Matthew's Google Workspace, Apple & AI EdTech Blog

  How I Built an AI-Powered Classroom Platform in Three Days (With No Coding or Technical Experience) and what it actually means. Three days ago, I had an idea for an AI-powered English learning platform for my P6 students. Today, that platform is live on the internet, with AI citizens students can chat with, investigation cards, a teacher dashboard, and a YouTube introduction video embedded on the landing page. I have never written a line of code in my life. The link to the project platform is here Here is what I learned about building with AI — and what every educator and parent should understand about why learning to work with AI is now, possibly, as fundamental as learning to read. 1. AI Can Turn Educators Into Builders The original version of this project lived in a Google Sheet with some App Script magic. It worked, but it was clunky. Students had to copy prompts, open ChatGPT in another tab, paste them in, then copy the AI responses back into their reports. The workflow was...

Last November, I wrote about what happened when I put a small group of Grade 6 boys in a room with an AI voice simulation and told them zombies were coming. They barricaded the door. They asked about supplies - food, water and AK47s (naturally). They knew it was a simulation, a game. They were laughing and chuckling quite a lot. And as ESL students they forgot they were speaking English. They proved that a machine could bypass the "translation freeze" that keeps Hong Kong students locked in Cantonese during stress. That post — How AI Voice Mode Simulations Can Turn English Lessons into Real-Time Language Challenges  — covered the simulation activities in detail. But that was only part of the story. The Adventures in AI group at PBPS has run for the full school year in 2025-26. Forty Grade 4–6 students. Weekly sessions with small groups of 4-6 students. And while the various AI voice-mode simulations such as Zombie Apocalypse and Tutor Susan were the headline-grabbers, the qui...

In a recent experiment documented in my YT video below, I pushed Kimi 2.5 beyond the familiar “lesson plan” use case and asked a more ambitious question: Can an AI model design a functioning, iterative educational resource that actually resembles a real course product? The answer, quite clearly, was yes. You can get Kimi here.  Starting from a simple prompt, Kimi 2.5 generated a complete short course website—structured, navigable, and pedagogically coherent—designed to teach an individual learner (me) how to transition from using Filmora video editing software to Final Cut Pro. This wasn’t just content generation. It was educational design, curriculum logic, and user experience thinking, all emerging from a simple, iterative dialogue with the model. Link to site here:  https://ovqbchvv6dpvk.ok.kimi.link/ For educators across K–12, higher education, and corporate training, this opens up some genuinely transformative possibilities. 3 clear positives that leapt to mind as I inter...

Many EFL and ESL classrooms still practise speaking and listening in calm, predictable settings. A scaffolded pair-work speaking task here, a multiple-choice listening exercise about two people at a train station there—perfectly valid and useful. But real communication in the real world doesn’t always feel calm or predictable. When you’re using English as a second or foreign language, you might forget words, someone might speak too fast, and you have to react instantly. Real life can be very different from a multiple-choice listening activity or a highly scripted pair-work speaking task in class. So, can we help our students develop—through practice—more proactive, real-world speed listening and speaking skills? Answering that question with a YES is the logic behind some of the activities in our school’s enrichment program this year: the Adventures in AI Group for Grades 4–6 students. One type of activity we’ve been testing involves AI voice-mode simulations that drop upper-p...