Inspiration
We were talking about our mutual admiration for Elle Woods, the protagnoist of Legally Blonde: a driven, career-oriented person with immaculate taste in fashion.
What it does
'elle' takes in a video link to a movie or a clip and the name of a character in said video and recognizes their three most iconic looks and breaks them down into separate parts to find shopping links on e-commerce websites.
How we built it
We used Reka's Vision + Research APIs to facilitate visual analysis & web scraping + Claude Compute to expedite our work processes
Challenges we ran into
This was our first major hackathon, so time management posed a massive challenge for us.
Accomplishments that we're proud of
We're glad to have actually built something, however it may function, in this kind of time span with the sort of limitations we faced.
What we learned
We learned to develop in an AI-driven environment effectively, such as understanding the limitations of Claude (such as being unfamiliar with Reka documentation) but also the potential it contains
What's next for elle
We need to flesh out the front-end for elle and make sure the data we generate actually gets to the user in a usable manner, in addition to optimizing Reka usage to minimize time taken and credits used.
Built With
- claude
- next.js
- react
- reka
- typescript

Log in or sign up for Devpost to join the conversation.