Project Info

Winner

Education Hacks

How likely am I to pass?

Devpost

This project did not submit a demo video on Devpost.

Inspiration

Deciding which classes to take can be challenging, with most students relying on word of mouth or platforms like Rate My Professor for guidance. But is there a more effective way for students to prepare, both generally and for specific courses? Enter "How Likely Am I to Pass?" – a tool designed to support both new and current students in excelling in their academic pursuits.

What it does

Our platform provides a comprehensive list of courses and professors for the current quarter. Students can access detailed information about each professor, informed by reviews from fellow students. Following this, you will complete a personalized questionnaire. This questionnaire is designed to help our AI evaluate the potential challenges you might face, based on your current academic habits and situation.

How we built it

We built it by first scraping data from all the sources that we needed to and aggregating it in a database. Then we made it accessible through API routes in our Next.js project. Next, we integrated it with our React frontend and created our Langchain prompts. Finally, we connected all parts of our full stack application and polished the frontend some more.

Challenges we ran into

Scraping problems, Next.js quirks, React and TailwindCSS learning curve, database problems, deployment problems, and AI problems.

Accomplishments we're proud of

There were many challenges that we faced, from setting up the database to changing minor styling bugs. The most good-feeling accomplishment was getting the API and Database server setup and connecting all of those, plus the AI portion, connected.

What we learned

We learned a lot of React, Next.js, and Tailwind. We also learned of ways to improve our web-application along the way.

What's next

Speeds are definitely a concern, but to have more accurate data is vital. We want to add a more personalized and detailed form for students to fill out for better prediction of their results.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • JavaScriptIn code
  • LangChainIn code
  • Next.jsIn code
  • PythonIn code
  • ReactIn code
  • SQLIn code
  • Tailwind CSSIn code
  • TypeScriptIn code

9 of 9 appear in the indexed code.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

58 KB

Source files

37

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars