ClassAI | Devpost

Inspiration

Covid-19 is negatively impacting millions, especially students who are forced to learn online. Online lectures aren’t as engaging in person, and pre-recordings are long and tedious to go through to find the relevant material you need to study.

We wanted to improve online lectures in a way so that they are easy to follow and keep track of key points of the lecture. We also wanted a way for students to easily review lectures without spending hours looking for important details. Our app, Classai, is a platform that uses data and artificial intelligence to process online lectures and pre-lecture recordings for students who are forced to learn online due to the pandemic.

What it does

Classai improves online learning by…

Allowing students to easily review pre recorded lectures by organizing the transcribed content and adding insight. Offering real-time transcription with live closed captioning for online lectures so that they are easy to follow and navigate. Features also include muting/unmuting mic, screen sharing, dominant speaker indicators and enabling/disabling the camera. Proving classes in a logical, easy-to-follow structure

How we built it

Classai’s design was created based on our audience, need-finding, user personas and user-flow. Classai’s tech was made with React, Material-UI and many other technologies. The core of our backend was made with Express and Node. Finally, the main APIs that we used were twilio and symbl.ai. Symbl Api is used to Transcribe video and live video call

UX

User Personas

Hi Fi-prototype

Prototype

Engineering

Challenges we ran into

We faced multiple challenges trying to use twilio and symbl.ai for our project, since it was our first time using those APIs. The largest challenge we faced would be communication, since everything was virtual and everyone on the team had very different time zones.

Accomplishments that we're proud of

We are proud that we managed to polish and finish our app! We finished slightly earlier than the hackathon deadline, so we decided to add extra details with Material-UI icons to make our user interface look more professional and organized.

What we learned

We learned to work remotely from each other since this was an online hackathon. We relied on discord for communication, google docs for brainstorming, Figma for our design and more. The technologies and APIs we used were a fun and good challenge as well.

What's next for ClassAi

If there was more time to work on our project, we would have added a lot more features. This includes adding related content to lectures for students to look over and allowing more media types for transcribing videos. Ultimately, we hope to see the app launch one day, we want to improve the online learning experience for everyone!