I built Spark, a personal AI assistant that runs 24/7 on my home server—it handles my morning briefings, tracks my trades, manages my tasks, and remembers the things I'd otherwise lose track of. Building it taught me more about AI architecture, memory systems, and cost optimization than anything else I've done. Before that, I studied Finance at UBC and spent years thinking about how money actually works—not the hoarding kind, but the kind that buys you time and options. I still trade, still budget obsessively (15+ years of YNAB), and still believe personal finance is really just personal systems design. I read constantly—philosophy, fiction, technical writing, whatever pulls me in. I keep detailed notes on most of it, which is half the reason I built an AI that can search them. Writing here is how I turn those notes into something useful. Mostly, I'm a new dad figuring it out. Flynn is the reason I care about building things that last, and the reason I think harder about what's actually worth my time.
View all authors
When I wrote about building Spark in March, I mostly wrote about the architecture: persistent memory, model routing, coding sessions, and a scheduler that could run work in the background.
Those were the pieces I had to build, but they were never really the point.
The point was that I was tired of being the database administrator of my own life.
I was at the gym one morning with my earbuds in, and I put on music instead of a podcast.
I almost changed my mind. I opened YouTube Music, saw my playlist, and had the familiar thought that I should probably use the hour for something. A finance podcast. An audiobook. Something I could point to afterwards and call useful.
Instead, I left the music on.
Somewhere in the first few minutes, I felt an ache in my chest. Not pain exactly. More like I had been holding something in for a long time without realizing it. It was strange how quickly my mind tried to move past it, find a better use for the hour, and get back to normal.
Over a year ago I started working with N8N, a self-hosted automation platform similar to Zapier that connects to basically any service you can imagine. They had a built-in AI agent builder that let me wire up my own bot using the OpenRouter API. This was before tools were a thing, before ChatGPT could search the web, before any of the major AI products had live internet access. My little bot could search the web. I remember showing that off to friends and feeling like I'd built something genuinely ahead of the curve.
Every draft of this post came back flat.
I'd describe the idea to Claude, get something back that was structured and coherent and said all the right things, and then I'd sit there trying to figure out why it didn't feel like mine. The arguments were sound. The flow was fine. But it read like a blog post about taste written by a system that doesn't have any. I kept editing, pushing it away from the centre, trying to find the version that actually sounded like me thinking out loud rather than an AI summarizing a concept.
That editing process is the whole point of this post.
In Rick Rubin's The Creative Act, there's an idea that caught my attention and stuck with me.
When musicians record a demo, they often fall in love with it. The specific sounds, the particular arrangement, all the little details that made it feel alive in that moment. But those details can become a cage. You can't expand a completed version when there's no room to grow.
So what do some of the best do? They write the demo out as sheet music. Strip it to the skeleton: just the melody, the chords, the structure. Destroy everything that isn't essential. Then hand it to the band and rebuild from the bones.
The result isn't a polished version of the original. It's something new, something with room to breathe.
I've had this vision in my head for years. The perfect note-taking app. Voice capture that transcribes instantly. AI that condenses my rambling into something useful. A fluid interface where I could zoom in and out of my thoughts like a map of my own mind.
I'd cobbled together something close using Obsidian and various plugins, but it never felt quite right. Then I discovered Claude Code, an AI that could actually write production software, and something clicked. I'd gotten pretty skilled at prompting. Maybe I could finally build the real thing, the app that matched my vision exactly.
So I started building.
My wife is Korean, and she has this way of teasing me that always lands harder than she thinks. She calls me 잔망 (janmang), which is a Korean word for someone who's mischievous, playfully silly, always clowning around. And honestly, she's not wrong. I've always been reactive, excitable, quick to jump into whatever energy is in the room. I get distracted easily, I talk too much, and I've always worn my emotions on the outside.
Then she'll say it: "You should be more like a tree."
In Korean culture, there's an adage about the ideal man. A man like a tree is someone who doesn't sway with every wind. He grows slowly, steadily, rooted in place, strong enough to shelter the people around him. He's not cold or rigid, just unmoved by the things that don't matter so he can show up fully for the things that do.
I used to brush this off. That's not me, I'm the fun one. Trees are boring. But then I became a father, and I started to understand what she meant.
I've been using a budget for over 15 years now. Even before I had a real job, before university, before any high-paying position, I started with You Need a Budget (YNAB). YNAB is an amazing tool that helps you create a budget. They offer classes on managing your budget and have principles like rolling with the punches, which means being flexible and adapting to changes. I loved this approach because it allowed me to give every dollar a job.
I just finished The Old Man and the Sea. It's a short book, maybe two hours of reading, but I found myself almost moved to tears at several points. Not because Hemingway told me to feel something, but because he left space for me to bring my own feelings to it.
I wanted to learn trading like a professional, not from YouTube personalities pushing their strategies, but from foundational knowledge drawn from the best traders and theory. No academy I know of offers this, but I knew the knowledge existed, it was just scattered and gated. So I overengineered the problem and built a system that could teach me.