Inspiration

The big impact that can cause a good result. Even though today it may seem line a LLM is great at any problem it was it inspiring to see the challenge that needed a mix of already established algorithms with modern LLM layer.

What it does

Our solution, Polar, is a helpful forensic auditor that helps you detect fradulent transactions that usually go unnoticed.

How we built it

We created a web app that connects to a backend motor that orchestrates calls between the fronted, db and AI workflow.

Challenges we ran into

The intrinsic nature of LLMs and random behavior, API quota, understanding finances laws, data processing, data optimizing, resources optimzing, understading algorithms and having a clear idea of a fraude.

Accomplishments that we're proud of

Have a working app.

What we learned

Have a good team structure.

What's next for Polar

No limits.

Built With

  • elevenlabs
  • googlegemini
  • n8n
  • nextjs
  • postresql
  • python
  • tigerdata
  • vultr
Share this project:

Updates

Submission history