Venkata Reddy, V. and Sheela, K. (2025) AI Browser Automation Using Gemini API and Web UI. INTERNATIONAL JOURNAL OF ADVANCE RESEARCH IN MULTIDISCIPLINARY, 3 (2). ISSN 2583-9667
SheeBrowser Automation_Gemini API.pdf
Download (489kB)
Abstract
This project, titled "AI Browser Automation Using Gemini API and Web UI," integrates artificial intelligence with browser automation to perform web tasks efficiently. Using the Browser-Use framework, Playwright, and a Gradio Web UI, the AI agent interprets user instructions through the Gemini API, navigating websites, extracting data, and executing actions like searches and transactions. It supports persistent sessions, custom configurations, and high-definition screen recording for monitoring. The system demonstrated over 90% task accuracy, showcasing its potential in data scraping, autonomous browsing, and AI-powered web automation, forming a foundation for future AI-driven automation tools.
| Item Type: | Article |
|---|---|
| Subjects: | Computer Science Engineering > Artificial Intelligence |
| Domains: | Computer Science |
| Depositing User: | Mr Prabakaran Natarajan |
| Date Deposited: | 27 Dec 2025 04:49 |
| Last Modified: | 28 Jan 2026 05:37 |
| URI: | https://ir.vistas.ac.in/id/eprint/11961 |


