# Paperclip: Orchestrating Zero-Human AI Companies

**Podcast:** The Startup Ideas Podcast
**Published:** 2026-03-26

## Transcript

How do you turn a group of AI agents into a company that actually runs itself?
You know, with org charts, roles, goals, budgets, and agents working around the clock 24-7.
There's this project called Paperclip.
Maybe you've seen it because it just blew up.
It got 30,000 GitHub stars in the last three weeks.
And it's an open source project that's building the orchestration layer for exactly that hiring a team of AI agents.
So I sat down with Dota.
He's the creator.
And it's one of the first times he's publicly talked about how to use his product.
We broke down exactly how to use paperclip in practice and what a zero human company could actually look like using paperclip.
Enjoy the episode.
Dota is here.
Well, his AI avatar is here, and we're gonna be going through Paperclip, the viral, you know, what are you calling it?
Yeah, so it's a uh agent orchestrator for uh zero human companies.
So it's a tool that you can use to put in your ideas and uh manage a company of agents.
Okay, and by the end of this episode, what are people gonna get out of this?
Yeah, so by the end of this episode, you will be able to know how to uh get paperclip up and running and use it to manage a team of AI agents uh to help you with your business.
Okay, and you're not gonna hold back from people, right?
You're gonna you're gonna tell you're gonna give us the unfiltered how to get started, how to get the most out of it, and maybe where the future of this product is going, right?
Absolutely, yeah.
Yeah, I'll give you my best tips.
Um, you know, I think there's a lot of tricky things when it comes to using AI agents, and we'll talk about it.
We'll talk about ways to keep them moving, we'll talk about ways to get quality work.
Um, I'll give you all my best details.
And and just just I have to ask, like, why are you an avatar and why are you not showing your face?
Oh, yeah.
Um, so uh because before I worked on paperclip, I was working in uh NFTs and uh the Dota persona has just been uh the my online persona ever since.
Okay.
You know, Naval always says uh the best uh the best outcome is to be famous, but nobody knows you.
Uh I I understand.
And listen, you got good hair, so you know, I'm not I'm not judging.
All right, let's get into it.
All right, yeah.
So let me talk about paperclip.
So paperclip, um, here I can show you this dashboard.
This would be the dashboard that I use to manage paperclip itself, which is pretty involved.
So let's take a step back.
So um the idea with paperclip is it is a tool for um the tagline is zero human companies.
Now, um, I think that is maybe a bit aspirational.
I'm sure you guys have seen tools like Pulsia, where you uh you you give it your credit card, it creates um business ideas for you.
And um paperclip is designed to be have a little bit more control right now because it's designed for um work that you're really accountable for doing.
Um the idea behind Paperclip is that you're really managing your business goals.
So it's not uh, you know, on one end you might have something like Pulsia that's totally automatic.
On the other hand, you might have like an AI coding tool where there's a bunch of tabs open and you're managing pull requests.
With Paperclip, your idea is you're going to manage business goals.
You define your goals, you hire a team, um, and then you approve what they're doing and they go and they work on it.
So an interesting thing about paperclip is that it's bring your own bot, right?
So you're already starting to see the um labs come up with project management tools.
So you have OpenAI, you have Anthropic.
Um with OpenAI, they have Symfony, with Anthropic, of course, they're releasing new project management tools every day.
With with Paperclip, um, you're able to bring your own bot.
If you use cursor cloud, if you use open claw, if you use um Claude CLI, like I I would say that all the programmers that I know, or all the like entrepreneurs that I know are uh using lots of different models because they all have such a different personality, and that's one of the key things um about paperclip is that you can bring your own agent uh into the system.
So yeah, uh Greg, one of the things I thought we could do is we could go to uh your idea browser.
Yeah.
And we could look here and we could try just try to decide something from the idea browser that we could try to use uh as as a case study.
So I don't know, what's what's one of these that you think might be a good uh a good option?
Um if you screw I mean there's a few really interesting ones.
Like I like the you tell me, I'll give you two and you pick.
So scroll up.
Yep.
So if you go down, there's a finance finance app that builds money habits in three minutes a day.
Okay.
That's one option.
And then the other option, if you scroll down.
Yep.
The uh flight compensation recovery agent for frequent flyers.
Both of those, I think would are great ideas.
Okay, nice.
Yeah, let's try let's try a finance app that builds money habits.
So one of the things I noticed actually when I was testing this out, if you just right click, you can copy like pretty much a good description from this, more than more than this.
Um so here we can come in here, like what do we want to name our app?
We'll name it um uh Moolah.
Yeah, Moolah.
Okay, great.
And what is this company trying to achieve, right?
So this text box, I suppose, is a little small, but um, we'll just paste it in and we'll come back and we'll look at this in a second.
Um after you write down what you want your company to do, you create your first agent.
So paperclip right now um best works when it's on your local machine, and especially if you already have something like Claude Code or Codex installed.
I think these tools are really important for really any agent-driven entrepreneur.
I'm guessing pretty much everyone in your audience has at least like Claude Code or Codex installed, right?
Um we recommend that you use one of these two for your CEO, which would be your first agent, but we do support other agent types, right?
You can use open code, which means you could use really any model that you have on uh uh open router.
So you've probably seen open router.
Um they have like uh what is it, leaderboard that kind of shows the most popular, yeah, the rankings.
They have the AI model ranking.
So you can use any of these models with Paperclip.
I think you're gonna get the best results with Paperclip if you use a frontier model for your CEO, but then maybe for other you know tasks, you can get away with a cheaper model.
Uh a hot tip is open router actually often has free models.
Um, so there's been this Hunter Alpha model was free for a couple of weeks, the step flash free.
So if you have work that can be accomplished by a free model, right, which would be sort of uh, you know, not all work can, you can use it and get free tokens.
Um, also the pie coding engine, whatever.
So it basically depends on some of these existing agents um to to operate.
This one's actually gonna run on my local machine.
So um we'll just go next.
And and do you recommend you know doing local or how should people think about this?
Yeah, so right now paperclip mostly works when you run it locally.
We're working on doing a cloud deployment.
So either you can self-host it yourself because it is open source, or eventually we'll provide a hosted solution for people that want to do that.
Um, but I think local is really how most people are doing a lot, everything with paperclip right now.
Yeah.
Cool.
So the first thing we want to do is uh give our agent something to do.
Hire your first engineer and create a hiring plan.
So you are the CEO, you set the direction for the company, hire a founding engineer, write a hiring plan, break the roadmap into concrete tasks and start delegating work.
So you can edit this if you want.
Um, you know, maybe your business doesn't need an engineer.
Maybe you're um like doing marketing sales.
You can sort of adjust this depending on what you want, but uh you know, having a founding engineer is helpful because almost every sort of online business needs to do a bit of coding.
So we'll click next here.
Okay, we've got our company, our plan, and uh it's kicks off.
So what you have here is um along this sidebar, we've got different companies.
Paperclip is made to run as many companies as you want to.
So I'm running paperclip itself in here.
Um, I'm running Forgotten Runes from here.
I've got a couple other companies that I'm like, you know, different apps that I'm working on.
Um here we've got our new uh entry for the Moolah company.
You can see right here we've got this dashboard.
Um part of the thing with paperclip is that it will track the monthly spend and it tracks all of the work your agents do.
I mean, I built Paperclip because I was uh using Cloud Code to build my companies, and I would have 20 or 30 Cloud Code windows open all at once.
And I couldn't remember what any of them were working on.
I would set them to run over the weekend, and I come back and I had no idea what anyone did.
I couldn't remember what they were supposed to do, and they had spent all my money on all their tokens.
My budget was busted, and I didn't know what was actually accomplished.
And so Paperclip is designed to solve those problems.
It actually tracks your monthly spend that you have in tokens.
Everything that it happens is done through issues.
So right now we have this first project here and it hires our first engineer.
You know, these things sort of take a while.
Ah, here we go.
We can see we've already got our founding, uh, our hiring plan installed.
So immediate hire, founding engineer, you know, a roadmap breakdown, etc.
etc.
You know, what it actually is for this call doesn't really matter, but you could look in here, you could edit it, give it feedback, give it comments.
So what happens in paperclip is your agents um have tasks that get created, and then they work on them.
I mean, that's it's as simple as that, right?
And uh paperclip sort of orchestrates this idea that uh each agent, uh each task can only be handled by one agent at a time.
So you're not going to get this kind of uh conflict of agents stepping on top of each other.
Um okay, look here, we've got something in our inbox.
Okay.
Hire agent, our first engineer.
Uh, there's a request from our CEO to hire an engineer.
Now, as you get more comfortable with paperclip and how your agents are acting, you can um turn this off and let your agents hire agents automatically.
But for sort of these like defaults, we've said, you know, a lot of people are getting started their first time.
We want to approve this manually.
So we just approved that our CEO uh can hire his first engineer.
So is that sort of the big mindset shift with Paperclip?
Instead of you know thinking of jobs to be done, you think of hiring agents.
Yeah, I think one of the things instead of thinking about like the the details, the goal of paperclip is that you're thinking at a higher level.
Like you think of yourself as like the the board.
Or and you should be talking to the CEO and saying, here are high-level goals.
Here's the MR MRR that we want to reach, here's like what we want to achieve.
Now I'm asking you to make a plan and institute what needs to happen uh within the company.
So you can see here we've hired this engineer, and now we've got uh like five live tasks actually happening here.
So let's look in a bit more deep deeply and see what's going on.
So if we click on the issues, you can see we've got um more issues.
Um set up the scaffolding, continuous integration, do progress tracking, the user auth and onboarding, build a core daily loop, right?
So the agent right now is uh working on these things.
The engineer is.
Um, I can see right now that the engineer is actually just working on one of these.
Um so I might go in here and I can up the concurrency.
So whatever.
There's advanced settings in here where you could say, you know, run four engineers at once, and it's a little bit in the weeds, but uh so wait, going back to that, because I uh you know, I know it's the weeds, but the configuration, yeah.
Like, should the should we spend any time in here?
Sure.
How should we be thinking about this?
Yeah, so one of the key things that you want to be able to do with your agents is you need to configure them with um a bit of persona.
So the uh paperclip right now gives you a default uh persona for your CEO.
So if you look here, it says, you know, you are the CEO.
Here's how we expect you to use memory.
Um we use a memory system by default that just stores your memory in files that's that was designed.
It's it's using like the para memory system, which is like uh I think Diego Forte's invention that um this skills from Nat Eliason.
He runs the FelixBot.
Um so it it gives your your CEO a default memory.
Now, um agent memory is a really involved topic.
Um there are a lot of different choices, which I'm happy to talk about.
Um, but this is gives you a uh a simple default, and then you give it some safety considerations, right?
Don't exfiltrate my secrets.
Here are some other things that I want you to look at.
One of the key things that you want to look at is the heartbeat.
And here's the the CEO's heartbeat checklist.
So when you think about AI agents, here's a tip about using AA agents with paperclip or or anything.
Have you ever seen the movie Memento?
It's like a course.
Yeah, yeah.
So if for people who haven't, Mento the Memento Man, he wakes up every morning and he is like um in really capable, but he can't remember where he's at or where he's doing, and he has to leave himself a little notes.
Right.
Your AI agents are Memento Man.
They wake up, they know how to fight, they know how to drive, they know how to like just take care of themselves and spend money, but they don't know who they are, they don't know where they are, they don't know what they're supposed to be doing.
And so what you need to do is actually write down, uh, you know, give them little Polaroids or write tattoos on their arm on what who you are and what you're supposed to be doing.
And so the heartbeat basically means like when you wake up as an agent, what are you supposed to do?
And and this gives you these instructions.
So fetch agents me, confirm that you who you are, learn who you are, um, read today's plan, look for your assignments, check out the work, and then break it down into tasks and extract your memory, and then you're done, right?
So these are your responsibilities.
I would say that um, you know, paperclip has been out about three weeks, and we are already um improving on this on a daily basis.
You know, one of the key things that um you always have to do with your agents is you really want to set up a way to kind of evaluate the quality of the prompts that you're giving them.
And this is really like a new field that a lot of people haven't it hasn't been figured out yet.
We'll be building more tools in paperclip for helping you do that.
Um, but really how a lot of people just do it practically is when it does something you don't like, you come in here and you say, rule, like make sure you remember to set, you know, like if I if it's if it's forgetting to set like a win condition, like make sure you set like a success condition for every task and ask the developer uh to have QA review it, right?
Like I might I might be using this, and I realize he never defines what success looks like and he never asks QA to review it.
And I'll literally just like add that line in here and then save it, and then you know, typically you'll you'll get a bit better results.
Which by the way, I think is something that we should have our CEO do.
So I'm gonna ask him to hire uh a QA uh person to help review the work.
So that's another thing.
Like, like so.
This is another way that you use paperclip is whenever you have an idea for something, just ask.
The CEO knows how to use Paperclip um very, very well.
And it if you're having trouble, if you want to set up a new project, you want to set up you improve your organization, you want to make a plan, you don't you you need advice, you just ask your CEO to do it.
Um, so I'll create this this issue, let him work on that.
Another key way that you might want to configure your agent would be with skills.
So, you know, if you've tried to use uh, you know, open claw, for example.
Okay, so let me talk about open claw for example for a minute.
Open claw is insanely powerful, right?
It's such a beautiful piece of software, just taking the internet by storm.
It's really the first time that, you know, if Chat GPT was the first time people realized that AI could talk, uh OpenClaw was the first time people realized AI could uh act, like that you could actually have AI act on your behalf.
I would say that like paperclip is is aiming to be the third um moment where you realize AI can do real work that you're accountable for, but that's the future.
Like with OpenClaw, one of the things that's amazing about it is that it can just do so much for you automatically.
But the problem that people run into is like if if you use OpenClaw for two or three or four weeks, you start to realize that it kind of like falls apart.
You don't really know what it's doing, you don't really know what it can do, it breaks and you don't know how to fix it.
And so paperclip kind of paperclip can use open claw as an agent, but paperclip is designed to give you a bit more accountability into what everyone's doing.
You can break your agents up into different um personas, and you can also give them different skills.sh.
Maybe not the best way, but it's one of the most popular.
Have you used this before?
Yeah.
I my my question here is how do you know you're not installing skills that are you know have bad stuff in it?
It's a problem, malicious stuff.
Yeah, it's it's a it's a real problem and it's something you have to be careful with.
I don't think anyone solved that.
Um of the things that skills.sh has is they do have um some degree of security audits.
Yeah.
So they have um these these badges.
So I think that that's that's as best as you can do, probably for now.
And I mean, you can just because it has a lot of GitHub stars doesn't mean it's you know a hundred percent secure, but it does it does give you directional kind of it's a data point, right?
If if it has if the remotion, you know, skill has a hundred and plus thousand stars, for example, chances are it's likely that there's value there.
That's right.
That's right.
So, what we can do if we wanted to, if we did want to make a video about this, right?
We can uh copy this here and we can go to paperclip.
There's a couple things that you could do.
You can um your skills are organized by uh company.
So we should be able to paste this here, or if you can't remember that, you can just ask your CEO, like add the remotion skill or whatever.
But you know, we don't need to do that right here.
We can just click add.
Um, yeah, there we go.
So we've now we've got the remotion skill installed into our company.
Okay.
And um this actually keeps track of um, like you can check for updates if the skill gets updated, etc.
etc.
You know, something that I might often do, like I might do is I might say, you know, hire a video editor and give them the remotion skill, and I would paste the URL.
And the CEO knows if you sign the CEO, he knows how to do this.
Um for the sake of demo, we'll just wait because we don't need to do that this second, but I'm just telling you that's that's that that's how you use paperclip, is just ask the CEO to do things for you.
So I have a question, I have a question about that specifically.
So, you know, the remotion skill, you know, I've used it and I've gotten sometimes I've gotten good results, and sometimes I've gotten bad results.
And the way I've gotten good results, the best possible results is giving it the most possible context, the most possible references.
Um my question is, you know, if I'm gonna hire a video editor and give them the remotion skill, how do I ensure that this is the you know a top 1% video editor using paperclip?
Mm-hmm.
So you you can never get around the idea that you have to provide that context.
Ultimately, like paperclip is not going to um on its own write that context for you.
That said, it does have tools that can help.
So when you have issues, you can have them.
Oh, we can hire our QA agent.
Um in your issues, we do have documents, and we're going to add features to do a better job at like organizing the documents, organizing the artifacts that you have within paperclip.
We'll do that.
But of course, your agents are able to access um pages anywhere you want.
So, for example, on the paperclip website, um, I have a brand guide.
Yeah, the brand identity.
So when we're asking this question, which is like, how do I make sure that my agent makes a video that's good?
One piece of that is like, do you have a brand guide yet?
Um, and you can ask your agent to do this, right?
So I would say for kind of Moolah, we haven't necessarily gotten there yet, right?
Our agents are still kind of working.
But eventually what you would do is you would create an issue.
Create me a bank brand guide, and it would give you the URL and you would look at it.
Um then the other part would be is I what might say, um, well, why don't we do this, right?
Let's say um uh let's plan uh 60 second remotion video um about Moolah showing the key pitch um that we could share on Twitter.
And we'll sign this to the CEO for now because we don't have a CMO, but maybe we should.
Maybe it should be in another project, but whatever, we'll we'll get there.
So um I would say make a plan for this, don't uh make it yet, but we need uh a video demoing the product and showing the pitch.
It needs to be animated, needs to be animated and pretty.
Agents don't really like care about typos, so you don't have to care that much about it.
So whatever, we'll let that we'll let that run and we'll come back a bit later.
Um, one of the things you'll notice is that our monthly spend right now is zero dollars, even though we've been doing all this work.
Um, part of that is because I'm using my codex subscription or clawed code subscription.
Actually, I'm not even sure which model we're using for these.
It might be Claude.
Um, oh yeah, look at this.
Our agent, yeah.
So our our our our our CEO is using the uh Claude Opus, and it's you are able to use your subscription um as well as API credits if you want.
And that's why you're seeing here that the costs are zero.
Um it's a little bit of uh, you know, it's you're still using your kind of inference for your subscription.
But if you hooked it into something like open code or were using like pure uh paper token values, you'd get kind of real dollars here.
Okay, we've hired our video editor.
Um, and let's check and see if he was given the skills.
Yeah, so there you go.
He has the remotion best practices skills enabled.
Our CEO is still working on uh planning the video, so we'll just let him kind of kind of work.
Doesn't seem like you have the context of firing a CEO, firing an engineer, firing a QA agent.
Is that correct?
No, so yeah, you you can, yeah.
You can come in here to configuration and uh let's see.
Uh, whereas, oh, let's see here.
I mean, I hate to be that guy, but no, right here.
We we got terminate.
You can terminate, yeah.
Okay.
Well, well no, no, no, don't do it, but you know.
He has had a chance, yeah.
Yeah, give him a shot.
Give him a give him a 30-day cure period at least.
Right, yeah.
So some of the other things that you uh can do with paperclip is this idea of shareable companies.
So uh let me take a step back, which would be it is not that clear how to structure your company in a way that um operates really cleanly and creates good results, right?
Everybody who's sort of tried to one-shot um a new startup with AI, you realize like it's super fun for the first half an hour and then it just kind of falls apart.
There are a lot of new patterns that are coming out around um like agentic design patterns.
OpenAI has a has a blog post where they call it harness engineering, but it's just a fancy way of saying like um ways to have your agents interact with one another that will help you get better results than just trying to quote unquote one-shot um results.
So these patterns are still being developed.
I would admit that I'm even learning them as I go.
A really basic one would just be like having a process within your organization where after the engineer creates something, he asks QA to QA it.
This is especially important for um like web apps where you need to like click on something and make sure that it actually works.
So, for example, um, you know, in here you can like at mention um the CEO or at mention a project, you know, like the onboarding project.
And this was like a really um, you know, you see it all the time, but it for whatever reason my agents had a hard time coding this.
Funny, I can even see here that the that the pills have a different height, and that really annoys me.
Um, so like what I might do is I would go into paperclip and I would actually post this screenshot here, and I would say, um the age agent mentions pill is misaligned with the like uh project mention pill.
Uh fix it, right?
And I'm gonna assign this to uh the claude coder for the paperclip app, and I'll say, you know, when you're done, pass it to QA to get eyes on it and verify it works here with a screenshot.
Now, listen, if you're gonna run a zero human company, you cannot be managing your apps at that level, right?
Like, I I'm actually acting not even as a C a board member or CEO, I'm actually acting as like a design PM or something.
And so there is kind of this like structure that needs to be built where you should have a design agent who's already looking at the website and detecting that stuff.
Um and and so that way you don't have to be um kind of micromanaging your agents, and I would say we'll get to that, right?
You basically have to make sure that you're ready to spend the tokens to do that, and you also need the avails to make sure that your designer um sort of shares your values in terms of how you want the app to work.
I would say that like even the models today, the best, like GPT 5.4 or um like uh uh opus 4.6, some of their taste is still not quite there, and and that's why um that's where a lot of the secret sauce is.
That's where you're actually gonna write your own skills, and that's where you're basically going to impart your own taste.
Like AI can do everything except know your values, and so you actually have to become more aware of your values and find out how to communicate them back.
Which is even in a pre AI era, the the concept of a good leader, of a good manager, of a good CEO, of a good founder is very much someone who can clearly communicate their values and taste, right?
That's right.
That's right.
So not much has changed except the vehicle to doing it is changed.
Instead of hiring employees, you're hiring agents.
I had a question before before we move on.
Now I had a question.
If if you you know, uh if you go back to the paperclip uh project, which by the way, it's so cool that you use paperclip to build paperclip.
I expect nothing less from you, obviously.
But you know, you're talking about you know, it's important to hire you know an agent for this and an agent for that.
How many agents do you have for the paperclip project?
Like we're talking about that many, actually.
Um so this would be the org, it's actually a little hard to see here.
Um yeah, I would say that it is growing all the time.
Um so we've got the CEO reporting to him would be a CMO, a UX designer, and a CTO.
And I use different agents for um different reasons.
I would say that the cursor coder and the claude coder would be my kind of workhorse.
They're using the frontier models on my subscriptions.
Um, then I have a QA engineer who has um both the Claude browser installed as well as there is a skill called agent browser, which is it basically gives your agent uh access to a web browser in a way that is um a little bit faster than using Chrome.
Like if you've used Chrome with Claude code before, I'm sure you've seen it like pops up a Chrome window and like takes over your computer, and if you click on it, you mess it up.
And so that's the QA.
Um, I also have am starting a Naval's engineer.
So the evals would be basically just a way saying, like, how do we start to um kind of like how do we do performance reviews on our agents and and be able to go back and reflect on what they did?
Paperclip is gonna be building tools where you can look at your past um issues, look at the feedback that you've given your agents, and your agents will be able to learn from that, right?
If you find that you're giving the same feedback over and over, we're gonna learn that, and um, you won't have to at make the same mistake twice.
We've got a UX designer who kind of has context around what I like for design.
I would say that's definitely a work in progress.
And then we're starting to build out the marketing organization, right?
Starting to build a blogger, a content strategist.
Um, you know, one of the things that we just added this week is the idea of routines.
So I would say that like man using paperclip to manage paperclip is is is not where I want it to be.
For example, we're adding new things to the code every day.
We need to have um someone who looks at all of the things that changed in code and crafts a Discord message that we can share in the Discord.
In fact, we should hook it up as a bot where it like automatically posts it in the Discord, right?
So maybe we can even set that up right now.
As I would say, uh, you know, uh create a Discord message on everything that uh that was merged into the main branch, uh or uh yeah, into the like master branch of the code today.
So is this uh is this interesting to work through?
Oh, a hundred percent.
Okay, great.
So we'll give this to I don't know, the content strategist, I suppose.
And this will be for the paperclip app.
Uh app here go.
So here's how I would actually do this.
I would say um every day we put work, uh put work into paperclip.
Um we're merging pull requests um from the community and adding features.
We want to have a Discord channel where we post the updates um in a community like in a community formatted uh like form.
Um we especially want to celebrate our community members who contribute.
So make sure you call out everyone who um added something that was merged.
We do take the weekends off sometimes.
So if there isn't anything, you you can just do nothing.
Okay.
Um read the GitHub changes for the last uh last 24 hours for this.
Okay, I know that took a little bit of a bit of time, but you know, the repo is here.
So you can find the paperclip repo here.
It's all open source.
We've got um yeah, 500 pull requests we're working on.
We've got um 30,000 stars.
So there's a lot of like motion happening in this repo that we want to be able to kind of celebrate on every day.
So uh fine.
I think this is good.
Good good enough.
Like, oh, this is what I would say is um eventually we'll post it.
Uh we'll post direct to Discord, but for now, just post in your issue.
Okay.
So I'm gonna create this routine, then from there I can do a trigger.
I can say, you know, every day at 10 a.m.
I add a trigger here.
Um, we can uh run it right now, and we can see what was actually run.
Now, this uh a routine, right, is actually almost like a template of an issue.
It's an issue that you're going to like rerun over and over and every day.
Um, but you still, with Paperclip, get that same kind of tracking where you're able to see um for this particular day when we uh decided to run this, what happened?
How many tokens did I spend?
What did the agent actually do?
What did what what did you find out?
So you so you so you get instead of just like having um some job that runs in the background that you have no tracing over, every single task that paperclip does, you can go back and look and make it better.
Is paperclip the most successful paper click paperclip project that you know of?
Um so one of the things so I guess that that goes into the the issue of like so who's using paperclip today and what are they doing?
One of the things that we're finding is like so paperclip has been out not even three weeks.
We're finding that a lot of folks that are having success with paperclip are using it to help manage AI business AI in their existing businesses, right?
As much as the tagline is like run a zero human company, we're finding people who already have um, you know, they already have a marketing firm, they're setting up agents.
Um one person who's using it has a security review company, and they used Paperclip to uh to do their own security reviews on paperclip itself, and they're using it to help manage their clients for like automated security reviews.
Um, so you know, we're we just had a um there is uh like an uh like an uh a dentist just posted this week that he was using paperclip to organize all the work that he has for a foundation that he's working on and managing his family.
So we're finding a lot of these kind of um maybe untraditional long tail uses, like even in even like blue collar.
Like I have a friend who he runs like a roofing company and they're um we're exploring using paperclip to help their like sales agents find leads right so you have this idea where um you want to find an area where there maybe recently was hail and it's an area that like where they're probably going to have insurance maybe a nicer area where they're willing to replace their roof or spend the money to do that right and so you can use paperclip to say well go gather all the satellite imagery go gather it all go gather all the hail data come up with these you know create an app where you might be able to like give your sales agents uh uh a better chance at kind of closing the deal right so to answer your question most deliberate directly I would say that like paperclip is the most uh has the most github stars but um well paperclip hasn't made any revenue yet so I would say it's the companies that are making money that are maybe more successful arguably yep cool so one of the things that we are shipping, um, probably by the time people are watching this, is the ability to import and export companies.
So uh for example, um we have I can show you this uh uh repo.
Um yeah, this'll work.
So for example, um you've probably seen uh Gary Tan has his G stack, which is um uh a set of skills that he uses where you can do um office hours like you're talking to Gary and his engineering and his style.
Um you we have um a tool which is not in the main branch, uh, but it will be um by the March 25th, where what you can actually do is is install um his company into your paperclip um or like a form of his company, which will have all of the agents, all of the skills that you need.
So um there's other uh repos like this that you've seen.
So the the superpowers um repo or agency agents, right?
This I'm sure many of you guys have seen this repo.
It has 60,000 stars, where there's some over a hundred agents, um, and you can import them all into paperclip with all the same skills.
And when it does this, it's not actually like copying the skills, it's actually referencing these remote repos so you can import any upgrades.
Um there's a uh a game studio, yeah, the Don Cheetos game studio, where you know, there's a creative director, producer, a technical director, there's all sorts of skills around creating assets.
So um ahead of time, I imported this already, and um I asked them to create a uh a bullet hell uh game in Godot inspired by Vampire Survivor, right?
And so they they start to plan the work.
Um, and I paused it because he was using too many tokens for me right now.
But uh if you want to make games, yeah, you can basically have this this massive game studio running on paperclip.
Now, the the the obvious question is like, yeah, but does it work, right?
Does this structure actually work?
And I would say that like it's just completely unproven at this point, right?
Because there's never been a piece of software like paperclip where you could go to these repos that have you know a hundred thousand GitHub stars and 300 agents, and it's like there's no evals for them.
There's no like there's no runtime.
There's no runtime other than paperclip to actually put these uh agents into an organization and test it out.
And so that's really where the future is.
If you the future of like agentic programming, is you download paperclip and you create the organization that you've actually tested that actually works.
It actually does create the TikTok marketing agency end-to-end, and then now you can share it if you want to, or just use it yourself, right?
Yeah, well, this is the sort of idea around uh yes, I can go and create hire agents from from scratch, or I can go and hire a proven team or Aqua Hire a proven team and bring them into my paperclip instance.
That's right.
That's right.
So yeah, so that's paperclip in a box.
I mean, you know, I can answer questions that you have.
I think that's that's that's where it is today.
You know, you can use any agent that you want.
Um, you uh and and really just it's open source, the community has a Discord server.
I think that like there's still a lot of rough edges, things that we wanna work out around um artifacts, having better onboarding.
We want to have a we'll add a CEO chat so that way you're not creating issues for every single thing.
You can just chat with any agent.
Um we're working especially on um my favorite feature that we're working on right now is called um maximizer mode.
And in maximizer mode, you basically don't really care that much about token spending you're saying, I wanna make sure that the CEO, the CEO makes sure someone is working all the time.
Like if I ask you to build the bullet hell game, you do whatever it takes to make sure that you have all the team that you need and that you're pressing on making it until that game is playable and you say it's completely done.
So we don't have that today in paperclip, but um give us you know uh a couple of weeks and you'll be able to use the paperclip maximizer.
When you say give us, who who's us?
Yeah, so us would be um there's myself, Dota.
Um, I also have two co-founders, uh, Devin and Scott, and then also the uh community, who is just doing an incredible job at contributing just every day.
We have so many pull requests we can barely even handle them.
And is that Devin Foley by the by the way?
Yeah, absolutely.
Yeah.
So yeah, he was at um uh Slack early on and at Figma early on, and um then also Scott Tong, who uh was head of product design at Pinterest.
Cool.
So it's not just an avatar, it's it's proven proven founders.
I know Devin from back in my days in San Francisco.
Uh I think he actually he invested in my last company.
So I do know him, and he's a great guy.
So it's people who've built startups before, yeah.
Um scaled them, and uh it's cool to see what you all have built.
You know, did you expect?
I mean, I'll end it with this.
Did you expect it to go this viral?
Um I you know, I wanted it to do well because I knew it was good and I knew it was something that I wanted, but I would say I didn't expect it to go as viral as it did.
It really struck a chord with people.
I think that like the um the big question in everyone's mind is like, will you need something like paperclip in a year from now?
Will the underlying models get good enough such that you don't need custom software?
And I think um that's an open question for everyone, really.
Like it's not just paperclip that would be that would uh succumb to that.
But I think that paperclip is built to sort of survive this this kind of um, I don't know what you want to call it, the bitter lesson, which is that the models will always kind of outpace how humans do things.
I think that like if we're going to find that AI takes um unfortunately a lot of people's jobs, you still need a piece of software that helps um manage the jobs that are left.
And you still like if if if I'm going to be able to not have 10 engineers under me, but I'm actually managing 10 AI agents or 100, you still need software that's going to help you manage the the taste and and and the organization at scale.
And so I do think that paperclip will have a bit of staying power because it's not um fixed to one agent, it's actually operating at this higher level of just what do you want to do?
And I don't know that like what do you want to do will ever really change.
Cool.
I I'm I'm watching, I think it's really interesting.
Um, you know, when when it first came out, I I hit you up right away.
Actually, you hit me up.
You're like, check this out.
And I was like, whoa, this is crazy.
And uh I'm happy you decided to come on the pod.
Um had to beg you, but you came on and uh I'm glad you did.
This has been really, really interesting.
I'll include links on where you can follow Dota, where you can sign up to Paperclip, play around.
Um, and uh thanks thanks for coming on the Startup Ideas Podcast, my friend.
Thanks for having me.
Thank you.