Inspiration
- We wanted to make a project that would be helpful in our daily lives.
What it does
- Our project allows you to simply say what you would like to eat, and you will get a recipe showing current prices from Target, as well as savings from choosing store brand over name brand.
How we built it
- We used TypeScript/Next.js/Vercel for most things, Claude via the Anthropic API for the AI parts, and Python for planning/testing/ideating.
Challenges we ran into
- Creating the Target grocery prices dataset.
- Getting Claude to respond in a structured, consistent format.
- Utilizing a technology stack we had little familiarity with.
Accomplishments that we're proud of
- Creating a functional web application in 24 hours.
- Our hand-drawn logo that showcases our passion for human creativity.
What we learned
- How to manage and deploy websites using Vercel and GitHub.
- How to use AI for software development in a responsible and efficient manner.
- How to integrate LLMs into an application via an API.
- How to design an aesthetically pleasing website.
What's next for Food Finder
- Using human-written recipes found via web search.
- Add more nutrition metrics
Built With
- anthropic
- next.js
- python
- typescript
- vercel