Year: 2025
Type: article
Abstract: An AI-Powered Automated Browser Navigation Agent enables users to control web browsers using natural language via text or speech. Developed with Python, it integrates Playwright for automation, LangChain for NLP, and Gradio for a user-friendly interface. The agent leverages OCR and HTML parsing to understand web elements, automating complex tasks like online shopping, document editing, flight booking, and job applications. Designed for accessibility, it enhances web interactions, making browsing seamless and efficient, even for disabled users.
Authors: Harishankar A, SIVA SUBRAMANIAN E -, PREM KUMAR M -, SAKTHI KOUSIK R -
Language: English
Topic: Web Data Mining and Analysis
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4409195110