Mehul Kar (@mehulkar) header
Mehul Kar (@mehulkar) profile picture

@vercel. @_amishap is No. 1 best.

Saint Louis, MO
Joined January 2009
Please stop making software factories that make themselves. There are other more useful and valuable and helpful test beds.
110
Mehul Kar retweeted
I just finished talks about my software factories at two conferences. Afterwards a bunch of people came up and told me what they were surprised about. Here is a distillation of what people thought were hot takes from my two talks. First hot take: I tell everyone to slow down. Most speakers go on about how fast they're going, but I strongly believe in pacing AI outputs to human speeds. I regularly tell AI-pilled CIOs and CTOs to chill: almost nobody is _actually_ going fast with AI. Engineering still moves at engineering speeds, and business moves even slower. The ones pushing too hard are starting to see downtime for it. If you don't pace your AI to human speeds, everything starts breaking around you, even at small operations like my online video game. I only have about a dozen humans working with my factory, and only a few hundred active old-timer players in the community who get along well, and still, introducing AI has still been very rocky. My agents have, at times, overwhelmed my players with features, my accountant with emails, my merge queue with tickets, and my machines with load. Agents have pissed off my admins, resulting in name-calling, they've made messes in the game, and they've launched broken OSS without permission. The list goes on. I can get away with all this chaos because everyone involved in my operation is very forgiving. They're excited by the potential. But even so, I had to learn to slow down, real fast. And so that's what I preach. Hot take #2: Should you buy a software factory? Do you even need one? No. You probably don't need one. Factories take an extraordinary amount of upkeep. They turn into garbage mountains unless you put a frightening amount of time and tokens into curating them. I had to burn my previous five factories down since it eventually became cheaper to rewrite them than to fix them. So I'm not out there advocating for software factories or swarms just yet. If you do want one, be aware that it is a significant commitment of both money and human leadership to keep one running. Several people told me that I was the only one who stood up onstage, at either conference, and said Build, don't Buy. But my experience is that software factories grow to be highly bespoke to your domain. Mine is super tangled up with my game, and I think that's inevitable. Because the factory is not just building my product, it's supporting it too. It's a company in a box. And they're easy for Claude to build for you. Third and arguably hottest take: Next year will have a lot of human/agent and agent/agent office drama, resulting from bringing in AI employees, and it will be gloriously funny, but also frustrating. Many of you are already on this bandwagon, but everyone next year will have a personal chief-of-staff agent. Busy people, even hobbyists, will have whole entourages of helper agents. The hot take is that people will become so dependent on these little private entourages, that they'll bring them to work. Your people will talk to my people, etc. Whole protocols will emerge for private entourages negotiating work between humans, inside companies big and small. Nearly all humans will wind up having to start working with AI employees next year, and it'll be the beginning of the biggest cultural change we've seen in a hundred years. So that's the hot takes. Slow down. Only build a factory if you think you really need one. And focus on empowering yourself with your own agentic chief of staff (or team). Your entourage will define how you work with others, so start by perfecting how you work with them yourself.
189
310
106
2,892
335,754
Mehul Kar retweeted
how do you all focus while working with both short and long running agents effectively? there are periods you are just waiting for the agents to all work but you can't really focus on anything else since there is always a thread which is ready with a response
13
1
11
1,959
I did ONE offline thing today and now I have 40 goga bits of creativity. Your computer is a local maxima.
1
2
258
Organizations are the most fascinating creatures of all. Mostly because the others are too complex for us to comprehend.
2
269
Mehul Kar retweeted
small monday 🚢: @vercel CI status is now mirrored in your browser favicon so you can keep an eye on build progress at a glance
4
2
58
1,711
The best thing you can do for your coworkers right now is to edit your written messages to be as short as possible. Especially if I'm your coworkers.
3
10
676
I hope my agents pick up this message
1
81
Everyone building software factories is imagining the singularity, or giving up and building primitives. I think the magic is somewhere in the middle.
2
2
499
me brian and god all work the same way
I've changed how I work over the last few weeks. I now have one lead agent for each area of focus, running all the time, and a chief of staff agent that oversees them. Each lead manages its own sub-agents that write code, test it, chase reviews, and coordinate with team members. Everything I need to decide or review comes into one prioritized queue, a simple local web app. Each product review includes screenshots and a video demo of the feature. I clear the queue in batches, mostly by voice and keyboard shortcuts. The leads also bring back ideas I hadn't considered. Working from one queue, instead of switching between dozens of chats, has cut a lot of mental overhead. The system keeps learning my preferences and distilling my judgment into a "Brian brain," so its recommendations and first drafts get better before they reach me. The goal is fewer corrections per change. Every change still goes through the same human review and security checks. It is eliminating tasks, not human judgment. What an exciting time to push the frontier of productivity, especially as we build the economy for agents (agentic finance). We should all keep pushing in this direction.
1
6
495
Bringing a fire back to life by blowing on the embers is one of the top feelings. 🔥🔥🔥
9
397
Enabling agents to use every single surface as easily as possible reminds of me the "sowing" part of the "me sowing and me reaping" meme. Not sure why.
1
1
142
Weekly PRs merged over the last month • Oct 5–11: 95 • Oct 12–18: 72 • Oct 19–25: 139 • Oct 26–Nov 1: 202 • Nov 2–Nov 4: 119 (this week)
1
6
615
Strongly believe that software factories are not about automating PRs. Rather, they are about finding the role of humans in software. This role can vary quite a lot.
13
1
2
69
4,388
Stack PRs are just cope because GH doesn't want to let you review/approve one commit at a time. But why.
2
3
459
Woke up to 23 of the dumbest PRs merged by my factory... and it's freaking intoxicating
1
1
207
I took the day off on Friday and my factory merged more PRs than the day before. Still the dumbest PR, but still so freaking awesome.
46
Mehul Kar retweeted
there’s a lot of power in being the first person to emoji react a slack message. sets the tone for the whole org. it should be done with care
37
139
9
5,087
89,078
Good point here. What is the agent version of Chesterton’s Fence?
This quoted post is unavailable.
161
Look I don’t know what they told you, but running a factory is more stressful than working in the factory.
2
6
435