These are my thoughts on product, tech and design.

I used to judge people for their overflowing inboxes. You know those screenshots where someone's mail app shows a gargantuan unread count? I'd cringe wondering why they wouldn't just deal with it. I mean, how hard is it to stay on top of your email? Turns out: very hard.

I'm officially in year 2 of working for a startup, and that's brought with it a lot of late nights and weekends with less time to spend on small but important tasks like working out, laundry and deleting D2C email pollution. In less than a year I went from inbox zero to inbox disaster. I'd try to do some cleanup here and there, but while the Gmail app on my phone is limited in its ability to help, I was more surprised by how hard it was to do deep cleaning even on the desktop web. The power was there, you just might have to do 6-7 clicks and queries first. Cleaning it up was so much harder than I first thought it would be that built my own app to help me do it (more on that another time), but now I've finally got it down from 14,500+ emails to 14 and I feel like I can finally breathe again but also I have a lot of thoughts about how I got here in the first place.

I often need sane estimates I can say out loud without cringing later. To solve this, I've made the Point-O-Matic to "price" project friction.

The most profound insights about technology often come from direct experience rather than theoretical analysis. Last October when I gave my first-ever conference talk on agentic AI I emphasized process over code, specialized roles over general capability, and sequential collaboration over full autonomy. I was right about these architectural principles, but for entirely wrong reasons. The real limitations turned out to be more fundamental: accountability, security and an imperceptible line between capabilities and constraints.