Inspiration We were inspired by our own experiences as students struggling to navigate the complex course selection process. We wanted to create a tool that would make it easier for students to find the courses that best fit their interests and academic goals.
What it does Course Compass is a Chromium-based program that uses natural language processing powered by GPT-3.5 to parse data from the UVA SIS and recommend courses to students based on their academic history and interests. The program also provides information on each course, such as the professor, syllabus, and reviews from previous students.
How we built it We used TypeScript and JavaScript to develop Course Compass. We first created a data parser that could extract relevant information from the UVA SIS. We then integrated GPT-3.5 to generate course recommendations based on the extracted data. Finally, we built a user interface that allows students to interact with the program and view their recommended courses.
Challenges we ran into One of the biggest challenges we faced was working with the UVA SIS data, which is complex and difficult to parse. We also had to carefully balance the use of GPT-3.5 to avoid over-reliance on the AI and ensure that the program's recommendations were accurate and useful to students.
Accomplishments that we're proud of We're proud of creating a functional program that can help students make informed decisions about their course selection. We're also proud of our team's collaboration and communication, which allowed us to overcome challenges and deliver a high-quality product in a short amount of time.
What we learned Through this project, we learned how to work with complex data structures, integrate AI into a program, and design a user-friendly interface. We also developed our communication and teamwork skills, which will be useful in future projects.
What's next for Course Compass In the future, we plan to expand the program to include more universities and course catalogs. We also want to incorporate more features, such as personalized course scheduling and real-time updates on course availability. Finally, we hope to continue refining the AI-powered recommendation system to provide even more accurate and helpful course suggestions to students.
Built With
- css
- docker
- git
- html
- javascript
- node.js
- puppeteer
- react
- render
- typescript
Log in or sign up for Devpost to join the conversation.