Meta Hackathon
Developed an Instagram Discovery Tool during a 24-hour hackathon that allows users to search for visually similar images.
<Contents>
<Projects>
<Overview>
During a 24-hour hackathon hosted by Meta, I had the chance to collaborate with a talented team to create an Instagram discovery tool that helps users explore content in a visual and engaging way.
Iggy Discover is an Instagram discovery tool designed for young adult users, allowing them to find visually similar content, profiles, and businesses. The project was developed during a hackathon with Meta, focused on supporting users in adapting to AI innovations. With just 24 hours to brainstorm, code, and present our solution, we created a prototype that delivers visually similar posts and accounts based on the image a user searched for.
<Toolkit>
- React
- JavaScript
- SCSS
- Node.js
- Express
- Figma
<Metadata>
Completed
2024
Timeline
24 hours
Role
Front-end Developer
<Features>
Here are some of the key features of Iggy Discover.
Discover similar content using visual search.
Iggy Discover lets users search for images from their Instagram feed to find similar posts. Whether it's a photo of pasta or a cityscape, the tool uses AI to return related content, helping users explore more of what they enjoy.
'%3e%3crect%20width='712'%20height='24'%20fill='%230C0C34'/%3e%3ccircle%20cx='12'%20cy='12'%20r='4'%20fill='%23AB1C4E'/%3e%3ccircle%20cx='28'%20cy='12'%20r='4'%20fill='%23CC821B'/%3e%3ccircle%20cx='44'%20cy='12'%20r='4'%20fill='%2327A26D'/%3e%3c/g%3e%3crect%20x='0.5'%20y='0.5'%20width='711'%20height='23'%20stroke='%230C0C34'/%3e%3cdefs%3e%3cclipPath%20id='clip0_462_129'%3e%3crect%20width='712'%20height='24'%20fill='white'/%3e%3c/clipPath%3e%3c/defs%3e%3c/svg%3e)
Find shops, restaurants, and brands with similar images in their posts.
Beyond posts, Iggy Discover helps users discover businesses or brands that offer products similar to the images being searched for. In the example below, you can discover restaurants serving up some delicious pasta. It's a great way to find new places, products, or services that match your tastes.
<Retrospective>
Looking back, the 24-hour hackathon was a whirlwind of collaboration and problem-solving. While the time constraints were intense, especially with different time zones to coordinate, we managed to stay focused by dividing tasks clearly and keeping communication open. We chose to hardcode the visual search results instead of attempting an AI-powered solution, as we didn't have the resources to implement it fully in such a short time. This decision allowed us to deliver a working prototype on schedule.
The hackathon taught me valuable lessons in working under pressure, prioritizing features, and collaborating with a diverse team. Although we didn't get to explore AI as much as we'd hoped, it sparked my interest in the potential of AI-driven content discovery. If given more time, I would love to explore implementing AI models for more dynamic results and refine the user experience.