Spring is here. My evenings lately have been deep in Boom. Writing this from Whispr, so I can’t scroll back and see what I’ve already shared. A lot has happened. Full refactor, dozens of new features, plenty of failed experiments too. Mostly when trying to let Claude run loose.
Claude is running a smoke test on Stripe.
Running a few projects this afternoon.
First up, a personal dev project. Claude + Notion + deep research.
Second, a hugggge Boom update that includes new domain, migration, backend refactoring, headless, a bunch of agentic stuff. This version is so hilariously ambitious, but pushing the agents hard. More on Boom in a second, but Claude thinks it’s 16 weeks of dev work in 3-4 days. Sure, Jan! We’ll see. Going to fire up Conductor and let it rip!
The third thing is more of a frustration or short rant. Planning for AI execution is hard. The fitness analogy lands for me: if I have a six-month goal to run a half-marathon at a specific pace, there’s research, sequencing, machine + human collabs, maybe external data sources. It’s not linear. Yesterday I was deep in some of this and it kept refactoring existing text plans and chunking things wrong. Blah blah blah.
I want a new type of space between Notion and Claude. This whole third space or fourth space thing has been overused.
The way it currently feels for me: Claude feels AI generative. Notion feels human generative. Where is somewhere in the middle, man?
I want something that leans human. A private collaborative workspace where you set the goals and accountability benchmarks (real humans versus agents) and remain the author, the main person holding the pen on your adventure. Sure AI is there and you can dial up and down as much as your heart desires but it’s mostly in the background. This works in single, multi-player, or even multi-agent mode. Whatever this category thing is the space I’m exploring with Boom! A human first headless accountability and intention layer.
Second screen and headphone status:
^54 min track is fire, bassline
New Boom TLD secured!! Will share later!
At least three times this afternoon I caught myself giggling at BOOM or if anyone actually cares about a headless shareable room builder in this AI era, especially one named Boom. And is it boom, Boom, or BOOM?
My new rules for picking side quest domains? No more than 10 minutes and 10 dollars.
Successfully recorded my first Boom video, 5 minutes, a little bit salesy, and all on my 2nd take. When creating anything, we are our own worst judge. The inner critic can rage. Ironically there’s that clip going around Twitter that screams the complete opposite. The ultra successful have zero introspection. Well, good for them I suppose.
The good news about whatever side quest you’re building → this is the worst it’ll ever be.
Last night I shipped a rough version of Boom! It deserves a blog post of sorts, and sitting as a subdomain for the time being. There’s another tab open trying to find a Boom TLD. Been working through bugs and polish all morning!
The last 20% always takes the longest. The last 5% even more so.
The good thing with AI is shocking degree to which a task (whether you are an engineer, designer, or PM) can be brought to 80%. The bottleneck then becomes people who can tell the difference between the 80% and 100%.
— Dan Grover (@DanGrover) March 13, 2026
Working until 6pm, then sending the newsletter. Finally.
Oh ya, and struggling with export settings with design assets, colours feeling washed out. Think I finally resolved it. Sharing this as more of a live dogfood test.