Inspiration
Our inspiration to make TutorAI was the fact that all other resources are extremely vague in their help and are complicated to use. We wanted to make a solution that allows students to get aid 24/7 in any country and any language.
What it does
Our app uses AI to tutor and aid students on school related subjects.
How we built it
We used Gemini's API and customized it to our needs. For the front-end we used the QT API and we used multi-threading to improve responsiveness.
Challenges we ran into
One difficult thing was finding a library to use for the GUI as there are so many different options. Initially, we began using QT Design Studio, however we found out that it doesn't support python, so we switched to coding a QT UI manually instead of using a software Another thing that was difficult was learning about the components of UI design such as proportions and wireframing. Once the UI was built, it was difficult to integrate the functionality of the AI model. One difficulty was that the initial AI model did not support instructions, so we had to research about the different versions of Google's Gemini to find one that would work for us.
Accomplishments that we're proud of
Our app successfully works allowing us to quickly get access to a tutor no matter where you are.
What we learned
We learned how to use API keys and how to do multi-threading.
What's next for TutorAI
File recognition: Our team could add file recognition where the user/student can upload a file or their homework and we can code the AI to interpret and provide responses based on the file.
Log in or sign up for Devpost to join the conversation.