AgriSence | Devpost

Inspiration

Agriculture in India faces persistent challenges such as unpredictable weather, crop diseases, lack of timely expert guidance, and fluctuating market prices. Many farmers still rely on intuition or delayed information. AgriSence was inspired by the need to bridge this gap using AI—making advanced, data-driven agricultural intelligence accessible, affordable, and practical for every farmer.

What it does

AgriSence is an AI-powered agriculture intelligence platform that helps farmers make smarter decisions. It provides real-time weather insights, soil and environmental analysis, AI-based crop disease detection using images, and profitability-driven crop recommendations. The platform supports local contexts and aims to improve yield, reduce losses, and increase farmers’ income.

How we built it

We built AgriSence using a full-stack, cloud-native approach. The frontend delivers a clean, mobile-friendly experience, while the backend handles data processing and AI inference. We integrated weather and environmental APIs, trained machine learning models for crop and disease analysis, and deployed the system on scalable cloud infrastructure. AI models process images and data in real time to deliver actionable insights.

Challenges we ran into

One major challenge was handling diverse agricultural conditions across regions, as soil, climate, and crops vary widely. Collecting reliable datasets for disease detection and ensuring accurate predictions with limited labeled data was also difficult. Additionally, designing a system that remains simple and usable for farmers while handling complex AI logic required multiple iterations.

Accomplishments that we're proud of

We successfully built an end-to-end AI-driven agriculture platform that combines multiple data sources into a single, easy-to-use system. The disease detection feature works in real time, and the recommendation engine provides practical, profitability-focused insights. We are especially proud of creating a solution with real-world impact potential for farmers.

What we learned

Through AgriSence, we learned how to design AI systems for real-world constraints, including data quality, scalability, and usability. We gained hands-on experience in integrating machine learning models with production-ready applications, deploying on the cloud, and building user-centric solutions for non-technical users.