Kowalski Central

Inspiration

Kowalski Central aims to empower users to make environmentally sound decisions. We were inspired by Kowalski the penguin and his immense ability to analyse the situation at hand, making the best recommendations. Penguins are also very endangered due to climate change, and we felt that theming our product around Kowalski would be humorous and effective to bring a positive message.

What it does

Kowalski Central aims to be a one-stop shop for the data needed to make environmentally sound decisions. You find yourself at a landing page, where you may enter the url for the product you wish to buy. After some analysis, Kowalski comes up with a recommendation on whether you should or should not buy the product based on its reasons. It then suggests three different possible environmentally friendly alternatives.

It also consists of a carbon calculator in order to have the user accountable for their carbon emissions. We strongly believe that the key is to empower users with the information they need to make an environmentally friendly decision.

How we built it

We built it with a Flask backend, calling using the rainforest API for Amazon related product information, which is then rendered on screen. The analysis is done by an API call to an OpenAI endpoint with specifically tailored prompts. This was connected to a React frontend, which rendered the information obtained. In the future, we aim to train a machine learning model to recognize not only the "goodness" of a particular product, which would give it the capability to make recommendations, but also recommendations through a similarity test.

Challenges we ran into

We had problems with the API, we had problems connecting the backend API to the front end, and rendering it correctly. We had problems with the Flask and React stack we used. We had problems with parsing API data. We had technical issues with our IDEs. There were so many issues over the 36 hour period, they were hard to count. Getting through them was a challenge, but it taught a lot.

Accomplishments that we're proud of

We're proud of having come up with the idea yesterday, and by the end of today having it put together, and functional. Of course there are improvements to make, but we completed the main functionality that we endeavoured to create, the analysis portion of the application.

What we learned

We learned the importance of communication, appropriate allocation of tasks, and to have a plan going into software development. It is very easy to get lost in the vast expanse of code that a project becomes, and having a plan helps order that. It is also very important that the team communicates, because without that, different team members head in different directions, and we end up with a non-cohesive product.

What's next for Kowalski Central

We aim to train a ML model to be able to make not only recommendations, but also to find alternate products, linking them on the analysis page so that the user has ease of access. We also want to use the application as a Chrome Extension, which not only increases the convenience of use, but makes it more flexible and able to be used on various different websites.