Use-Case: Competitive Price Intelligence with Amazon Nova Act

nova-act/README.md

@@ -12,6 +12,7 @@ Nova Act enables developers to build intelligent agents that can interact with w
 - **Integrate seamlessly** with Python code for testing, assertions, and debugging
 
 The SDK works in conjunction with **Amazon Bedrock AgentCore Browser**, a secure, cloud-based browser environment that provides:
+
 - Session isolation and security
 - Built-in observability (live viewing, CloudTrail logging, session replay)
 - Containerized ephemeral environments
@@ -38,12 +39,14 @@ Automate quality assurance testing for web applications using Nova Act and Agent
 - **Integration with pytest** for comprehensive test reporting and CI/CD pipelines
 
 **Key Benefits:**
+
 - Reduce test maintenance overhead by 40-60%
 - Execute comprehensive test suites in minutes instead of hours
 - Eliminate false negatives from UI changes
 - Scale testing across browsers, devices, and environments effortlessly
 
 **What's Included:**
+
 - Sample retail web application for testing
 - 15 ready-to-use JSON test cases
 - Pytest framework with parallel execution support
@@ -52,15 +55,44 @@ Automate quality assurance testing for web applications using Nova Act and Agent
 
 [→ Explore the QA Testing Use Case](./usecases/qa-testing/)
 
+### 💰 [Price Comparison](./usecases/price_comparison/)
+
+Automate product price comparison across multiple retailers using Nova Act. This use case showcases:
+
+- **Intelligent product search** that navigates retail websites and finds matching products
+- **Concurrent execution** across multiple retailers for faster price discovery
+- **Structured data extraction** using Pydantic schemas for reliable pricing information
+- **Captcha handling** with user prompts for manual intervention when needed
+- **CSV export** for easy analysis and comparison of results
+
+**Key Benefits:**
+
+- Compare prices across Amazon, Best Buy, Costco, Target, and more in minutes
+- Reduce manual price checking effort by automating browser navigation
+- Get structured output with product names, prices, and promotion details
+- Easily customize product searches and retailer sources via CLI arguments
+
+**What's Included:**
+
+- Ready-to-run price comparison script
+- Support for custom product SKUs and retailer sources
+- Pydantic-based data validation for extracted pricing
+- ThreadPoolExecutor for parallel retailer searches
+- Complete setup and usage instructions
+
+[→ Explore the Price Comparison Use Case](./usecases/price_comparison/)
+
 ## Why Agentic Workflows?
 
 Traditional automation approaches face significant challenges:
+
 - **High maintenance overhead**: Scripts break with UI changes, requiring constant updates
 - **Limited scalability**: Manual testing is time-intensive and incomplete
 - **Technical barriers**: Creating automation requires specialized programming knowledge
 - **Brittleness**: Automation relies on specific selectors that fail when components change
 
 Agentic AI with Nova Act addresses these challenges by:
+
 - **Adapting dynamically** to interface changes without manual updates
 - **Mimicking human interaction** patterns for realistic testing
 - **Enabling non-technical users** to create tests through simple JSON definitions
@@ -81,6 +113,7 @@ This project is licensed under the MIT-0 License. See the [LICENSE](../LICENSE)
 ## Support
 
 For questions, issues, or feature requests:
+
 - Open an issue in this repository
 - Refer to the [official Nova Act documentation](https://github.com/aws/nova-act)
 - Contact AWS Support for enterprise assistance

nova-act/usecases/price_comparison/README.md

@@ -0,0 +1,162 @@
+# Price Comparison using Amazon Nova Act
+
+This project demonstrates automated price comparison across multiple retailers using Amazon Nova Act. It showcases how AI-powered browser agents can intelligently search for products, navigate retail websites, and extract pricing information to help consumers find the best deals.
+
+## Overview
+
+This demonstration implements a concurrent price comparison workflow that searches for products across major retailers (e.g. Amazon, Best Buy, Costco, Target) and compiles results into a sortable comparison table.
+
+### Key Benefits
+
+- **Automated Price Discovery**: AI agents navigate retail sites and extract current pricing
+- **Concurrent Execution**: Parallel searches across multiple retailers reduce total execution time
+- **Structured Output**: Results exported to CSV for easy analysis and comparison
+- **Flexible Configuration**: Customize product searches and retailer sources
+
+## Architecture
+
+The demo consists of two main components:
+
+1. **Nova Act Browser Agents**: Automated browser sessions that navigate retail websites, handle captchas, and extract product information
+2. **Concurrent Execution Engine**: ThreadPoolExecutor manages parallel searches across multiple retailers
+
+## Prerequisites
+
+Before running this demo, ensure you have:
+
+### Development Environment
+
+- **Python 3.11 or higher**
+- **pip** (Python package manager)
+
+### API Access
+
+- **Amazon Nova Act API Key** - Visit [Nova Act home page](https://nova.amazon.com/act) to generate your API key
+
+## Getting Started
+
+Follow these steps to set up and run the price comparison tool:
+
+### Step 1: Install Dependencies
+
+```bash
+# Navigate to the project directory
+cd nova-act/usecases/price_comparison
+
+# Create and activate virtual environment
+python -m venv venv
+source venv/bin/activate  # On Windows: venv\Scripts\activate
+
+# Install dependencies
+pip install -r requirements.txt
+```
+
+### Step 2: Configure API Key
+
+Set your Nova Act API key as an environment variable:
+
+```bash
+export NOVA_ACT_API_KEY="your-api-key-here"
+```
+
+### Step 3: Run Price Comparison
+
+```bash
+# Run with default product (iPad Pro 13-inch M4, 256GB Wi-Fi)
+python main.py
+
+# Run with custom product
+python main.py --product_name "iPhone 15 Pro Max 256GB" --product_sku "MU793LL/A"
+
+# Run with custom sources
+python main.py --sources '[("Walmart", "https://www.walmart.com"), ("Amazon", "https://www.amazon.com")]'
+
+# Run in non-headless mode (visible browser)
+python main.py --headless=False
+```
+
+## Usage Examples
+
+### Default Search
+
+```bash
+python main.py
+```
+
+Searches for "iPad Pro 13-inch (M4 chip), 256GB Wi-Fi" (SKU: MVX23LL/A) across Amazon, Best Buy, Costco, and Target.
+
+### Custom Product Search
+
+```bash
+python main.py --product_name "MacBook Air 13-inch M3" --product_sku "MRXN3LL/A"
+```
+
+### Custom Retailer Sources
+
+```bash
+python main.py --sources '[("Walmart", "https://www.walmart.com"), ("Newegg", "https://www.newegg.com")]'
+```
+
+### Debug Mode (Visible Browser)
+
+```bash
+python main.py --headless=False
+```
+
+## Output
+
+Results are saved to `price_comparison_results.csv` with the following columns:
+
+| Column            | Description                              |
+| ----------------- | ---------------------------------------- |
+| Source            | Retailer name (Amazon, Best Buy, etc.)   |
+| Product Name      | Matched product name from retailer       |
+| Product SKU       | Search SKU used                          |
+| Price             | Current price (sorted lowest to highest) |
+| Promotion Details | Any active promotions or discounts       |
+
+## Project Structure
+
+```
+price_comparison/
+├── README.md           # This file
+├── main.py             # Main application script
+└── requirements.txt    # Python dependencies
+```
+
+## How It Works
+
+1. **Initialization**: Creates Nova Act browser sessions for each retailer
+2. **Captcha Handling**: Detects captchas and prompts user to solve if needed
+3. **Product Search**: Searches using the product SKU on each retailer site
+4. **Result Extraction**: AI agent identifies the most relevant product and extracts pricing
+5. **Data Compilation**: Results are aggregated, sorted by price, and exported to CSV
+
+## Troubleshooting
+
+### Common Issues
+
+1. **Captcha Detected**
+
+   - The tool will pause and prompt you to solve the captcha manually
+   - Press Enter after solving to continue
+
+2. **Product Not Found**
+
+   - Verify the SKU is valid for the target retailers
+   - Some products may not be available at all retailers
+
+3. **Browser Session Errors**
+
+   - Ensure you have a stable internet connection
+   - Try running in non-headless mode to debug: `--headless=False`
+
+4. **API Key Issues**
+   ```bash
+   export NOVA_ACT_API_KEY="your-api-key-here"
+   ```
+
+## Additional Resources
+
+- [Amazon Nova Act](https://nova.amazon.com/act)
+- [Nova Act Documentation](https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html)