Copyright © 2025 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{176518,
        author = {Shashank S N and Abhin K M and Srihari A S and Shadakshari D and Dr. Joseph Michael Jerard V},
        title = {AgriBot: A Generative AI-Powered Multilingual System for Sustainable Fertilizer Recommendations},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {7076-7083},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176518},
        abstract = {With the increasing need for sustainable farming practices and improved crop productivity, intelligent systems that guide fertilizer usage have become critical. This paper introduces a Generative AI-powered system, AgriBot, designed to recommend fertilizers based on real-time soil and weather data inputs. The model is developed to be multilingual, enabling accessibility for farmers across linguistic regions, and supports natural human-like interaction via an integrated chatbot interface.
Core Methodologies: The system utilizes a GPT-based Generative AI model to provide fertilizer recommendations based on user inputs such as soil type, pH value, nitrogen (N), phosphorus (P), potassium (K) content, temperature, rainfall, and crop type. Prompt engineering is used to structure the input context for precise and sustainable suggestions. Multilingual translation is built into the interaction flow, supporting Indian regional languages such as Hindi, Tamil, Telugu, Kannada, and more. The user interface is web-based, featuring a form-driven input and chat-based follow-up for continued guidance.
Performance Insights: The system shows promising results in generating crop-specific, soil-aware, and environmentally sustainable fertilizer suggestions. User feedback highlights the ease of interaction and clarity of multilingual responses. Though real-world deployment and scalability are ongoing challenges, the system demonstrates high relevance and usability for farmers, especially in rural or low-resource regions. Areas of improvement include refining domain-specific language generation and expanding language support to dialects for localized precision.
This paper discusses the integration of Generative AI in agricultural advisory systems, analyzing the benefits of language flexibility, sustainability focus, and real-time interactivity. It serves as a valuable reference for agri-tech developers, policy bodies, and researchers aiming to improve precision farming outcomes using AI technologies.},
        keywords = {Generative AI, Sustainable Farming, Fertilizer Recommendation, Multilingual System, Precision Agriculture, Chatbot, GPT, AgriBot.},
        month = {April},
        }