Ralph Krysler 🪓

Got a new Shopify app idea. - sent 200 DMs - got 20 positive responses - going to build in 48hrs this weekend and live tweet it #buildinpublic #appchallenge

@nbaschez This is the way! Now add team collaboration, and you have something worthwhile

Introducing Roughdraft! A new open source project designed to make collaboration with agents better. The idea is to bring commenting and suggested changes to markdown (e.g. plan docs) in a nice interface. Free, local, etc. 👉 roughdraft.md 👈

Started seeing this: § A lot more in AI generated responses. Is it the new — ?

@tibo_maker SEO

this is the exact SEO checklist I've used for every single product I've launched 20+ products, $8m exit and now $1m+ mrr SEO was the backbone of all of it 💪 here's the sequence: month 1: it's about making Google trust your site month 2: it's about building topical authority month 3: it's when you look at what's ranking position 8-20 in GSC and turn those into your biggest wins most makers skip the foundation and 6 months later they wonder why nothing's moving I put the exact week-by-week breakdown into a free 90 day sprint sheet - every task, in order, linked to the right tool comment SEO and I'll send it over 👇

@MatthewBerman @vercel maybe try turborepo and see how you can cache as many things as possible. should reduce your build time

welp. this @vercel bill came as an absolute surprise

I got tired of losing sessions when I accidentally closed my terminal. So I created this: Auto-resume claude code sessions. Per-pane isolation, per-project isolation so multiple sessions in the same dir don't clobber each other. gist.github.com/Crunchyman-ral…

Sign the Bring Back Buddy petition, i miss Glitchaxl github.com/anthropics/cla…

RIP buddy, bring him back

I like my new buddy, makes me feel like I'm pair programming, drop your buddy in here!

@mattpocockuk great idea

Working on a tool that orchestrates locally sandboxed coding agents in TypeScript - Sandboxed in Docker - 100% offline: commits made in the sandbox get patched back to the host - Build complex workflows in Typescript - Claude, Codex, OpenCode It's called Sandcastle

@mitchellh at this point, is there anyone who isn’t part of vercel

Excited to share that I've joined Vercel's Board of Directors. Vercel is made up of builders and tastemakers that continually ship things that deeply impact how developers work: Next.js, AI SDK, v0, etc. I can't think of a more exciting place to be. Let's fucking ship. ▲ My relationship with Vercel goes back to the earliest days. HashiCorp was an early adopter of NextJS and Vercel (~10 years ago!) and it remains my default tech stack and deployment platform to this day. Ghostty's website is all on Vercel, too! Beyond that, I've been continually impressed with the teams relentless focus on shipping meaningful software. And importantly, software that has incredible taste. Now we are in the age of agentic software development. Vercel is building agentic infrastructure that I think every app and agent will need (I certainly need it!) and I can't think of a more exciting place to be. Huge thanks to @rauchg , Jeanne, Marten, @cramforce, @tomocchino and the entire Vercel team for the warm welcome. Time to work.

every time you start a new claude code session you spend the first 10 minutes re-explaining your project "here's the stack. here's what we're building. here's what was decided last week. here's the file structure. DON'T TOUCH THIS PART WE JUST REBUILT IT" but it's not just your own context. your teammates shipped 3 new things since yesterday, two architectural decisions changed and a dependency got swapped out. you need to capture all of that too, or claude is building from a stale snapshot you won't remember everything. so claude compiles context from scratch, misses things, and pulls in a direction that might completely miss the point. now multiply that by every dev on your team, every session, all day literal coordinated drift what we do instead: the .hamster folder syncs decisions, plans, and context to the filesystem automatically. claude reads it and just knows. no re-explaining. no stale snapshots. everyone's always got a fresh .hamster folder which updates in real-time as the rest of the team (or you) ship decisions, tasks, briefs, methods, skills, etc try it. you'll love it → @usehamster

everyone on your team maintaining their own CLAUDE.md is a symptom, not a solution. the root cause is that shared context has nowhere to live and evolve as your team makes decisions. you can't fix it with naming conventions or a better folder structure. decisions need a home. not a static file someone remembers to update. a workspace that accumulates as the team works. when a decision changes, it changes once, and every agent on the team pulls from that. there's no need to keep the markdown files up to date or copy-paste anything anywhere. claude just knows. your PRDs, your tasks, your skill files, your CLAUDE.md are all projections of the same underlying decisions. if the decisions live somewhere real, everything else stays aligned. if they stay up to date automatically, the rate of progress can explode because the synchronization overhead disappears. that's what we've been building into hamster. decisions get a home. blueprint holds your product's current state. methods encode how agents should work. the projections stay aligned because the source of truth is real. dm if you want to try it GA reeealllly soon!

We're so back baby. But for how long ?

I feel like all AI needs right now is 1M token context, I often find myself solving my problems at around 50% of that, so 500k to 1M is the sweet spot per problem

Went back from using opus 4.6 1M tokens to just normal opus 4.6 What a difficult life

Opus on 1M token is really hard to attain, I find myself often finishing at like the 50% mark lol

7/ The best AI teams won’t be the ones with the smartest prompts They’ll be the ones with the strongest harnesses The ones that are enabling AI workflows, not prompting and praying 😆

6/ You talk to AI for hours. It says it understands. Creates a PR. Says it works. You test it. Doesn't work. Now you're babysitting every agent instead of letting them run. Harness first. Then scale agents

AI coding isn’t the bottleneck anymore, PR reviews are But the fix isn’t “review faster” or find tools that can help me review faster It’s building a harness where bad code can’t survive long enough to waste human attention But how do you do that ? 👇