What I Built

I built LazyNotesAI, a lightweight, open-source study revision assistant using Python.

As a student learning programming, I wanted to create something practical that could make revision easier. Students often spend time turning their chapter notes into summaries, keywords, and practice questions.

LazyNotesAI helps automate that repetitive work using simple text-processing techniques.

✨ Features

  • Generates quick summaries from study notes.
  • Extracts important keywords.
  • Creates revision questions with answers.
  • Saves revision material as text files.
  • Avoids overwriting previously saved notes.
  • Runs locally without external Python packages.

The project currently uses rule-based text processing, rather than a machine-learning model.

Demo

LazyNotesAI runs through a simple command-line interface.

For example, I tested Version 4.2.0 with a short Gravity chapter.

Example Input 

Chapter: Gravity Gravity is a force that attracts objects toward each other. Earth attracts objects toward its center. DONE

Example Output (Selected Excerpt) 

QUICK SUMMARY • Gravity is a force that attracts objects toward each other. • Earth attracts objects toward its center. IMPORTANT KEYWORDS • Attracts • Objects • Toward • Gravity • Force • Earth • Center REVISION QUESTIONS & ANSWERS Q1. What is gravity? Answer: Gravity is a force that attracts objects toward each other.

The program also saved the revision material to:

saved_notes/Gravity.txt

This test demonstrated the basic summarization, keyword extraction, question generation, and file-saving features.

The example above is a selected excerpt. I omitted a less useful question generated by the current rule-based system, which is an area I plan to improve.

Code

GitHub Repository:

https://github.com/thebugbag/LazyNotesAI

Version 4.2.0 Release:

https://github.com/thebugbag/LazyNotesAI/releases/tag/v4.2.0

The project is published under the MIT License.

How I Built It

I developed LazyNotesAI using Python and its built-in libraries:

  • re for regular expressions and text processing.
  • collections for keyword-frequency analysis.
  • pathlib for managing saved files.

The application processes the student's notes, identifies useful keywords, ranks sentences for the summary, and uses predefined patterns to create revision questions.

Technical clarification: Despite its name, LazyNotesAI does not currently use a large language model, an open-weight AI model, or an external AI API. It is a rule-based Python automation project.

I chose this approach to keep the application lightweight, understandable, and easy for beginners to run.

Why Open Source Matters

Open source makes it possible for students and developers to inspect the code, understand how the program works, suggest improvements, and contribute new features.

I believe beginner projects are valuable because they encourage learning through experimentation and collaboration.

By publishing LazyNotesAI openly, I hope other beginners can learn from the project and help make it better.

The Lazy Payoff

LazyNotesAI reduces the repetitive effort of manually organizing study notes into revision material.

Instead of separately writing summaries, identifying keywords, and preparing questions, students can enter their notes and generate a first draft of revision material in one run.

I tested Version 4.2.0 with a Gravity chapter example. The program generated a summary, keywords, questions with answers, and saved the results.

The output still needs improvement, especially for more complex chapters, but it demonstrates how simple Python automation can make studying more convenient.

Future Improvements

I would like to add:

  • More accurate and natural question generation.
  • Better-balanced chapter summaries.
  • Multiple-choice practice quizzes.
  • An interactive revision mode.
  • Improved handling of different subjects and longer notes.

These are future plans, not features included in the current release.

What I Learned

Building LazyNotesAI helped me practice Python programming, regular expressions, text processing, debugging, testing, GitHub documentation, and publishing a software release.

One important lesson was that software does not need to be perfect before sharing an early version. Testing, identifying limitations, and improving it gradually are all part of learning.

This is an early version of my project, and I look forward to improving it over time.

Built for students who want to revise smarter. 📚

If you have suggestions for improving LazyNotesAI, I would love to read your feedback!