RoastMyCode

RoastMyCode is an AI tool that reviews your code, gives your code a quality score, roasts it with a sense of humor, and provides a way to improve your code.

Comment

Inspiration

Learning to code can be frustrating, and traditional code review tools are often serious and technical. We wanted to build something that makes code feedback both helpful and entertaining. RoastMyCode was inspired by the idea of turning code review into a fun experience where developers can paste their code and get roasted by AI while still receiving meaningful suggestions for improvement.

What it does

RoastMyCode is an AI-powered tool that analyzes user-submitted code and provides instant feedback. Users paste their code, choose a programming language and roast intensity, and the system evaluates the code, assigns a quality score, generates a humorous roast, explains issues in the code, and suggests improvements.

How we built it

We built the frontend using React to create an interactive interface where users can paste code and select roast settings. The backend was developed using Node.js and Express to handle requests and communicate with the OpenAI API. When a user submits code, the backend sends a structured prompt to the AI model, receives a JSON response containing the roast and analysis, and sends the results back to the frontend to display in a formatted results card.

Challenges we ran into

One of the biggest challenges was ensuring the AI returned responses in a consistent JSON format so the frontend could reliably parse and display the results. We also had to handle cases where the AI response failed to parse and create fallback responses to prevent the application from breaking.

Accomplishments that we're proud of

We're proud of building a full-stack AI application that integrates a React frontend, an Express backend, and the OpenAI API. We also implemented a polished user experience with animated loading screens, rotating messages, and structured results that make the feedback both engaging and easy to read.

What we learned

Through this project we learned how to integrate AI APIs into a full-stack application, structure prompts to produce reliable outputs, and handle asynchronous communication between the frontend and backend. We also gained experience designing user-friendly interfaces for AI-powered tools.

What's next for RoastMyCode

Future improvements could include support for more programming languages, deeper AI analysis of code structure, and features like roasting entire GitHub repositories or generating automated code reviews.

Built With

Share this project:

Updates