AgriSense

• 

  Map/Search

• 

  Landing Page

• 

  Recommended Crop

• 

  Beginning Steps

Inspiration

We were inspired by the struggles farmers face in India, where crop failures and financial uncertainty can have devastating consequences, including farmer suicides. We wanted to create something that could help farmers make more informed decisions and reduce some of that uncertainty.

What it does

AgriSense helps farmers and gardeners decide what to grow based on their location and acreage. Using real agricultural data, it recommends suitable crops, explains potential risks, and provides AI-powered growing advice. Users can also compare fertilizer options based on cost, environmental impact, and personal preferences.

How we built it

We built the frontend using Next.js, React, TypeScript, and Tailwind CSS, with a Python backend. We integrated agricultural data from USDA, NASA POWER, and UF/IFAS to calculate crop suitability scores. Anthropic's API helps turn those results into personalized, easy-to-understand advice. We deployed the platform using Vercel and Render.

Challenges we ran into

missing information. We also had to make recommendations realistic for different land sizes. Along the way, we ran into CORS issues, deployment problems, and API limitations that took plenty of debugging to resolve.

Accomplishments that we're proud of

We're proud of building a working platform that goes beyond simply asking AI what to grow. AgriSense combines real agricultural data, acreage-aware crop rankings, interactive maps, fertilizer recommendations, and AI explanations into one easy-to-use website.

We're especially happy with how much the project evolved from our original idea.

What we learned

We learned a lot about integrating APIs, working with agricultural datasets, building recommendation algorithms, and deploying a full-stack application. More importantly, we learned that AI works best when paired with reliable data and that making complex information understandable is just as important as building the technology itself.

What's next for AgriSense

We want to expand beyond Florida to support more regions, eventually including India, which originally inspired our project. We'd also love to add soil-test uploads, real-time weather forecasts, profitability estimates, and multilingual support.

Built With

• anthropic-api
• claude
• javascript
• leaflet.js
• nasa-power
• next.js
• python
• react
• tailwind-css
• typescript
• uf/ifas
• usda
• vercel