Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196698,
        author = {N.Padmavathi and Maheshwaram Niharika and Deepika pabbathi and Gorre Manohar and Govuri charan Raj},
        title = {An AI Agent That Fills Web Forms Based on Human Language Instructions},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {4387-4392},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196698},
        abstract = {Web form interaction is a fundamental yet repetitive activity in modern digital ecosystems, with studies indicating that users spend approximately 18–25% of online session time on form-based tasks. Traditional automation approaches rely on static scripting and predefined element locators, making them fragile in dynamic web environments. This paper presents an intelligent AI-driven system that automates web form filling using natural language instructions. The proposed system integrates Large Language Models (LLMs), semantic DOM analysis, and browser automation to enable adaptive and scalable automation. The system interprets user intent, extracts structured entities, and maps them to corresponding form fields using semantic similarity techniques. DOM parsing enables identification of input elements, while Playwright-based automation ensures real-time execution. Experimental evaluation across 25 real-world web forms shows that the system achieves an average execution time of 7.8 seconds per form, with a field mapping success rate of 92.6%. The system also reduces manual input effort by approximately 85%, demonstrating its efficiency and usability. The proposed approach eliminates dependency on manual scripting and provides a flexible, user-friendly solution for web automation, contributing to advancements in intelligent agent-based systems.},
        keywords = {AI Agent, Web Automation, Natural Language Processing, Large Language Models, Semantic Mapping.},
        month = {April},
        }