Skip to content

Mansi2821/python_code_helper

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 

Repository files navigation

Natural-language prompt for AI assistant

"You are a friendly coding helper. A student will show you some Python code that isn’t working. Look at the code and try to understand what might be wrong. Give small hints or tips to help the student fix it, but don’t give the full answer. Keep your advice easy to understand so the student can try it themselves."

Explanation of design choices

I wrote the prompt in a friendly, easy-to-read way because I wanted it to feel like a real person talking to a student, not a formal or robotic instruction. I used words like “friendly coding helper” and “small hints” to make it approachable. I avoided giving the solution by clearly saying “don’t give the full answer” and “help the student try it themselves.” This way, the AI focuses on guiding the student instead of solving the problem for them. I encouraged helpful, student-friendly feedback by asking for “simple hints or tips” and “easy to understand” advice. This makes sure the AI explains things in a way the student can follow and learn from, instead of just dumping technical details.

Answer to given questions

1.Tone and style: The AI should be friendly and encouraging, like a helpful tutor who’s patient and easy to talk to. It shouldn’t sound bossy or like it’s scolding the student for mistakes. Keep the words simple and supportive.

2.Balancing bugs and guidance: The AI should first point out what might be going wrong in the code, but without giving the full fix. Then it should give hints or ask questions that make the student think and try to fix it themselves. It’s like nudging them in the right direction instead of solving everything for them.

3.Adapting for beginner vs. advanced learners: For beginners, the AI should use very simple explanations, maybe with small examples or analogies, and give more step-by-step hints. For advanced learners, it can be more concise, focus on logic or structure issues, and give subtler hints that push them to think deeper without spelling everything out.

Setup Instructions

1.Clone the repository Open a terminal and run:

git clone https://github.com/Mansi2821/python_code_helper.git

2.Go to the project folder

cd python_code_helper

3.Create a virtual environment (optional but recommended)

python -m venv env

4.Activate it:

Windows: .\env\Scripts\activate

Mac/Linux: source env/bin/activate

5.Install dependencies

pip install -r requirements.txt

6.Run the project

python main.py

Start coding and testing!

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published