array of failed steps"],
  "screenshots": ["array of screenshot filenames"],
  "description": "AI-generated analysis",
  "htmlReport": "/test-report.html"
}

GET /test-report.html

View the latest test report in a beautifully formatted HTML page.

Features:

• Test status and timing information
• Step-by-step results with success/failure indicators
• Screenshot gallery
• AI analysis and recommendations
• Responsive design for all devices

GET /screenshots/[filename]

Access individual screenshots captured during the test.

GET /api/test-results

Retrieve the history of all test results.

Project Structure

.
├── server.js           # Main server file with API endpoints
├── playwright.config.js # Playwright configuration
├── screenshots/        # Directory for test screenshots
├── package.json       # Project dependencies
└── .env              # Environment variables

Test Report Features

The HTML test report includes:

1. Test Information

   • Test name and timestamp
   • Website being tested
   • Test duration
   • Overall status

2. Step-by-Step Results

   • Visual indicators for pass/fail steps
   • Detailed error messages
   • Screenshots at each step

3. AI Analysis

   • Comprehensive test analysis
   • Failure root cause analysis
   • Impact assessment

4. Visual Documentation

   • Screenshot gallery
   • Step annotations
   • Error highlights

5. Recommendations

   • Suggested improvements
   • Next steps
   • Best practices

Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.