Project AIM: AI-Inspired Mastery

Inspiration

Since the theme of this Hackathon is EdTech, I originally thought of some themes like:

• Enhance learning experience, like how I make students have a more fun and exciting learning experience.
• Help teachers by making tools to help them with their work. -Improving access to learning, like something along the lines of Khan Academy's mission: providing free, world-class education to everyone.

At KLS, we strive to embrace project-based and mastery-based learning. This approach helps us, students, foster a deeper understanding of the subject content, and encourages us to apply our knowledge to real-world problems. The current limitation is that the projects in our classes are mostly on a per-subject basis. But, the real word is multi-domain.

What it does

Holistic projects which incorporate different domains can further encourage problem-solving and innovation. To do this, I thought of creating an easy-to-use tool that can suggest personalized multi-domain projects. This program is helpful to both teachers, for creating and assigning innovative projects to their students, and students for deepening their understanding of all subject content, and doing a project which they are passionate about!

How I built it

In the program, the user inputs their grade, and what they are learning in a few subjects. The input then goes to the program (which uses the ChatGPT API), to output a personalized multi-domain project for the user. The user will then be asked if they like the project or not. If they do, then great! If not, the program will run again with the same user input. Everything was done in Python.

Challenges I ran into

One of my main challenges was that the prompt I gave to the ChatGPT API to create the project (with the user input), was not generating the project with all of the input given. I spent a good chunk of time playing around with the wording of the prompt and trying to make it as specific as possible so that this issue would not occur. By continuing this process and looking on the OpenAI website for any info on this, I was able to solve the problem!

Accomplishments that I'm proud of

I am very proud of myself for being able to code something using the ChatGPT API, and incorporating seamless user input into the program to make it very user-friendly!

What I learned

I learned how to use the ChatGPT API and integrate it into projects, and I also learned that with AI prompting, it's good to be as specific as possible so that the AI does exactly what you want.

What's next for Project AIM: AI-Inspired Mastery

For the next steps of Project AIM, I would like to do the following: -Train the AI model by giving it the user's past projects/assignments, which will help create even more personalized projects using the user's strengths and weaknesses. -Incorporate tools for sharing and collaboration so that users can share their personal projects and collaborate with their peers on different projects.

Built With

• chatgpt-api
• python