Building MealDeck — a game-like way to decide what’s for dinner — in short, focused bursts has been less about speed and more about learning how to work with an AI that’s quick, occasionally clumsy, and always in need of a steady hand. Two weeks into building MealDeck in my spare time, I’ve settled into a rhythm — part curiosity, part experiment. I’m not chasing speed for its own sake, but I am interested in seeing how far I can get working alongside an AI for just eight hours a week.

I’ve recently carved out a small window of time each week to return to hands-on coding, with the help of AI tools. This post is a reflection on what it means to re-engage with a long-standing side project — MealDeck — while balancing the demands of work, life, and everything in between. It’s also the beginning of an experiment: how far can I get with just eight focused hours a week?

I decided to embrace 2025 and finally go wireless with my mouse game. What a mistake. I just burnt 90 minutes searching high and low, trying (and failing) to make a decision. My stream of consciousness for the last 90 mins went a bit like this: How are there so many options? Will this work with my mac or not? Will it make me install some horrible software? Just what is DPI and Hz and why should I care?

I remember when I was introduced to Google Search. I found myself – a young boy – slightly lost amongst the shelves of our local library. Turning a corner, I stopped to gaze at a cramped desk overladen with three CRT computer monitors. We didn’t have a home computer, but my father had, on the rare occasion, let me play Bow & Arrow on his work ThinkPad. A librarian must have noticed my curiosity and asked if I had used something called the web before.