Daily log

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.

Still convinced agents are going to be incredibly useful for development and brainstorming, but they don’t understand nuance for visuals, feels, or vibes. If you ask an LLM what “washed out” means, it will spit out directionally correct text, but won’t be able to translate that into actionable outputs. The same as asking your neighbor or spouse, they’ll feel an image, potentially agree with you, but won’t have an actionable way of making something less or more washed out. Any attempt will be futile.

Which brings me to the point I keep coming back to: strategy (accountability), marketing, product marketing especially, and brand designers are not getting replaced by AI anytime soon. I already see a massive demand for designers who have real product marketing chops, and that’s only going to grow. The taste and feeling.. that bringing to life magical process has to come from within. A human!

This afternoon I’m chatting with two teams who want to start experimenting with AI. Earlier this morning I got some time to play with a few different models, running due diligence on designer portfolios and design assets. Interesting exercise. Basically how or why I wrote the blurb above.

After a super rainy and snowy week, the sun is out and it’s marvelous… shining bright like a diamond. House bombs are on in the background and summer is coming, baby. Trumpets and all

Now: back to the newsletter that has to ship in the next few hours

Every team seems to be debating total token spend and how to measure AI success, especially as huge chunks of code get written and released to production. Some of these booby traps aren’t found out or catastrophic until days, weeks, or months later. For example, the recent Amazon outage caused by AI code wiped out an estimated 6.3M orders and somewhere between $250M and $380M in revenue. And the 13 hour AWS outage that followed cost between $500M and $1B!

Contrary to popular belief, uptime would be the number one metric teams should focus on, followed by deployments that push successful business metrics, followed by experimentation and AI learning. We’ve somehow missed this step in the equation and prioritized speed at all costs.

My caveat to that is if early in the pre-seed, then of course move fast and break things, but if you’re an established company with substantial users, it may be time to revisit your KPIs.

Paper.design is the new design baddie. A few friends think that Figma will acquire them, although it feels rather early. Product is tons of fun, and the website has several easter eggs. Screenshot below.

With three weeks left in the quarter, transitioning away from experimentation into execution mode. This website design, my personal website is giving me the ick. Trying to resist the temptation to nerf everything and just use plain text files for everything, something that humans and browsers can view, but most importantly agents.

Predicting coffee shops and community spaces are going to be a huge 3rd space moving forward.

Two camps:

1. No-screen/phone cafes - a refuge from AI and tech
2. Builder cafes - fast internet, real community, upskill camps, micro events worth showing up for (WeWork 2.0)

AI is going to have far more people working hansolo. We need community. The builder cafe doesn’t really exist yet.

Local govs and tourism boards should be funding these. Genuine economic dev hiding in plain sight. The second most obv funding choice is Claude & OpenAI. Maybe subsidized cafes.. enter the UBC (Universal Basic Cafe)!

And 100p writing this from Perfecto Cafe, where the wifi internet can’t keep up with Claude’s agentic demands.

Something I’m trying: spend at least 20 minutes looking at nice visual work across the web instead of tinkering with new AI design tools. 75% ingesting visuals that look and feel good, 25% actually designing with new AI tools.

Attaching a photo as a reminder to try new things.

What else? It’s Taco Tuesday, duh. My meat is cooking in the background while writing this, and drafting a newsletter.

Raincouver is going off and I’ve carved out a few days to get my to-do list checked off. Let’s gooo

This morning I built attempted to build a mini tool that scrapes various web pages, reports back fonts, takes screenshots, and produces those results into a single page. Something I was expecting to crank out within 30-45 minutes turned into a 2.5 hour adventure where I eventually trashed the project.

Two minor frustrations:

1. HTML files produced by app kept crashing Claude. Regardless of working in Cowork, Command Prompt, or the web based version it would time out and run out of context. It’s very peculiar bc the HTML page rendered properly within Safari and Chrome but Claude just wasn’t having any part of it.
2. Hallucination. It flat out lied, ignored instructions, told me it scraped fresh content when it leveraged previous data.

These are all part of the learning process, right? AI build reps!

What else?

• published v1 blog post draft The Plus Exchange
• learning more on ai harnesses and chunking
• had an agent review 150 designer applications
• hoping to ship a mini app tonight

Happy friday

My social media feed is full of cherry blossom photos from Tokyo, Kyoto, and Osaka. Either that, or my friends and extended network in Singapore are going off about the local government’s new AI initiative.. specifically, the free premium OpenAI account for every resident over 25 who completes a few AI workshops. People are completely outraged lah

The Ship 10 Challenge I started about three weeks ago came to a close. I fell off last week, but I’m restarting it right now! Let’s goo

Today: shipping one new mini product, emailing my network to use said new product, writing a quick newsletter, draft new blog post, showcasing recent strategy and design work for a client, and laying the first few pages in my Moleskine on how to build Agentic Soul.

A few weeks back I couldn’t stop myself from building every new microservice. This week, it’s reviving all my old startup sunsets. New rule: wait at least two weeks before digging up startups from the grave.

Saw this photo of Tokyo. Sharing because it’s cool, and japan has been on my mind recently…

One rule I’m trying to stick to: only share what’s already done, or what I’ll finish in the next 8-10 hours. A daily log should be about today, not tomorrow.

AI has made words, plans, and agentic to-do lists cheap. Here’s what Claude says about best practices for writing a daily log:

A daily log is essentially a running record of what you did, decided, and learned throughout a day.

Why keep one? The core purpose is externalized memory — getting things out of your head so you can move faster, think clearer, and not lose things. It also creates an audit trail for yourself (and sometimes others).

Canceled ChatGPT this morning. Two months into Claude Max and haven’t hit a limit yet. There was a 10-day stretch in the middle where I slowed down, but the first 20 days and what’s coming next more than make up for it. Going pretty hard over the next 3-4 days.

How do we collect information and onboard new humans into dashboards or shared agentic experiences?

A few moments ago I scrapped my fourth rewrite. I’ve decided to do two things: simplify, and go back to my trusted Moleskine.

For new digital experiences, my intuition says Claude + ChatGPT, while incredibly effective at producing a V1, miss the mark when trying newer / experimental things. The Claude output just feels like microwaved slop. My goal today is to finish V1, scale back design, and get real humans through my new little mouse trap.

This mini launch won’t be what I’d hoped. It completes my first goal but not my secondary ones. Next week or the week after, I plan to try some of these radical onboarding experiences just to see what happens.

The question bouncing in my head: how do humans and agents onboard and share collaboratively with other humans and agents? Shared spaces, context, and gardens.

Tonight, if I wrap up some other deliverables, I’ll go back to the Moleskine and jot through my ideal user experience to see if this feels any better.

How does the chocolate banana chip muffin taste?

Pretty good, he said.

Yeah, I was thinking about getting one.

Oh, did you want some? Did you want to try it?

Oh no, I shouldn’t.

Yeah, go ahead.

The asker used his thumb and index finger to gently scoop the piece into his mouth.

Mmm, that’s actually pretty good. I’m gonna get one.

He walked to the counter. Sold out.

He returned to the bench.

Hey — have you tried the chocolate chip cookie?

No, I haven’t.

Do you think it will be any good? If I grab one, will you have some with me?

Oh yeah, that would be nice.

This was the start of a bromance between two strangers who spent the next 35 minutes sharing life goals, pleasantries, and newfound plans to meet halfway around the world in Tokyo. I sat front row, typing away on my MacBook Pro, in quiet awe. All from the last chocolate banana chip muffin.

after 10 days of testing every browser out there, i’m back on Chrome. Mainly for 2 reasons: the Notion clipper (basb) and Google video meetings.

exploring design agents today, specifically a brandkit agent for a product that was sunset but could be revived. inspired by Emmett - https://x.com/emmettshine/status/2024113482623258907

Claude utilization on my Max 20 plan increased from 4% per day to around 6% over the last few days. Let’s see how that trends for the rest of month.

Are admin dashboards dead? After 45 minutes refining and redesigning for a new mini app, I realized that moving forward, all report requests will be automated daily, potentially include a genAI UI report, and be accessed via command line or Slack. Duh. What am i even doing?

The second realization: AI sucks at PMM. I’ll make the claim rn, no model will ever fully get there. It’s storytelling and craft maxxing. It might generate word salad, but they’re empty greens. PMM is foreplay for beautiful product.

And with that, I’ll start PMM’ing this website. Whenever I roll up my sleeves and pace my hallway relentlessly, the positioning, perceptions, and idea maze balloon… both the product marketing and the product get stronger. New ideas. They feed into each other. Iterations, a/b, technical debt, pruning features.

imho, the best product minds use PMM as the gateway, a middle layer after v1 of the product. Amazon talks about starting with the press release, and that works for larger, established companies. In the 0 to 1 startup phase, I believe the dance is product → PMM → product → PR → then PMM again.

good night

Created four new projects today, and can’t remember ever creating as many gh repos in a single day where they weren’t all related to each other. One scope-creeped as I was making so much progress and the requirements I fed Claude kept changing like a mad men. Pushing claude! My biggest frustration rn, which is my own fault, is Claude Co-work inconsistencies with MCP and random timeouts.

Three competing challenges with my Ship 10 experiments:
Which track? Am I spending too much time or effort here? Focus whereee?

1. Development and shipping mini apps. Start and finish from command line.
2. Leaning into design: prototyping and refining as much as possible within design tools. Design, dev, design.
3. Marketing and growth: positioning, content, marketing copy, product marketing pages, design, and demand.
4. AI systems: operation, skills, shortcuts, integrations, orchestra, and so on.

The plan is continue Ship10 challenges through each area, shifting after this week from dev, design, mrktng, to systems. I may regret the sequence…

Juggling multiple AI projects takes significant cognitive load. Restricting the number of open tabs, bookmarks, and read-laters is paramount.