co-founder @mainframe. prev: @figma @diagram @facebook.
NYC
- Tweets 4,567
- Following 1,850
- Followers 9,789
- Likes 32,231
Vincent van der Meulen retweeted
this is becoming more true, but we are limited by our tools which are still catching up
designers are working in tools built for engineers because that's where the most power is, but it can feel intimidating and unfamiliar. we are working on fixing this @mainframe
the “design engineer” will evolve to represent the blurring lines between design and code and more of us will become one
it will be both a designer than can now code thanks to AI
and an engineer that can now design because of AI
25
4
163
13,885
the best ai interfaces come from small but powerful ideas:
- github copilot: what if you could autocomplete more than a word?
- chatgpt: talk to google like it’s a human
- cursor tab: what if you could autocomplete more than a sentence?
- claude artifacts: chat and output side-by-side for instant visual feedback
- og cursor composer: code by prompting for multi-file changes
- claude code: you don’t need an ide if you have agents
- cursor bug bot: bug finders should run automatically and leave pr comments like a human
- conductor: you can parallelize work with worktrees + a master detail view
- devin: coding agents should run in the cloud and have a computer
- grok bot: personal agents should run in the cloud and have a computer
- cursor projects: it’s better to talk to a single orchestrator instead of dozens of agents
17
3
50
4,855
the future of design isn't drawing pictures and developer handoff as a step shouldn't exist.
It doesn't feel natural to compare Webflow or Framer X to Sketch/Figma/Adobe XD but as time progresses we totally will.
The future of design isn't drawing pictures and developer handoff as a step shouldn't exist.
11
1
49
3,236
Vincent van der Meulen retweeted
we're starting to test a new app with designers @mainframe
DM or reply if you want to try
413
10
813
46,029
i've been shipping prs from my runs, showers, and commutes by calling @bot.
get yourself an always available eng manager. go into debt if you have to
how to use @bot for engineering and get a ton done:
1. create a (cursor) project for every big workstream. i have ten, such as a “mcp project” and a “bugs project”
2. make sure every project spins up cloud agents with /poteto-mode
3. in grok bot, make an eng bot whose sole job is routing requests to the right project.
4. now voice call (!) your primary bot and braindump all your tasks.
your tasks will automatically end up at the correct projects, and result in sweet prs :)
you get all the benefits of projects + pstack, but don’t have to think about anything!
13
1,498
how to use @bot for engineering and get a ton done:
1. create a (cursor) project for every big workstream. i have ten, such as a “mcp project” and a “bugs project”
2. make sure every project spins up cloud agents with /poteto-mode
3. in grok bot, make an eng bot whose sole job is routing requests to the right project.
4. now voice call (!) your primary bot and braindump all your tasks.
your tasks will automatically end up at the correct projects, and result in sweet prs :)
you get all the benefits of projects + pstack, but don’t have to think about anything!
44
13
361
31,340
one underrated hack is to let your @bot manage your screen time.
e.g. my grok bot has access to my rescuetime so it can change what websites are blocked, checks in daily about # hours worked, etc.
1
10
1,436
the paid partnership label makes any brand look so cringe that i’m not sure the eyeballs are worth it
1
13
1,336
why shipping 100s of prs makes sense
there's always something to improve in your product's codebase. if your goal is to make customers happy as fast as you can, it makes sense to fix those things the moment you find out about them. we're no longer limited by intelligence!
some of this is of course the result of the new way of working. ai is a net-benefit for codebases, but leaves behind more residue as people are less in tune with low risk areas. which you then have to squash by shipping more.
of course it's a little bit different for frontend/design, where the (human) thought required for the average fix is higher. but in backend land, there are always obvious bugs waiting for you to eliminate them.
i think many people would benefit from focusing on speed! it's the equivalent of the running advice to "just run more."
unless you cheat your way out, it's hard not to get to a better product/codebase/engineering skills by simply trying to put up more prs.
we're in the brief period where models still need our slight handholding and energy, which is why this advice still feels uncomfortable. but soon enough models will make the rate at which we used to evolve products feel dull.
Can someone help me understand how shipping 100s PRs a day makes sense?
Why do you need to ship so many PRs in the first place?
I might just not be AI-pilled enough to understand the need for it yet, so I’m genuinely trying to understand it.
8
28
4,366
merged 145 prs so far today! would recommend the @poteto playbook:
1. get a lot of tokens
2. create a project (orchestrator) for every workstream. only talk to them, via ui or grok bot
3. tell your projects to spawn cloud agents in poteto mode
4. verify with cross model reviews
30
15
455
50,481
i think token scarcity is secretly causing people to underperform.
you can't do your best work if you're worrying about limits, picking dumber models than you actually need, and holding back tasks until resets.
2
2
33
2,807
i'm noticing it in myself and my decision making.
it reminds me a lot of this book (banger btw): amazon.com/dp/0805092641
2
4
522
@poteto how do you decide when to create a project?
i read that you have ~10 parallel projects and was curious why you don't have a single, big one!
since the benefit of projects seems to me that you don't have to worry about routing.
3
8
2,809
e.g. i imagine for perf work one could make their persistent project spin up a smart agent (e.g. opus 5.5 xhigh) and route all perf work there. instead of create a 2nd project?
but not sure what tradeoffs are/what cursor does internally!
also cc @alexirobbins!
1
410