Matt

Finally launch day. Hundreds and hundreds of hours have gone into this. Fun to see other people are as excited as we are and willing to show support with their dollars. kickstarter.com/projects/moder…

@tymyshoe86 @codyplof I would guess he’s using intelligems. Elevate works well for me at about 1/4 the price.

@codyplof What are you using to AB test? In the ad platforms or some Shopify app?

I’ve spent a ton of time vibe coding in Shopify. I think I’m pretty good at it. I don’t do it during the day. But it’s my current night, weekend, and early morning obsession. No idea why but it’s so fun and rewarding. Plus makes me more money. I’m setting up 2-3 new landing pages or multi variate CRO tests per week. Here’s a bunch of what I’ve learned and some tips on my process: Strategy is so important because of how fast you can move now. Our hit rate is higher than ever on CRO tests. I have a bunch of skills I built for CRO and insights. CRO skill - trained on CRO best practices and frameworks, all of our past intelligems tests, and site traffic to prioritize. But most importantly attached to a giant customer intelligence file that is fed via api from Typeform, listen labs, outer signal, junip, and more. Every survey we run or review we get makes this step better. I have a few different skills for building new pages or features. They kick off the insights process and competitor analysis. They build a html brief compiling all of this with some low fidelity mockups. The mockups are usually rough, even though they are using the design system. I’m sure I can architect some of the skills better, but it always makes mistakes and takes some trial and error. But I can get it looking 90% or the way there in an html file pretty easily. From there I have two workflows. One is pushing straight to Shopify. I have html to liquid skills that are trained on our theme architecture and requirements. Then using the Shopify CLI. Always building locally and pushing to a dev theme to preview. My favorite way to do this is on my phone using remote control and wispr. I often find it’s easier to polish designs in Shopify because it has all of our CSS. The other workflow is going from html to Figma. I find the Figma mcp is bad for this, so I use the html to Figma plugin. It’s not perfect but it gets the job done. I’ll have my design team polish the last 10% in Figma, and then I’ll use the Figma mcp to push back to Claude and then liquid. I find the Figma mcp much better for this part than pushing to Figma. From here I can just finish in Shopify and then I have a skill to manage the whole GitHub push/ pull/ merge/ PR process. Also been using Greptile for code reviews. I’ll often get a 3/5 at first and just feed Greptiles comments back into Claude; do 2 rounds of iterations and gets tons 4/5 and then I will submit the PR again. Before the PR I have two share skills. One is a design system audit, and the other is one I built for compliance to our theme that is based on feedback from early PR mistakes. A lot of things just trial and error. It’s like a video game; you just push, aww where you get stuck and try new things to push past it. When one approach works, build a skill to repeat it and it becomes part of hour workflow. But you’ll probably want to iterate on your skills. Happy to answer any questions or show some things I’ve built. At first I thought I was only gonna do this for landing pages. But I rebuild our cart while I was poolside last week, have a nav test, etc. I truly think one person can now run a best in class CRO/ experimentation program that encompasses strategy, research, design, copywriting, development, and analysis. Maybe it’s not the best in the world, but it would normally cost a lot more. We’re still hiring for this person. I’m essentially going to train one highly ambitious person on this workflow and give them a bunch of tokens. If that’s you, hit me up.

@codyplof @mbertulli Would really love to hear more about how you created the html to liquid skill that’s relevant to your specific theme architecture.

@TheSzef That makes sense. I wish manus wasn’t so expensive to iterate on.

@mattslyk i think over prompting it with good examples of what you see out there is the way. When it doesn't get something right, tell it why and how. The more you do this the more it learns

Fun Manus task: Give it access to your content drive in google and have it gather video content from every folder you ever made. Then tell it to take all existing video and put it into one main folder call it “brand video.” Out of that folder tell it to make “hype reels” of 15-20 seconds and choose the style of videos you want from some other stuff you’ve made. It’ll generate reels for you.

How are you taking what manus makes and making it live? I can get html from it and paste into gempages or similar, but then I lose the ability to graphically modify with gempages visual builder (the best feature for them). I can separately get build-out instructions from manus to make it in gempages visually, but that’s super tedious to do.

Another Manus night. Getting to the point where I just type in which product is launching, give it a few photos, and a perfect landing page is built within 4 minutes. Changed our "About Us" page to something worth looking at. Created a 'top 6' landing page with ease. Testing multiple PDPs variations. Built a website for a local run club. Building another one for baseball travel program. Revamped the web presence of an old pile driving company that has been around for decades... Best part is you can build a landing page and then have Manus actually design out your email campaigns and flows from that landing page. You have it slice up the email for you and toss is straight into @attentiveHQ ready to rock. On top of that you can take the LP, Email campaign, and any images you have and have it create you the ads that go along with it.

@codyplof Just wait until they discover how good manus is at LPs

Expect to see a lot more of this. We’re literally posting a Job opening for this role this week. The times are changing. And they’re exciting.

@theisaacmed @gefensk I think your residents are going to need nice pens machined in-house. Modern Fuel pen / pencil machine shop would be cool! Love this idea!

I am building a city as a weekend project. But I have a problem and I need your help. I have no citizens and very little buildings. I put some pre generated stuff in there as a placeholder. I put my friend @gefensk and her business Couplet. If you comment below your business, and some things that you would like to see me add, I will personally add it all in. You can access the city so far here: citybyisaac.com I will be updating it daily.

It’s amazing that despite how good AI has gotten so quickly, there are still some glaring issues that have to keep us on guard. A warning for those who are taking everything AI does as the truth. (Promoted on Claude, Haiku extended, 9 March 2026)

An AI agent / OpenClaw is only meaningful for your business if it can do one of two things: 1) increase revenue 2) decrease costs The best implementations do both.

@TDeinnocentis @Seanfrank lol $40? I didn’t look for one, just commenting on the maths

@mattslyk @Seanfrank You are right - I still don’t see a $45 tee however

I love yeti. I am a fan boy. But I am not spending $60 for their t shirts. 50% more than buck mason. Basically the same price as JP.

@TDeinnocentis @Seanfrank I don’t think you understand percentages 😂

@Seanfrank What buck mason tee is $30. How about you stick to raising your prices and bragging about the “growth”

@andrewjfaris @kos_lovro Two questions: 1) what about it is making a difference? 2) how do you know the media buying is making a dramatic impact (how do you know the counter-factual)?

@kos_lovro I've just gotten eyes on a lot of accounts recently where the media buying is very clearly making a dramatic impact

I am now the most convinced I have ever been that the "media buying isn't that important" take is extremely, extremely wrong.

When was the last time you built a live supply chain dashboard with AI co-pilot, AI customer service rep, IP infringement monitoring agent, and market / competitor sentiment monitoring agent all in one day? I’ve never done that either, but my operations agent just did it all for me. What a time to be alive.

The best part is that if you structure your agent(s) properly, you can improve things with LESS overall work on your end. The agents learn and make recommendations and GO IMPLEMENT ENTIRE PROJECTS for you and come back when it’s done. Knowledge workers will become AI-savvy implementers or will become obsolete.

When people’s agents come online it’s euphoric. You feel like you have superpowers. Everything in your brain can suddenly explode into the real world. You begin to think with a broader sense of possibility. It stretches your mind. You can now do so much. It’s infinite possibility. How you relate to that sensation probably has a lot to do with what you believe about work and its place in your life. Much like how people say having lots of money makes you more of who you already are, i find Ai use to be the same. People just become amplified versions of themselves with the tools.

@TaylorHoliday It’s absolutely unreal the things we can do now. I have improved how my business operates more in the last two days than in the past year. And it’s cost me $250 + a Mac mini.

Shopify's checkout is currently blocked. Do this and it fixes your shipping rules and unblocks checkout. Everything just got unselected for every zone for me. Just re-select and it works again.

@eric_drymer Done

@mattslyk can you actually follow me so i'm able to dm you 😂

@eric_drymer placed an order 2/3 that seemingly hasn’t shipped yet. It seems like you guys are experiencing hyper growth rn - that’s great, but I would suggest you take the “next batch ships tomorrow” countdown timer off (or change the day) if it’s not actually going to happen. Just leaves a bad taste in the customer’s mouth when you miss by this much.

@TaylorHoliday @kelceylehrich @jacob_posel As in not owning a business? Or what else do you mean? genuinely curious

@mattslyk @kelceylehrich @jacob_posel Those arent the only choices.

One day I hope to feel strongly about something as much as @TaylorHoliday believes someone making $300k/yr is poor

I’d take a $2M top-line e-commerce business *distributing* $300k per year doing what I love any day of the week. Would I rather have a $20M business growing too fast to kick out more? Probably? But it’s not always a choice of what you get — there’s risk in giving up the former to pursue the chance of the latter actually working out.

@kelceylehrich @jacob_posel Still doesn’t make it a good business. Or one that couldn’t be substantially better. Also highly unlikely to make anyone (in the United States for sure) feel rich. Nor should it because it is a lot of money compared to what people made in 1900 or the dark ages.