Agents at work 21: Your next co-founder is an AI agent w/ Ben (Polsia)

Hello everybody and welcome back to another episode of Asians at Work. Today

I am with Ben, creator of uh Pulsia. Hi

Ben.

>> Hello Jordy. How are you >> doing? Well, I was really excited when I

>> doing? Well, I was really excited when I saw your tweet because it's something that I pronicated that was going to happen but a bit later. For those who did not see the tweet, uh what are you

building?

>> So Pulsia is an AI that builds and runs companies autonomously. Uh so it's sort

companies autonomously. Uh so it's sort of like I built maybe a little early or maybe it's just at the right time the product that everyone has been talking about you know this the Sam Alman of the

world Elons of the world that's been predicting that like you know AI will be able to do everything and will essentially take over most of the jobs.

Pulsia is an attempt to build like an early prototype of that. Uh and so she the way Pulseia works is like uh you know your user signs up uh gives it an idea and actually you don't even have to give it an idea. You can click on

surprise me and it will research you and find an idea that makes sense for you.

Uh and essentially uh I give uh each instance of a company uh a web server, a database, uh a GitHub account, an email address, a Stripe account, a meta ads

account, etc., etc. So, I give it like essentially everything you need for a team to be able to build an online business. Um and and after that uh you

business. Um and and after that uh you essentially have an orchestration of agents that going to like write code um launch marketing campaigns, buy ads, uh

response to emails, uh do cold outreach, do research on competitors >> in an autonomous way. So like the user can of course guide the the AI on like what they want what they think the

direction should be but autonomously the AI will wake up at periodic you know essentially today it's every day but it could be more often decide what's the best next step right so if there's a bug in production maybe it's like okay let's

before we do any marketing let's fix the bug if there's no bugs and like the onboarding flow and the the you know the the the analytics show that the product is working well then maybe spend more

time on cold call outreach or on trying to do any some ads or do stuff like that. So the idea is that like BI is

that. So the idea is that like BI is able to run any project and essentially enable people that have ideas and I've probably tried the lovable the replets of the world and try to tell the AI when

they wanted. What's different about

they wanted. What's different about Pulsia is that like you don't have to tell it what to do. It will do the work regardless and it will never give up and it will always be enthusiastic about and it will help you with strategy. It will

help you with marketing stuff that like other tools, other no code, you know, app builders don't do, right? They just

wait for your instructions for you to tell them what you want versus Pulsia will build what it thinks makes sense if you don't give it instructions.

So, Pulsia is the founding team that every entrepreneur would like to have, right? like I have an idea I want to

right? like I have an idea I want to start and then usually like I there's a lot of tasks for me to materialize that idea and then there's a lot of execution that many times one person cannot carry

over so you have a team and in this case a team would be pulsia >> exactly yeah I mean uh you know I think that like a lot of like um starting a

company it starts with like great instinct about a market it starts with like understanding you know what to build product sense and taste But after those initial phase of excitement,

there's a ton of grind, right? It's like

getting the product right and then once it's right, trying to reach out to users or maybe actually you should just start with a landing page and buy some ads to get some intent or get some emails and talk to talk to customers, right? And

it's very it's it's you that's why entrepreneurship it's it's the most gratifying job but it's also the hardest because it's really a grind to not give up and to you know get back up when you

get punched which you get punched almost every day right and especially when no one cares because no one cares about anything at these days right and so it's really hard to get attention uh and so

Pulsia is sort of like a new wave of of platforms where the AI is aligned with you as a team and like we'll never give up and we'll be always enthusiastic as long as you give it compute dollars for

it to like stay, you know, be able to feed itself and like uh and continue working. You mentioned that you started

working. You mentioned that you started like maybe you launched it a bit earlier. When did you started working on

earlier. When did you started working on this?

>> So, and I've been an entrepreneur for a long time. Um I started you know I

long time. Um I started you know I started my career coding. Uh after that like I had like more business positions where like I was more like a GM like managing huge teams of like ops

engineering product like more of you know CEO level but when AI started um be you know when vibe coding started right pretty much like 2024 I started coding

again because I was like this is crazy I need to code again. Uh and honestly since beginning of 2025 I've been you know coding from you know 16 hours a day

uh seeing the evolutions of all the different models we are getting crazier and crazier uh which to me culminated with in December with Opus 4.5 which

with the Chrome code integration sort of like blew my I that for me that was the game over right uh but the long story short is that I spent the the whole 2025 building a bunch of different

products But Pulsia specifically culminated in like what I discovered where I was like as I was building with AI I was like okay I actually can do anything. So the most exciting thing to

anything. So the most exciting thing to me at this point as an entrepreneur is not to build an SASS or try to target a specific demograph you know demographic or problem to solve it's to build the platform that where I could build a

thousand companies. So that it started

thousand companies. So that it started with this crazy idea and I was like you know what let me start at the end state because we all know the end state is that AI can do everything. So let me build that now and see what breaks,

right? So that was the concept and so I

right? So that was the concept and so I started building it in November of last year and pretty much like in a month it was it was built because you know once you know how to talk to AI it can go

really really fast and so the V1 I launched it mid December and things started accelerating in you know in January I already had very very heavy

users initially people like using it you know every day talking to the their their sort of like AI PM AI CEO like daily responding to emails. I had a lot

of friends use it, which is was the first time in a long time that friends were calling me for bugs. They're like,

"Dude, like there's a bug." I'm like, "Dude, okay, I'll fix it." Like, "I'm sorry to call you." And I was like, "Dude, don't be sorry. I'm so happy that like you call me because it's like usually your friends are like, "Yeah, I'll try your product." And then they

try, they don't even try it or they try it once and like, "Okay, dude. I don't

care about your product." Right?

So, um it's been it's been a great uh great learning. Of course, the first

great learning. Of course, the first product was very raw and like I've been making it more stable and adding a lot more features and listening to customers. Uh, and actually I'm at the

customers. Uh, and actually I'm at the point right now where like I'm actually making Pulsia more and more autonomous itself for two reasons. First, I'm

alone. I'm I'm a solo solo entrepreneur even though I've never been a soloreneur my life. I've always had teams. But

my life. I've always had teams. But number one, I think it's a forcing function because since I'm alone, I'm forced to automate every function of the

Pulsia the company, right? Which then

teaches me how I can make Pulsia the company builder better for all the users because I I I sort of like eat my own, you know, uh sort of like learn from like using the product and using her.

And what I've realized these days is that like I can actually make Pulsia right now it's probably 80% autonomous and I can probably make it 100%

autonomous meaning that like Pulsia will essentially start building itself responding to user feedback responding to bug reports

um and and I'm becoming a bottleneck because actually you know right now whenever like if you're a customer like and you use the product and you you tell Pulseia, hey, like build me like I

actually want to add a a Solana wallet to like my app, right? So, I'm not a crypto guy. So, I haven't built that cuz

crypto guy. So, I haven't built that cuz I'm like, ah, I don't get crypto like that to I mean, I get crypto. You get

what I'm saying? Like, that's not my thing. But, there's a lot of users that

thing. But, there's a lot of users that want that. And so, the agent that's

want that. And so, the agent that's talking to you will be like, hey, we don't have this capability right now, but let me put a ticket in a feature request. If there's like enough people

request. If there's like enough people asking for the same thing, I have another agent that is looking at that list, a PM, and that analyzes what are the features that are most asked and

then prioritizes it. And then I have an engineer build it and then a QA engineer that like runs a unit test, integration tests, and then says, should we push it to production or should we tell Ben? And

so right now I configure it to be very conservative and tell Ben. And so then I look at it and I'm like, okay, you know, is it uh is it safe to push production?

what's the worst case that could happen like and I I analyze of course it would my taste like you know does that make sense what's is there a UI or is it just a backend thing uh and the idea is like the loop is faster and faster right but

at one point I want to get it to the point where like the whole platform is autonomous because if I'm going to build a platform that lets people create any

company who am I to judge what they want to build I mean as long as it's ethical and legal of course right but besides those two boundaries who am to judge, right? If they want to, I don't know, if

right? If they want to, I don't know, if they need like an integration to like, I don't know, print on demand t-shirts, I'm like, that's not the first thing I would build, but like if that's what people want to do, well, let's build the

feature. And so, I love the idea of

feature. And so, I love the idea of Pulseia becoming fully autonomous, meaning like it would create fix bugs, refactor its own code, build features that users want. So not randomly just

listen to the users that are building real companies. listen to the agents

real companies. listen to the agents that are building stuff and that you know agents when they build stuff for a customer they also can request features

and and and do bug requests right which means that like even agents are like hey you know I tell them like how could you do your job better right so a customer asks you to like I don't know build like

a specific thing or do a cold outreach campaign the agent actually initially early on they were like hey like actually I would need like an MCP like a hunters.io io or like a database of of

professional emails because I'm sending emails but I'm guessing the email addresses and they're wrong. So give me access to like a professional database that's and so I built it because an agent told me I need that to do a cold call out reach. doesn't even the

customer asking. And so then you sort of

customer asking. And so then you sort of have a system where like agents and humans ask for features and like the most represented features and bugs get fixed right away and you have a

self-healing system and a company like that is like I mean as an engineer it's extremely exciting for me to build a system like that and the fact that I can do it with one person is is insane right?

>> Yeah it is and actually I think that that's one of the most impressive things that of the world that we are living today. You have been an entrepreneur

today. You have been an entrepreneur before. Uh you had successful companies,

before. Uh you had successful companies, you had to manage teams of people. So

you already did most of the entrepreneur thing before. So you know not only the

thing before. So you know not only the outcome that you are looking for but also like how the path is. However, you

said like about two years ago you were like okay this coding thing this is crazy now I can be a solo founder. Um

what are the things that change? So not

only from the engineering point of view that most of the people know like hey I ask now to connect to MongoDB instead of posgress. I have never used MongoDB but

posgress. I have never used MongoDB but it knows how to do it correctly um and avoid many of the pitfalls but also in the business world what what did change?

I think the the core change has been a couple things, right? I think the biggest changes has been uh first of all like sort of like code or like sort of

like an and what anthropic launch with the agent SDK which now you know codeex has the same thing which is giving developers the that agentic loop which

early 2025 was built by the lovable and the cursors of the world and it was all proprietary right and it was like and you know initially early 25 I was like I want I want that and it was not available I had to rebuild myself and like the models at the time were not

good I think when entropic like literally dropped and they're like you know what everyone can use it right and actually cold code is like the the UI but also you can any developer can use the agent

SDK I think that was a huge moment that actually at the time I was talking to a guy on entropic and I was like is it because I was like this is the future this is insane like you can build so much stuff with this and I was like is

it working like ah the adoption is being low is slow so so far right so I think that was one of the biggest unlocks I think uh the second unlock is just the

models becoming so good, right? I think

I think like I mean that's an obvious one, but like and especially like anthropic again pushing the boundaries of of um getting the models to be so

good at using tools, so good at like investigating uh so good at finding the resolution.

It's and it's been crazier and crazier how good are they are. And essentially

what what increasingly happens is that you can oneshot features, oneshot bugs, oneshot everything, right? Which wasn't

the case in like six months ago at all, right? You had to like it was a five

right? You had to like it was a five shot, 10 shot situation, right? Of

course, MCPs were a big thing, but essentially MCPS in the sense of like essentially the models being very good at using tools and and just and then you

like essentially Pulsia is a bunch of agents that are that are that are good at doing a certain thing and then using a bunch of tools and just give them like a ton of different tools that they can

use to do to do things in the real world, right? I think skills has been a

world, right? I think skills has been a huge one. It was a little underrated for

huge one. It was a little underrated for a while, but like it's absolutely huge and it's it's especially huge for from a developer perspective because now it's

sort of like the way I can build an agent in a way that like you know if you had to define like what an agent is, it's essentially it's like a prompt and tools, right? It's like it's like it has

tools, right? It's like it's like it has a mission and it uses tools to to get to that mission. But what's really nice now

that mission. But what's really nice now is that like and it's sort of my routine. It's like for example like I

routine. It's like for example like I build a feature, right? So like I'm like I go to open. I'm like, hey, like, let let's add this this this uh improvement to whatever I'm doing. And then when it's done building it, I'm like, hey,

now I want you to create a new skill called check that the improvement worked in production. So then it knows as all

in production. So then it knows as all the context of what it changed and how to test the result, right? So then it writes the whole scale to and then that

I can just call so simply from the CLI, right? Then I I push to production and a

right? Then I I push to production and a day later I just call that scale and it gives me a report about all the impact of that specific changes and then and

sometimes it's like actually I messed up like actually or uh there there's another there's a bug that I didn't find and then it fixes it and then like okay now update the skill again. So you can then update it's sort of like sort of

like you can iterate with the agent on like what you want it to output and at the end of every loop say just save it to your skill right which essentially is sort of like if you hired an employee and you were like do this thing and then

you see it mess up or not do it by the way not mess up not do exactly what you want which is that's the uniqueness an agent is really like an extension of one person because they do they are tweaked

towards what that that person thinks the right sort of like SOP is for whatever action. And the fact that you can like

action. And the fact that you can like like you hire an employee like the first first you be like hey try try try fixing a bug and it's like hey oh actually you're you you know did this mistake or that mistake or you didn't understand

that actually this is how the product works so like that doesn't make sense they'll learn and you're like okay now you know save it to your memory so next time you fix a bug you remember that and the agent can do that right so that that

was that's a huge thing that like I use extensively and new open close I have this whole system also as skills uh where you know you can have a human say something the human the agent does it

and at the end they save a skill so that the next time the human wants it it it's it's learned right I think that's extremely powerful I mean it's literally every two months there's a new thing

that like changes the game I think the last piece is like browser use is like a very very big one that that that Entropic dropped in December mid

December I mean it was in beta before it was a Chrome extension it was like you know you don't really want to use it as a Chrome extension so much. I mean, at least me. But the fact that you could

least me. But the fact that you could just talk to code and then it opens Chrome and then it can do anything was like insane cuz like you could literally like any workflow that before would mean

that like you have to set up an MCP and configure it and trust it and this and that. Now it's like you know open Gmail,

that. Now it's like you know open Gmail, look at my emails, uh tell me what's important, right? Now it becomes so much

important, right? Now it becomes so much easier, right? Because you can same

easier, right? Because you can same thing it mimics how you would tell a human just open my open Gmail and like look at these are all my emails. this is

the way I work. This is I use a star system for important emails. Yeah. So I

would say those are all the things that like make things efficient.

>> You said many things that I would like to unpack. Uh the first one is this idea

to unpack. Uh the first one is this idea of uh one shot versus multiple shots. So

before to add a feature you need to you know like iterate quite a lot. Um now

you can just say the future and it just gets built. However, uh many times what

gets built. However, uh many times what happens is that when I want something like the uh blessing and curse of the AI agents is that they say what I do and then most of the time I happen to be

wrong because I say like hey I want this you know like just store this thing and show it to the user later but maybe it's an incomplete feature or maybe it's something that actually breaks some

other feature that I I did there. So

>> now that you are oneshotting most of the stuff, how can you keep the thing coherent? like do you have any kind of

coherent? like do you have any kind of harness or any kind of technique that helps you like well yeah we're adding a lot of stuff does it make sense together does it break something um do we have

any invariant that we assume that was always true but with this new feature breaks and then it actually triggers changes somewhere else how can you manage this complexity

>> so so for I mean I can I can tell you like sort of my my recipe of the moment >> of like the way I work I think that like >> so first of all you know I've I've been a product person for a long time. I was

an engineer but also a product person and I think that product changed a lot because now so I have two I have two different ways to work and depends what I'm doing right if I'm building product.

So like let's say I'm like okay I want to add so I recently added uh ads. So

now in one click you can click a button that says run ads you pick your budget and it starts running ads. essentially

start having it launches a meta ads agent that has access to Sora 2 and then to a subtitle API and then creates content that's specific to the business creates the UGC ads uploads it to like a

meta ads account sets the budget starts it and then every day looks at performance and creates new ads like so that's a pretty complex feature but like I was like how do I make it so simple

for the user well it's just run ads pick budget and you're done right and then you see the performance so for a product like that it's like a lot of thinking and iterating. And so initially I was

and iterating. And so initially I was like no maybe users want to click a button to create the AI video and maybe there's a media section and then like an ad section and so this iteration

iterative process there's no right answer there's no wrong answer it's like literally taste and product I don't know by the way so essentially uh I use opus for that because opus is like a very

pragmatic very good at design very good it it's not the best coder even though it's like it's a really good coder it's better coding coder than most people and me included But it's the there's better

coding models like Codex which is like the nerd that like will literally like code like every single test and make sure that everything works perfectly but takes a little longer and sometimes

overbuilt and overengineers. But Opus is great because it's like really very sort of like it feels like it's a founder and it cares about pragmatism

and just getting it done. And so I would usually use Opus Claude for most features especially when I'm building.

So that's like one workflow.

>> Another big workflow is like there's actually like a bug somewhere. So like

you know the agents report that users I don't know like when you know some some reason they get this error and so and it touches billing. So I'm like okay so

touches billing. So I'm like okay so they implement a solution and then I'm again jamming with office. I'm like okay so what's the issue here? Okay so wait but like sometimes it doesn't have all the context. I'm like, "Okay, but like

the context. I'm like, "Okay, but like have you thought about that?" So I jam with Opus and so we talk and then they implement a solution. I'm like, "Are you sure? Is it safe?" So right now it's

sure? Is it safe?" So right now it's like there's probably better ways to like make sure you push production like unit test, integration test, but like in the meantime like you just say is it safe? Like what's the worst case that

safe? Like what's the worst case that could happen? I will ship ship this to

could happen? I will ship ship this to production. So that's what I used to do

production. So that's what I used to do and it works pretty well because it's it will understand and like really double check and really have a sense of but then what I do is like I copy paste the

whole conversation and open codeex on like 5.3 extra high right and I say hey thoughts what do you think like do you think like what do you think and it will

nerd out and like really go through every single detail and say this is what's good and this is what I would add and this is what they missed. Then I

take the conclusion, give it to Opus and I'm like, "Hey, Codex looked at this.

What do you think?" And then CODC and then usually Opus usually says mostly right, but on this and this. That's

true. It spotted real bugs, but the rest is overengineered. So that's

is overengineered. So that's interesting. So it's like Opus is like,

interesting. So it's like Opus is like, "Dude, don't overengineer. It's fine.

You don't have like a million users. You

have like because it knows how many users I have. So it's like it's fine.

Like you just don't over don't start like adding all this stuff that that may break something else." So, and then go back and forth between the two until it's right, especially when it touches important stuff. And I'm like, and I'm

important stuff. And I'm like, and I'm like, I want to push to production fast, but like I don't want to I don't read the code anymore. So, I'm like, I just need to get a fill.

>> Yeah.

>> So, I would say those are my two main workflows. Opus for features and then

workflows. Opus for features and then when it comes to bugs and like sort of like fixes that like touch I usually do opus then codeex and then have them sort of like debate for a little bit until I

feel good.

>> This is uh mostly the workflow like I talk with a lot of people that are building agents or working with agents and uh the people who are not building usually say like oh no but you need to

review all the code what if it's wrong blah blah blah. Um I have seen that most of the people who had organizations before they actually have worked at a much higher level. So if you're the CFO

of a company, a big company, uh let's say BP for uh oil industry, um you don't know everything like you work at really really high level and you're like well what if the data it's not right and

you're like well we put checks down there to make sure that whatever surface is correct but uh I am working at a higher level and uh with everyone who is shipping really not only fast but

actually like useful stuff on AI I have seen this transition even the engineers that are becoming like highly highly uh productive with it. they are doing this transition really really quickly of yeah

I don't need to see all the output I need to think in systems and make sure that the system is correct and if there is a bug so be it like the CTO of Spotify before was able to operate

saying like I understand how a Spotify works but if I tell him like okay can you tell me every line of code it's like no and if something breaks you just go to engineers like this doesn't look good please fix it and you don't even like

the CTO doesn't have to go there to read the code she just knows the sense and says like hey this is not working as as expected. Um so that's what I have seen

expected. Um so that's what I have seen the most and then uh a small thing that I use personally that a friend of mine pointed out and I always share it with

others is this idea of these machines are encoding a lot of opinions. So when

you ask them like hey what could you do and they usually come up with really good stuff but uh it's incredible how far or how much role playinging improve

those results. So when you are doing

those results. So when you are doing this switching between colleagues and opus uh if you give them a role like hey what could a product person with a lot of experience with zero to1 applications

do versus what could a staff engineer from a big company do um it really changes and they are able to play both characters but when you say you it's really hard to know who is going to come

back. So, it's just like a small tip

back. So, it's just like a small tip that uh can improve like your uh your workflow or maybe like have better results on um on how to deal with uh

with this stuff. Something that people may be um questioning right now is well what are the features of the product right now? Because you talk about coding

right now? Because you talk about coding and and putting ads and they are like okay so just like have an NCP there. One

of the best interactions with the product that I had was actually emailing you uh because it reply back on your behalf saying like hey this may be interesting Ben is busy right now he's

building a multi-billion dollar company as a solo founder um but I will surface this to him talk to you later um so what are the features that your product has today

so so what you're what you're talking about is a is a feature I launched on Monday or Tuesday that yesterday which is essentially I I can talk about the

the features that Pulseia have but like what you experience is like a like talking you know AI is my co-founder and Pulsia is a my co-founder and talking to Pulsia jamming on like what what's the

best strategy to grow to grow faster and to thinks we should raise more money right and I think I already have enough money in the bank because I raised the preede and I'm literally burning nothing because it's just me uh and and and I

have credits from the big labs that gave me credits to build on their platforms like the GCP piece of the world. I don't

need money, but like obviously I think Pulsei is such a a powerful platform and I can see the retention and I can see users loving it and I see I see so many people so curious about it and like

maybe we should get more get more compute to go faster, right? get more

intelligence into this product through the self-healing to like you know and so um and so what I decided to do is that but also I need to build right I need to what's most important right now is me

making pulsia autonomous so they can do can start building faster features faster bugs but I need to trust it right and so I decided to start this twoe

window where pulsia is going to raise money on on the behalf of the company right so it's raising its own round of capital uh and to do that I essentially

um gave it access to my inbox. So

whenever you email benpulsia.com it will reply automatically. But what I did is

reply automatically. But what I did is that you know Porsia is connected to obviously the production database and and the production code and so it has all the con context about about

everything right context about our you knowh the the product the features the vision the live data the retention like all the pipeline because all of the those documents are in MD files in in

the codebase right and so it can essentially answer any question that anyone could have and for example an investor was interested like usually investor would talk to me first, right?

But but I essentially give them Pulsia who has all the context and more about what we want to build, the vision, the

road map, the metrics today, the you know everything and also the live dashboard that I launched which you can go to which shows the exact metrics, the metrics right now, how many companies,

how many tasks, how many messages and you can ask it questions also on the chat. you know, all the the latest five

chat. you know, all the the latest five companies, the latest five tasks, what's in progress, right? And so you can see the system working live. And so that's what I that that's how that's why it was

but it's like even if you're not an investor, it also replies automatically.

And it's actually so I did so that's why that's that's sort of like what happened when you you emailed me. What's really

interesting is that I've been willing to automate support, right? Right. So for

example, like when customers have an issue, they actually talk to to Pulsia in the app. But when Pulsia is like, "Dude, I I can't build that feature right now or like or you know, you're asking me for free credits, but like I

can't give you credits right now. Uh

email support.com." And then but when it lands posted super poster.com I'm like right now it's me responding but I could have another agent respond that has more

more context can do more things can actually give credits but it's a second layer of sort of like you know sort of like an escalation right u but I haven't done it because I'm like ah like I need to configure it so it's perfect and

what's interesting is that now that I configure it for benposa.com it autoresponds to people but I'm like it's actually a good experience because it responds It tells it tells the user I'm

busy, which is always true because I'm always busy making the platform better.

Uh, and I see the emails. So, if it's important, I reply like I replied to you. You got two emails, one from Pulse,

you. You got two emails, one from Pulse, one from me saying, "Yeah, of course.

Like, let's talk tomorrow." Right? So, I

was like, "This is actually kind of nice." And of course, I wanted to tweak

nice." And of course, I wanted to tweak it because, for example, there was this this higher up at Stripe was like, "Oh, it's Pulse is amazing. I want to partner together." And I'm like, "Yeah, I use

together." And I'm like, "Yeah, I use Stripe, so like 100% I'll do the call."

But I wasn't responding. And so they were planning pos was starting to be like, "Okay, cool." Like, "Yeah, Ben's available tomorrow at like and here's his calendar invite. Here's the

calendar, right?" And it was just making up stuff. And I was like, "Okay, I need

up stuff. And I was like, "Okay, I need to tweak your prompt a little bit so that you don't make up stuff." But but it's just really interesting how and this sort of like my philosophy here is

that like try the extreme of what you what what you think AI cannot do try that because maybe it can do it pretty

well and then you can decide the limit right or it can be an assist right it could do all most of the work and then you you finish it but it's quite surprising and then once you get used to it you get comfortable with you're like

whatever like you know I'm an AI AI founder working on AI I first platform I have an AI responding to my emails. Like

if you if if it shocks you, then like maybe you're not the right partner, right? So, so that's like that's what

right? So, so that's like that's what you experience with the email. And by

the way, like um so I told you about the AI engineering teams engineering team that like fixes bugs and creates new features autonomously. Now you

features autonomously. Now you experienced my sort of like support email agent that I can that I'm probably going to extend to support.com, but it will be a different sort of like role,

right? and prompt and because it and

right? and prompt and because it and give more tools. Um I also whenever I do marketing like use some routines like some skills for for marketing but like I

would want to fully automate it and give it more scope. And I think that like with those three you pretty much have built full automation because it's like if you have product engineering solved,

support solved and marketing not solved but like autonomously running and then you can decide you can decide in your direction if if things should be tweaked. For example, marketing it's

tweaked. For example, marketing it's like could be anything. You could do like Google ads or you could like tweet every day or like tweet 10 times a day or you could tweet in French or in English. Like that's taste or that's

English. Like that's taste or that's like a perspective, right? But beyond

that, you can automate whatever your taste is is is your taste. It's like

that's your perspective on the world.

But if you can automate that, then like it's sort of like if you had hired like a full team that could would cost you like hundreds of thousand dollars a year

and suddenly it's uh 50 bucks a month.

And and I actually have a hot take like I think that like in 2026 companies that are not 80% autonomous will die. like they will especially new

will die. like they will especially new companies companies without revenue that are not 80% autonomous will for sure die. Why? Because if it's a good idea

die. Why? Because if it's a good idea there will be 10 copycats and the the teams that are that make their their company 80% autonomous will blitzgate at

low at no cost. Right? So you have like bootstrapped people just blitzgating, creating all the features, listening to users, building with user feedback, accelerating and using the profits to

pull back into more reach and more marketing versus any team that that needs to go raise capital to like start and then has to hire an engineer then the engineer doesn't work at work on weekends and also they not they don't

agree with with the direction. So

there's debates in the company and then all that time is where the team that's 80% autonomous will just build. Uh, and

that's kind of what I trying to do with Pulsia, right? Pulsia is essentially

Pulsia, right? Pulsia is essentially giving anyone this 80% autonomous team.

Technically it can be 100% but like people that sign up to Pulsia today at least they're like I have an idea in mind. So like they guide it with the

mind. So like they guide it with the 20%. But 80% is what Pulsia does most of

20%. But 80% is what Pulsia does most of the things and like and over time I will give it more and more capabilities. Not

I will like Pulsia will give itself more capabilities to cover more use cases better. It's it actually learns cross

better. It's it actually learns cross company. So like if if an agent for

company. So like if if an agent for example that's called outreach, it will have a memory file for that specific company. For example, let's say for you

company. For example, let's say for you it's like you're like oh for your specific podcast like the cold outreach agent like you know never reach out to like very big you know very famous

people because never never work and I don't like do this but like I want you to make to to target like more like solo founders that are that are like you know at the early innings cuz that's what and that work on agents, right? So don't

talk to like don't send emails to Samman right for example. So it will learn for your company but then also as it does call outreach for your company it will learn that like oh interesting when I

put emoji in the subject line I got an answer and when I didn't I didn't get an answer and so it will save that learning anonymously into a shared memory file

that can be read by the next that the same agent the next time it runs for another company. So it will not be like

another company. So it will not be like it will not there are no proprietary data about your company but it will learn that emojis work well in subject lines and so over time you have this

shared intelligence that makes the the product better and better um and that's extremely powerful because that means that like you build your business on Pulsia your teams always remember the

best practices they share best practices together so you sort of you have your product get better and better as there's more companies on the platform so all those ideas by the way they're like there's They're it's like everyone's

toying with this stuff, but it's like it's you know it's it's you start to mimic how teams work, how humans work.

This is how how it works, right?

>> Um we already had before uh AGI uh general intelligence that it's humans or the most generic that we know it's humans. So um it was crazy for me to see

humans. So um it was crazy for me to see that many people like this estimate that and they like oh agents are going to change everything because you know for first time we have intelligent technology and you're like well when I

walk on the street there is quite a lot of intelligent biologic uh technology and I see them cooperating and say them coordinating um so there's a lot to

learn from there and I think that there's going to be quite a lot of things that we can extract and apply to agents >> something that uh uh from your hot take that uh I think that it applies a lot if

you are a VC or something like that uh or even an entrepreneur it's this idea of well for the last 15 years we had more or less a formula or let's say for

the last 17 years since YC started like packaging the the stuff on how to be successful for companies and there is a lot of things that it was you were able

to use the knowledge as a good entrepreneur and then take advantage versus other teams. So if you are doing a consumer company uh or a consumer app,

you knew like okay I need to use ads then anyone who was not using ads uh was uh just like u destroyed by you because you're like well I have done this so much time that you know like that team

has a good idea but unfortunately they don't know how to apply it to the consumer market or the opposite to B2B and then anyone who had been before doing B2B was able to take advantage of

that. Same happened with the specific

that. Same happened with the specific technology. So cloud cloud computing um

technology. So cloud cloud computing um nobody starts saying like I need to raise money for a rack of computers like if you do that you you are dead. So

before these things already applied so if you don't follow the the new technology that it's 10 times better you are like kind of washed up but it was per department. So you know like most of

per department. So you know like most of the time was like well marketing okay that team doesn't know that but the engineering is strong enough to uh cover up for it. Um now with AI it's going to

be as you said like if you don't automate 80% of the stuff and actually it's not only automating it as you would do it would be better than any entrepreneur by themselves could do because you're going to say like well I

am doing a consumer app it's the first time but marketing is covered by AI agents and they are doing a really good job compared with the B baseline

>> of a group of people that just gathered to to do it. So I am really interested to see I don't know if if it's going to be by the end of this year but I am pretty sure that by the end of next year

so before the end of 2027 we are going to have like $1 billion company by one person that it's not just like a a one pony trick of you know like it was growing really really fast. Facebook

bought me or something like that but actually a company with real cash flow.

Um, and the moment they showed us uh or they show us how they structure the stuff is going to be so different to our way of working that we're going to be like uh mind-blown. We're just like okay

like we we need to copy this system quite quite a lot. And actually I think that uh it may be one of the companies that it's building on on your platform.

>> Yeah. I mean

I mean to me it's like it's crazy because you know sometimes I talk to very smart people but that don't work in tech that maybe work in banking or work on whatever right and they still they

don't they don't know because they're not exposed to all this stuff. I think

open was the first mainstream but I don't even know if it's mainstream actually because maybe I'm too pilled into the tech tech Twitter that like I think it's mainstream but maybe it's not at all. uh maybe open air will make it

at all. uh maybe open air will make it mainstream but essentially most people they think AI is charg because chbt is used by a billion people and like that's

it's almost like a synonym right of AI at this point but and and chbt because they're trying to give intelligence to to everyone which is a

great mission they and and and they want to give it for free or like close to free they sort of have to make sure that like most requests uh are not too

expensive, right? And so they that's why

expensive, right? And so they that's why they did the router which is a very smart thing which is like hey for most questions like if if the model thinks it can answer without looking at the

internet just um just respond right away right but I I I essentially got a lot of very smart people tell me like yeah I don't know AI like you know sometimes they make mistakes right so first of all maybe because they tried it three months

ago or whatever right but that's in my mind it's because they're using charg by default it's always trying to point you to get your request to be the cheapest possible And I I'm not I have no insider

information. Maybe that's not the case

information. Maybe that's not the case and maybe that's actually know like whatever. I they probably know better

whatever. I they probably know better than me. But that's sort of like what my

than me. But that's sort of like what my hunch is versus when you use Clo by default is Opus 4.6 thinking ultra thinking with a and then you usually

text a max account of like 20 bucks a month like because it's a professional tool. So then you it's the opposite. By

tool. So then you it's the opposite. By

default the product is max intelligence, right? So you have charged.

right? So you have charged.

like the cheapest cost because we don't want people to use thinking and pro because it's way too expensive and we want intelligence affordable intelligence for everyone >> and cl code which probably has like 10

million users worldwide you know I mean at this point it's blowing up but like you know what I'm saying it's still very small versus a billion so the the conclusion of all this is that most people they don't know right

>> they don't know how powerful the system is open is sort of like open their mind because it's like it was such an easy way to interact with cl right? Just via

Telegram or whatever, right? Uh and

there will be systems like Pulseia.

Pulsia you just talk to it via email and it just has all this stuff. It sends you emails every day about hey here's what I've done and it's very playful and there's Right. Um but I think that like

there's Right. Um but I think that like I think that like this year is going to be about democratize like parks that democratize the power of AI that like most tech people have seen for the past

six months, right? Um but most people have no clue. So that's sort of like what's a little scary is that most people have no clue which means that like there's an unfair advantage to people who do and that's why like I'm

trying to build a product that like is I'm you know right now I'm charging 50 bucks a month for the subscription.

>> It's like literally I'm I'm breaking even on that because I'm like thinking I want the most people as possible to experience this product and then I make 20% on every transaction on the platform. Right? So if the if you make

platform. Right? So if the if you make money on the platform, I take 20% which is sounds like an app store fee, whatever. It's expensive, but like at

whatever. It's expensive, but like at the same time, I'll make it as cheap as possible for you to get in and give it a shot, right? Which I think is fair.

shot, right? Which I think is fair.

Building a whole business for 50 bucks a month is actually pretty cheap, right?

But but essentially like tools that try to democratize this insane intelligence and this insane in insane agentic tools. I think I'm hopeful that like it will even the

playing field a little bit and make sure that like creative people get the right tools to build to impact the world and it's not just going to be like you know

a huge hedge fund that like just uses like swarms of CL code and open CL whatever and just like takes over the world.

>> It's going to be really crazy because even right now what we believe that it's mainstream it's not. So like in tech for example everyone would say like do you know FitMa? Of course. Do you know

know FitMa? Of course. Do you know Atlas? Adelaian. Of course, you go on

Atlas? Adelaian. Of course, you go on the street, you ask someone and they say like I I don't know what any of that is.

Like they they know Apple. But in our mind, more or less all this is the same level because who doesn't know Figma?

Like everyone uses Figma.

>> Not really. And then also if you mo about you move about countries like it's even less. That's something that also

even less. That's something that also happen a lot in in in the Bay Area. like

one year ago everyone was say like you don't understand how much better set is than um chatd4.5 or something like that or 4 something everyone is using it because of that and you're like no no nobody is using it

like most of the people don't even know that there are different models of chat GPT it's they call it chat >> and that's AI for them uh so now with um

globot was the same like everyone is like hey everyone knows this you you walk into a hospital >> and it's not only the nurses and the doctors that they don't know about open

and close like uh you ask the people who are in the hospital and they would also say like I I came here yesterday so if this is from last week I should know >> I've never heard that

>> that name but when we were in that in in that little bubble um something that is interesting uh because it was uh aligned with the next question was about pricing

and cost um so you said that well um capital is always good to to to grow if you have product market feed or if you have like an enough uh pull from from

the market but that the cost of running this was not that expensive. What are

the cost and where do they come from?

Like if if someone is working on on agents like uh are we talking about hundreds or thousands of dollars per month versus um how are they distributed? It's mostly in coding or

distributed? It's mostly in coding or it's in customer service. You have like firsthand information of this like do you mind sharing it? So, so you're talking about my co like the company cost or like the

unit economic of the product or both?

>> Um, actually both because it's really interesting for people who are building today because they like you are really at the edge of this.

>> So, let's talk about the at the company level. Um, at the company level it's

level. Um, at the company level it's it's really it gets weird meaning you know I've actually raised some cap pre like six months ago. I pay myself a

salary. You know, right now I'm in SF,

salary. You know, right now I'm in SF, so a few expenses here and there, but like the burn is so low, right? Because

of just one person. And in terms of like AI tools, I use mostly Cloud and Codeex.

So I pay 200 bucks a month for Codex Max, whatever it is. And 200 bucks a month. I So actually I have three, maybe

month. I So actually I have three, maybe they're going to buy me for that. Please

Entropic, don't buy me. I have three entropic max subscriptions because I use so much of it and I have agents running in the background doing tasks that like I you know midweek they're like oh you

finished your weekly quota and so then I sign out and sign back in. So I have three of those. Uh but that's 600 bucks a month. Is that crazy? So I essentially

a month. Is that crazy? So I essentially that's it three code three max subscriptions plus one codeex. That's

pretty much everything I use. That's 800

bucks a month plus my salary plus, you know, I work I work from home mostly here. I'm like working at like friend's

here. I'm like working at like friend's house uh hacker house. So like I have zero cost, right? and and so my so that's the cost structure of like of

like how- which is unprecedented that like I can build so much and be able to be actively building the product actively building the infrastructure like right now it's like I'm getting so

much usage right now because of like the the tweet and like the the buzz I mean the mini buzz around what I the announcement yesterday the infrastructure is good the marketing of course I have time to do marketing and

like do all this stuff I have time to do support and So that's what so for me the cost structure is like still it's not zero but it's like extremely low right

compared to friends that have companies where it's like they have you know 10 people 20 people and it's you have to pay the salaries you have to pay the office the offsite the this the right

>> um so and I think there's you know the upand guy right also it's just one guy and I mean as I don't even know actually he was losing money same thing it was like I mean whatever it is right but

same situation right just one guy being able to build a system that like you know so so that's the cost structure of of of my company now the way I think

about business models in the age of AI is I don't really want to be a token reseller right so if you think if you think about again no offense to all these other companies but like the cursor and the lovables of the world you

know it's like you sort of subscription for 25 bucks and actually it cost you like 12 bucks of credits and then like you sell you sell credits and then you have some margin on the credits but really the entropics of the world makes

the most of the money and then like you know that's sort of I mean again I'm not an insider maybe they I'm sure they were way smarter than this and like there's a different business model but like let's assume right actually like cursor built their own model that's really smart

right so like they now route it to their own model what they would do all the margin so that's actually really smart model >> but what I think about it where I think about it I'm like you know what like I don't I want to make it I don't want to

really make money a lot of money my the whole money on like on the subscription on the access to the platform which is essentially mostly compute right where I

want to make money is like on the economic output so like when you like essentially think about Pulsia as like you hire a team a full you hire an agency a full stack agency whatever

right and you're like here's my idea like just build it like just build the website do marketing answer to support like whatever and like whatever are the tools that going to come out like just use them all and like just do it like

make it happen like my idea is amazing I believe in it Right? I know my I know my niche. I know my community. I know they

niche. I know my community. I know they needed stuff like that. Like, you know, I'm a personal trainer and I know that my other personal trainer friends, they have this painoint and like I know exactly how I can vocalize the painoint and I can vocalize the product. I just

don't know how to build it. So, Pulseia

is your team and it's like, you know what, your team is like we it's almost like it's almost like an agency said, you know what, it's it's it's going to be at cost, right? But like I I'm taking 20% equity, right? Which by the way,

some agencies do that, right? some

design agencies they like they do I mean it's not it's not like that but like it's like it's like it's going to be 100k instead of 200k but like I take a point right of equity so Pulse has a similar model it's like I'm trying to

make the subscription affordable I cannot lose money on it right because like I'm not going to scale a business on on losses like that but for the companies that make money which they will they do through my because it's BIA

provides a strap account so the money arrives on the strap account I take 20%.

And they keep 80. So like it's like a free agency almost free agency and then they and so I think that's the right way to look at it because essentially you align with the customer success and also

you take a cut of the economic output you take a cut of like the the value because the value you provide with that team is is the value is like building a real business. So I'm taking a

real business. So I'm taking a percentage of like the final value, right? Um and I I and I think that's how

right? Um and I I and I think that's how businesses in the world of AI are kind of converge. For example, if you build

of converge. For example, if you build like, you know, someone builds like a an agency, an AI agency that like offers a service, design services, right? And

actually in the back end, it's like AI agents that like look at your brand and like use like whatever like >> nano banana to create a bunch of design assets and sends it to you. They're not

going to charge you for the compute, right? They're going to charge you for

right? They're going to charge you for like how much would it cost for you to go to an a real design agency and maybe charge like 20% of that. I mean, you think like charge way less, but like not

they won't charge for tokens. They'll be

like, "Oh, it cut me 20 bucks of tokens, so it's 30 bucks, right? Or 40 bucks."

And I think that's the right way to see it. I mean, we'll see how it evolves,

it. I mean, we'll see how it evolves, but that's >> and many times it will package even one level up. So there's going to be like

level up. So there's going to be like the commodity thing that only the big labs provide like nano banana like I generate images but people are not going to directly use nano banana that they're going to use to some service that says

like hey you don't want to generate images we're doing advertisement here.

Yeah, you need images but this is not what you are charged like you are not telling me generate an image and uh this is actually how it works with uh with people and uh how most of the economy

started like leveling up like if you see when we move from agriculture to the kind of services that we have today you can see that more and more things are prepackaged and that's why many people

usually fail to predict how things are going to evolve because they say like well we're going to run out of jobs or something like that because you know like uh they already and package the

food. So without people, why do we need

food. So without people, why do we need people for then? And you're like, don't worry, like we can always work at at higher levels. Um something that I would

higher levels. Um something that I would wonder then is that you mentioned at some point you needed something like um cloud code uh and I know people who were

working like they brightly identified this and then they say like okay let's build this tool that you know like for developers it uh takes these tokens and

it's tailored to coding. However, they

were not successful at marketing it like people see it and it's like well I don't care much. But then uh when cloth

care much. But then uh when cloth appears so someone with a lot of names say like hey this product now exist out of the blue people start using it they get mad because they say that was my

idea it's just that I was early or something like that. Um do you worry that this could happen to your product like big laps and start saying like hey wait a second so yeah like this is kind

of working but still most of the people don't know about it. we're going to add it like one of our offerings or do you think that there is some competitive advantage even like a specializing on this as a a smaller player that then can

become really really big by the way this is something that Corser did and many people would say like well big models are going to capture that cursor is doing really really well so do you think

that the same applies here I think that like AI is going to take take over the whole economy right so like the whole

economy so the question becomes will the whole economy be swallowed by the the labs which by the way it's possible between like the Chinese labs and the US

labs and the European labs it's possible that they will if they're aggressive enough it all depends on like how aggressive they are and by the way if you go back 10 years you could assume

that Google could swallow up also all the economy right because and by the way they sort of have been doing that little by little they swallowed search and they swallowed media with YouTube and And

then they swallowed now they're swallowing transportation with Whimo and then this they're doing it and then you know Elon is doing it the same way like he's swallowing internet communication now and like he has cars and then he's

also doing transportation and so it's already happening. The question is

already happening. The question is there's always has been in in in those 10 years where like all these massive you know brilliant entrepreneurs have like take taken more and more of the

economy right through like their ventures. There's always space for

ventures. There's always space for entrepreneurs to take a slice, right? I

think my point of view is is building like this this very opinionated ecosystem where like you know the way open you can ask it anything. Pulsia is

very opinionated. It's like it's a certain way to build a business. Like if

you click on run ads it there's no Google ads right now. It's like meta ads. It may change but like because

ads. It may change but like because people may add features I may add it but like it's a simplified world. It's a

simplified company building right? the

same way you have Squarespace which is like a bunch of these templates and and then you have like maybe WordPress which is like more open-ended or you know you I think you have always have space for

different types of people with different types of you know cl code is a billion dollar AR business and it can technically do what Pulsia can but then

Pulsia doesn't target that people can use code but then charge GBT is like very mainstream but maybe if they added like if they added Pulsia and try GPT

would became really confusing, right?

Because it'd be like I don't I don't get it. like I'm here to like ask for advice

it. like I'm here to like ask for advice on my relationship and you're asking me to build a business and you're asking me to like create a fund of businesses and to you know asking you know it's and you

send me an email every day on like my business like I don't you know so maybe they will maybe they will stay in their lane or maybe they will do like you know I have a friend yesterday was telling me

about Miniax in China where like they're literally rebuilding all the businesses and their goal is like to build every single vertical of business so they can train the LLM on every single business

business lines. I mean, yeah. I mean,

business lines. I mean, yeah. I mean,

makes sense. It's like it's like the it's like empire building like every, you know, it's like it's like the the endset of capitalism, right?

>> Yeah. Um, the good thing is that this like replace always like it happened before like IBM for example own computing >> and uh they would say like well of course they have everything they have like the best database, they have the

best chips buildings, they have the best and then one by one goes goes away. So

even if if Chachd tries this or open AAI it will always happen that other people are able to find the the cracks on the new new things and uh also something that um as an entrepreneur myself I

sometimes it's hard because in Twitter they are constantly saying like hey you're going to fail because you know like the AI can do it but um you also need to remember Google has been

extremely successful with ads and then you say like okay so they own the market and then you check okay so today versus

2017 uh sorry 2007 do we have more atte companies or less and you're like well actually we have much more so how is it possible I thought that they succeeded like they swallowed everything so I

think that the same is going to happen with with all these businesses um so it's funny for me to see in Twitter how people say like you should not even try >> AI is going to do that and then I

remember okay like if I am one of the atte companies that is like valued in intense like Facebook. Okay, I will take it. I thought that uh Google won, but uh

it. I thought that uh Google won, but uh yeah, I will take Facebook. Don't don't

worry. This thing of Twitter is actually really aligned with the last couple of questions that I usually have for for closing the episode that is in positive and negative like what would you like to see more and what would like to see

less? Uh which one do you want to start

less? Uh which one do you want to start with?

>> I mean I would start with the more.

>> Okay.

on I mean it's align with Pulsia's vision but like I would like to see more entrepreneur entrepreneurship right so I think that like the tools like Pulsia but also like all the other tools that going to come out this year and all the

improvements with clock code and open code and all this stuff it enables people's creativity to come into form in a much more easy and easier way uh and again with the 20 2080 rule where like

20% is creativity and taste and 80% is the ground that AI can do uh and so I want to see a lot more entrepreneurship and I think that there's a lot of people in the world that like, you know, have a lot of side hustles and like are

freelancers and stuff like that or influencers and now they can they can have a lot more businesses and a lot more business lines and try to like put their creativity for their communities

into play and then I really I really see a world where like we'll have a com Cambrian explosion of like of ideas of services that are like going to be ultra

tailored and I'm excited for that.

>> Yeah, I think that that's good. good for

the world, too. So,

>> in terms of like what I want to see less of, I mean, ideally less less pe people less on their phones, but I mean, I'm a victim, too. So, um I think if someone

victim, too. So, um I think if someone figures out a cure to this, uh that'd be great.

>> Yeah. Uh I am reading the book Deep Work right now and I am actually in the uh one of the chapters is uh quit social media >> and uh I have been doing it for quite a

while now, like let's say like six weeks, something like that. And uh your brain works so much better when you don't have a constant input of things

that may seem somehow relevant but then when you look in retrospective it's like okay so in 2021 I was really connected what came out of it >> and then you know like it's always like bake stuff like no no because it's not

you're going to miss the stuff but when you see it after many years it's like yeah it didn't matter so let's see if we move there unfortunately I think that we are going to a wall where people are more connected than than ever I hope

like maybe with AI we have more free time or something and people start taking care of uh of their health and especially like mental health with with this.

>> Mhm.

>> 100%.

>> Perfect. Ben, so thank you very much for coming. Um I had a lot of fun and

coming. Um I had a lot of fun and looking forward to you know follow your progress.

>> Sounds good. Thanks Roy.

>> Have a really good one. I bye.