TreeLoan

Inspiration

Access to green funding is often complex, slow, and opaque. Many environmentally positive projects fail to secure financing simply because sustainability impact is hard to measure, explain, and compare. We were inspired to bridge the gap between green project builders and green funders by creating a platform that translates sustainability into clear, data-driven insights—instantly.

TreeLoan was built to make green lending smarter, faster, and more transparent using AI.

What it does

TreeLoan is an AI-powered greener lending platform that evaluates project proposals and connects them with suitable green funding opportunities.

Users upload a project proposal PDF and instantly receive:

A green sustainability score (0–100) based on environmental impact
Funding estimates tied to the project’s green score
Actionable improvement suggestions to boost sustainability and funding potential
Recommended green funders, including NGOs, lenders, and investment firms
A comprehensive project analysis report, including categorization and extracted project details

Projects must meet a minimum sustainability score of 20/100 to qualify for funding recommendations.

How we built it

TreeLoan is a full-stack application with an AI-driven core:

Frontend: Next.js 16, React 19, TypeScript, Tailwind CSS
Backend: FastAPI (Python 3.11)
AI/LLM: Groq API with Llama models
Deployment: Docker Compose (local) and Render (production)

The platform extracts key project data from uploaded PDFs, evaluates sustainability factors such as renewable energy usage, carbon reduction, and sustainable materials, and generates scores, insights, and funding recommendations in real time.

Challenges we ran into

Designing a balanced and fair sustainability scoring system
Extracting meaningful data from unstructured PDF proposals
Ensuring LLM consistency and reliability across evaluations
Mapping green scores to realistic funding estimates
Managing containerized services across frontend, backend, and AI integrations

Accomplishments that we're proud of

Built an end-to-end AI-powered green evaluation pipeline
Successfully integrated LLM-based sustainability analysis into a lending use case
Delivered actionable improvement suggestions with visible score impact
Shipped a production-ready, Dockerized full-stack application
Created clean architecture with clear documentation and deployment workflows

What we learned

Sustainability scoring requires both technical accuracy and ethical consideration
AI is most effective when paired with transparent, actionable outputs
Containerization significantly improves development and deployment consistency
Green finance is not just about evaluation—it’s about enabling improvement