Inspiration
Rural and low-income communities lack access to reliable financial and career guidance. We aimed to bridge this gap with AI that works even in low-connectivity environments.
What it does
FinPath AI provides personalized financial planning and career recommendations based on user profile, including income, education, and location, with support for low-bandwidth access.
How we built it
We built the frontend using Streamlit, integrated LLM APIs for intelligent recommendations, and designed fallback offline logic to ensure usability without internet.
Challenges we ran into
- API access and model compatibility issues
- Handling low-bandwidth constraints
- Ensuring simple, actionable outputs
- Managing environment and deployment setup
Accomplishments that we're proud of
- Built a working AI system with real-world impact focus
- Integrated offline fallback (rare in hackathons)
- Created a clean, user-friendly interface
- Designed for inclusivity and accessibility
What we learned
- Importance of robust system design (fallbacks, APIs)
- Real-world users need simplicity, not complexity
- Deployment and environment management are critical
- AI is powerful only when made accessible
What's next for FinPath AI — Inclusive Financial & Career Navigator
- Add regional language support (Hindi, Bengali, etc.)
- Integrate government scheme databases
- Enable SMS/WhatsApp-based access
- Deploy on cloud for real users
- Add skill-gap analysis and job matching
Built With
- claude
- python
- vs
Log in or sign up for Devpost to join the conversation.