Conducting an AI and Vibe Coding Workshop at NPR Arts & Science College

On 11 September 2026, I had the pleasure of conducting a hands-on workshop on AI and Vibe Coding for the students of the Department of Computer Science (Artificial Intelligence) at NPR Arts & Science College, Natham, Dindigul.

The session ran from 9:30 AM to 2:45 PM in the college's IoT Lab, and it was built less like a lecture and more like a working day. Students didn't just hear about AI-assisted development, they picked an idea, wrote prompts, generated code with AI, tested what came out, and iterated on it themselves.

From Prompts To Working Code

We opened with the shift software development is going through right now: from writing every line by hand to describing intent and letting AI turn that intent into a first working draft. I broke this down into a simple loop that stayed with the students through the day: you write a prompt, the AI predicts and generates code from it, you run what it produces, and then you test, react, and describe the fix when something breaks.

That loop - prompt, generate, test, react - became the backbone of everything we built afterward. It gave students a repeatable way to think about working with AI, instead of treating it as a black box that either works or doesn't.

A Full Day Of Building, Not Just Listening

The workshop followed a roadmap rather than a single talk: a kickoff on what vibe coding actually is, groundwork on tools and setup, an idea and prompt pitch where students described what they wanted to build, two build sprints where they actually built it, a review and extend round, and a closing demo and Q&A.

That structure mattered. Students moved from an idea to a working prototype in the same room, on the same day, with AI as a collaborator rather than a shortcut. Watching that shift happen in real time - hesitant prompts in the morning, confident iteration by the afternoon - was the most rewarding part of the day.

Curiosity In The Room

What stayed with me most was the curiosity. Students didn't just want to know how to write a better prompt; they asked how professional teams actually use AI in production, where it breaks down, how much of generated code to trust, and how their own workflow should change because of it.

Sessions like this are never one-directional. Their questions about how the next generation is thinking about building software gave me just as much to reflect on as anything I presented.

Gratitude

My thanks to NPR Arts & Science College and the Department of Computer Science (Artificial Intelligence) for the invitation, the warm hospitality, and for giving their students a full day to genuinely build rather than just watch.

I closed the session with a line I try to live by in my own work, and hope a few of them carry forward too: keep building, keep experimenting, keep asking better questions. Looking forward to more opportunities to share, mentor, and build alongside students like these.