What is it about?
More and more software is built by describing what you want to an AI tool instead of writing every line by hand, a practice often called vibecoding. Most college computing courses still teach only hand-written code. We created Vibecoding: Introduction to Applied AI, a free, openly licensed course with a textbook, slides, a syllabus and a hands-on lab for each chapter. Students learn to write clear specifications, direct AI coding agents, and check AI-written code for mistakes and security problems before relying on it.
Featured Image
Photo by Steve A Johnson on Unsplash
Why is it important?
Employers increasingly expect graduates to work with AI coding tools, and surveys show students want this training, but few courses teach it directly. Because the materials are free and openly licensed, any instructor can adopt or adapt them, including at schools without the time or staff to build such a course from scratch. The course also teaches where AI tools fall short, so students learn to verify what the AI produces before they trust it.
Perspectives
I learned to build software with AI models by trial and error, mostly on my own, because my courses treated the tools as something to police. Banning them never made anyone a better programmer, and they are not going away. I helped write this curriculum to be the teacher I did not have. It matters most for people with no technical training, who can now build software that was out of reach a few years ago, as long as someone teaches them to plan the work, direct the model, and check what it produces.
Eli Young
AlgoArena
Read the Original
This page is a summary of: Teaching Vibecoding: An Open Curriculum for AI-Assisted Software Development, November 2026, ACM (Association for Computing Machinery),
DOI: 10.1145/3795860.3846244.
You can read the full text:
Resources
Contributors
The following have contributed to this page
