BEGINNER TRACK
Inspiration
Many of the online courses we've taken cover too much material, much of which we already know. For social issues, we thought it especially important that people understand the full picture on issues.
What it does
This an online learning app to learn about social issues, with lessons that are short and based only on what the user doesn't know yet. These lessons are dynamically generated by summarizing longer articles from various sources (that can be user-provided) and picking results and summaries that match the user's knowledge.
How we built it
The project was built using Flutter as a front-end, with a Python backend to generate the summaries. The summaries are generated using ChatGPT, as this was far superior to the other summarizing tools we uzed. We also utilized MongoDB Realm to manage the data used in the application (including the users database and summaries).
Challenges we ran into
The main challenge we ran into was in generating the summaries. Language processing is difficult and we knew we had to use an off-the-shelf solution given the time constrains. After trying several alternatives, we settled on ChatGPT as this generated the most accurate summaries and was most easy to feed inputs to.
Accomplishments that we're proud of
We're proud of the amount of progress we were able to make in only 24 hours. The application feels somewhat complete despite the time constraints, and the summaries are accurate enough to be useful.
What we learned
We learned quite a bit about several technologies in the making of this app. MongoDB Realm, for example, was something neither of us was familiar with. It ended being a great tool to quickly build out our schema, and is definitely something we will use in the future.
What's next for
There is still much to do! Mainly, we still need to develop a better user-facing interface for creating and publishing articles and summaries, and we also need to improve the UI on the quiz interface.
Log in or sign up for Devpost to join the conversation.