This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend
What I Built
I built Finance AI, a simple AI-powered personal finance recommender for a close one of mine.
The idea was pretty simple: give the app your monthly income, add your regular expenses, and it calculates how much money you have left at the end of the month.
Instead of just showing that leftover amount, Finance AI uses AI to suggest a few ways you could consider using it — such as emergency savings, Fixed Deposits, Recurring Deposits, or Mutual Funds.
Each recommendation also includes a simple explanation of what it is, how it works, potential returns, risks, and things to know.
The goal was to make personal finance feel a little less intimidating and a lot easier to understand.
Demo
Live Demo: https://finance-recommendor.vercel.app/
Code
GitHub: https://github.com/Adhithyan2004/Finance-AI
How I Built It
The project is built with Next.js, TypeScript, Tailwind CSS, and Groq.
I used the open-weight GPT-OSS 120B model through Groq to generate the financial recommendations.
The flow is intentionally simple:
Income → Expenses → Remaining Balance → AI Recommendations → Financial Education
The frontend collects the user's income and expenses and sends them to a Next.js API route. The API calculates the remaining balance and sends the relevant financial information to Groq. The model then returns structured JSON containing three recommendations along with educational details for each one.
I also made sure the API key stays server-side instead of exposing it in the frontend.
Why Does Open Innovation Matter?
Open innovation makes it possible to build useful AI experiences without needing to create everything from scratch or rely entirely on expensive closed systems.
For this project, using an open-weight model gave me the flexibility to experiment with the prompt, response structure, and the overall AI experience while keeping the project small and hackathon-friendly.
More importantly, it let me focus on what the AI could actually do for a real person, rather than spending the entire weekend building infrastructure around it.
This project started as a simple idea for a close one of mine, and turned into a small experiment in making personal finance easier to understand with AI. 💚
Top comments (0)