LifeMax

Inspiration

Have you ever been so bored and you didn't know what to do? We have all been there endlessly scrolling through our phones, unable to decide what to watch, read, listen to, or cook. That feeling of being stuck inspired us to build LifeMax. We wanted to create a personalised discovery platform that gives people meaningful, tailored suggestions about topics such as music and movies to recipes and activities.

What it does

LifeMax is a personalised discovery platform that helps you figure out what to do, watch, read, listen to, or eat. Users take a short quiz selecting their preferences across music, books, movies, cuisines, dietary requirements, and hobbies. The app then uses the Gemini AI to generate tailored recommendations across all five categories, which users can browse, save to their favourites, and revisit anytime.

How we built it

Frontend: HTML,CSS, JavaScript Backend: Python, SQL,PHP

Challenges we ran into

One of the main challenges we encountered was designing the relational database. Because our app handles multiple types of personalised data such as users, recommendations, and saved favourites. It was difficult to identify the right entities, their attributes, and how they should relate to one another because there's a lot of interconnected data to consider, and figuring out the schema took significant trial and error.

Accomplishments that we're proud of

We are proud to have built a fully working solution within the hackathon timeframe. One of our biggest achievements was successfully integrating the Gemini AI to generate personalised recommendations across multiple categories such as music, books, movies, recipes, and activities.

What we learned

We learned how to integrate an AI API from scratch and use it to generate personalised content.

What's next for LifeMax

We want to improve the UI by adding more visual elements such as photos of the products. We also want to allow the user to access the product easily by providing direct link to the product. We plan to expand our recommendation categories and refine the personalisation algorithm based on user feedback.