# Project export: Legal AI

This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small.

## Project metadata

- Hackathon: Cal Hacks 11.0
- Tagline: Simplify legal jargon and understand it in your native language.
- Devpost: https://devpost.com/software/legal-ai-t70a2p
- GitHub: not linked
- Demo: https://calhacks-legal-ai.vercel.app/
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

We just thought about our own situation because it is always difficult to understand legal texts, then imagine when English is not even your first language. On top of that, having a conversation would help for user experience, sort of a consultation.

### What it does

Focusing on immigrants in the US for whom English is not their native language, they could ask questions in their native language to understand how leasing agreements work in San Diego (for ex.) through a conversation with Legal AI. On top of that, Legal AI could recommend based on the topic of the conversation, different lawyers that are specialised in this topic and who are located in the area of the user.

### How we built it

We built this project using Next.js for the frontend and flask and chroma for the backend. Gemini API was used for transcription and analysis while Cartesia API was used as a text-to-speech model. The project was deployed on Vercel.

### Challenges we ran into

Coding because the documentation from the sponsors had some errors... :// Business model because right now we are just guessing based on what would make sense but actually we should talk to the different customer segments to receive feedback and decide upon the business model.

### Accomplishments we're proud of

Mainly solving the errors in the documentation because this took a lot of time.

### What we learned

We learned more about the API's of Gemini and Cartesia, most specifically how Cartesia AI does multilingual text-to-speech. Furthermore, this involved integrating AI and text models in a way we we haven't before, all before hosting with a service most of us have no familiarity with.

### What's next

Talk to the different customer segments and get feedback!

## README (from the GitHub repository)

No README available.

## Detected evidence (automated analysis)

No repository was indexed for this project. Claimed technologies below could not be checked against code.
- CSS (language) — claimed on Devpost, not found in the code
- Flask (technology) — claimed on Devpost, not found in the code
- Google Gemini (technology) — claimed on Devpost, not found in the code
- JavaScript (language) — claimed on Devpost, not found in the code
- Next.js (technology) — claimed on Devpost, not found in the code
- Python (language) — claimed on Devpost, not found in the code
- React (technology) — claimed on Devpost, not found in the code
- TypeScript (language) — claimed on Devpost, not found in the code

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.