The Exchanges

Q And is there a fundamental technical difference between ephemeral and long running? So if you have an agent that runs for 24 hours, how does that translate in terms of sandbox requirements?

A The reason most sandbox environments do not run forever or even is because it's a technical problem. If you think about servers underneath, these servers also have to be managed, right, and maintained. And so if your sandbox can run forever, that means that you can never reset. You can never reboot the underlying server. You can't update it. You can't patch it. You can't do all these things without turning off all the sandboxes. And so the way you solve that, the easiest way to solve that is having sandboxes that have a termination time. It's like, they will only last an hour, 24. It doesn't matter. Pick your time. And then if you decide that you have to do something with the underlying machine, you just, you just flag that machine as non-schedulable. And so at some point in time, there's nothing else on that machine. You can do what, you can fix it. You can like reboot it. You can do whatever you want. Easy peasy done. Right. And so because historically most of the workloads were femoral, you didn't have to try to solve that problem because you didn't care. Like most workloads, like a Lambda function usually runs what? Five minutes, 10 minutes, like whatever. It's not a problem, right? You never had that restraint or constraint. Now that you do, to have something that can run forever, you have to be able to live migrate the sandboxes itself between the machines so that you can…

AI assessment note: “you have to be able to live migrate the sandboxes itself between the machines”

Q And is there a fundamental technical difference between ephemeral and long running? So if you have an agent that runs for 24 hours, how does that translate in terms of sandbox requirements?

A The reason most sandbox environments do not run forever or even is because it's a technical problem. If you think about servers underneath, these servers also have to be managed, right, and maintained. And so if your sandbox can run forever, that means that you can never reset. You can never reboot the underlying server. You can't update it. You can't patch it. You can't do all these things without turning off all the sandboxes. And so the way you solve that, the easiest way to solve that is having sandboxes that have a termination time. It's like, they will only last an hour, 24. It doesn't matter. Pick your time. And then if you decide that you have to do something with the underlying machine, you just, you just flag that machine as non-schedulable. And so at some point in time, there's nothing else on that machine. You can do what, you can fix it. You can like reboot it. You can do whatever you want. Easy peasy done. Right. And so because historically most of the workloads were femoral, you didn't have to try to solve that problem because you didn't care. Like most workloads, like a Lambda function usually runs what? Five minutes, 10 minutes, like whatever. It's not a problem, right? You never had that restraint or constraint. Now that you do, to have something that can run forever, you have to be able to live migrate the sandboxes itself between the machines so that you can…

AI assessment note: “you have to be able to live migrate the sandboxes itself between the machines”

Q You had a great tweet the other day where, where you were talking about like the, Actual use cases, uh, that you see as a provider of sandbox of agents. Do you want to go through this? You had a, uh, code command execution, computer use, browser use, an RL environment infra. Do you want to unpack that?

A Sure. We basically, I've made it, I, I think I've structured it better since that tweet, which is right now we have two major use cases or two types of customers consuming Daytona and different use cases. And one is on the researcher side. So it'll be, You know, RL evals benchmarks, and the other will be on what we call background agents or long running agents. And so when you think of background agents or long running agents, the most popular, those are where a human is the end consumer. The human talks to a, let's call it app layer service that has an agent in that. And then the agent will call in the sandbox. So things will be, you know, think of like Harvey or perplexity or whatever as, or lovable. As these types of background long running agents. And so they can both be, uh, sort of headless. So code and command execution and or computer browser use. So depending on what they need to do. And the same thing is on the researcher side, where it's like RL and evals and whatnot, you can do RL and evals for, you know, coding. And for that, it's basically just headless commands and command execution in there, or you can actually teach it To do things in the real world. And then it does have to fire up a, you know, Windows, a Mac, a Linux sort of desktop or a browser to go through the thing. So code and command execution and browser computer use are like two ways an agent can work…

AI assessment note: “we have two major use cases or two types of customers consuming Daytona”

Q So that's a great, um, sort of sandbox one-on-one introduction to, to, to the concept. Um, help us understand, uh, where sandboxes fit in the overall picture of this Emerging, uh, agent stack, uh, that, uh, I think everybody's trying to figure out at the same time. So there's, there's different components, there's, uh, file systems, there's orchestration, there's like, what, what, what are the different pieces?

A I, I try to think about everything. To me, it's actually quite interesting where, and we'll get this a bit later as well, it's like, a lot of this all exists in real life today. And so people are like overthinking this. I'm not saying that there, there's not going to be new, Products and solutions and technology to solve it. But it's like, it's not a new fundamental way of work. And so when you think about the agent stack itself, it's like, okay, you first have the models and the models are essentially the brain that that is what it is of equivalent to what a human's brain is sort of. So you tell it something, it replies and understands and whatnot. And then under that is like, oh, what are the tools it can do to get Things done. Right. And so that can be anything from like any of the MCP or tool calls can do. It could be the sandbox, the computer, like whatever we as humans, we also have a bunch of tools that we use everything from a hammer to a computer and everything around that. Right. Um, so all of those things exist as well. Then there is memory that exists. Can, can an agent remember these things similar to like, like, do you remember these things that are there? People that talk about orchestration of agents. It is like management. You manage people. I manage people. Managing agents is similar, is not dissimilar to managing humans. Now, what tools will you use to manage…

AI assessment note: “when you think about the agent stack itself, it's like, okay, you first have”

Q Why does it matter? Uh, how quickly you can initialize a new sandbox and how many it depends on the user and the use case.

A So if you're like a long running background agent, again, Everyone prefers it to be fast. Like no one wants to wait. Like you don't want to wait for a reply. Like everyone wants to be fast to be very clear. So the faster, the better, but generally there's an actual reason why you want it very, very, very fast. And that is, especially if you, so for, I was gonna say for a background agent, a background agent might work for like 10 minutes or an hour or whatever. So the incremental millisecond might not matter, but I still believe that from a user perspective, even a second of waiting is Kind of uncomfortable. You don't want that. And so it's a 60 or 90, maybe less so, but there you want that one, two seconds for sure under that. But the interested, the more interesting part where that is really, really important is for the researchers where when you're doing reinforcement learning, you basically have allotment of GPUs and you want the GPU is more expensive than the CPU. So the vast majority of sandboxes are CPU boxes to be clear. So they're the computers that we all work on. There might be a graphics card in there, but Basically, it's the compute, the RAM, the CPU, um, and the hard disk that's in there, and they are cheaper, or less expensive, and easier to, to get, at least for now, we'll see for how long that lasts, than GPUs, which means you want your GPUs always to be at max…

AI assessment note: “you want your GPUs always to be at maximum utilization”

Q You had a great tweet the other day where, where you were talking about like the, Actual use cases, uh, that you see as a provider of sandbox of agents. Do you want to go through this? You had a, uh, code command execution, computer use, browser use, an RL environment infra. Do you want to unpack that?

A Sure. We basically, I've made it, I, I think I've structured it better since that tweet, which is right now we have two major use cases or two types of customers consuming Daytona and different use cases. And one is on the researcher side. So it'll be, You know, RL evals benchmarks, and the other will be on what we call background agents or long running agents. And so when you think of background agents or long running agents, the most popular, those are where a human is the end consumer. The human talks to a, let's call it app layer service that has an agent in that. And then the agent will call in the sandbox. So things will be, you know, think of like Harvey or perplexity or whatever as, or lovable. As these types of background long running agents. And so they can both be, uh, sort of headless. So code and command execution and or computer browser use. So depending on what they need to do. And the same thing is on the researcher side, where it's like RL and evals and whatnot, you can do RL and evals for, you know, coding. And for that, it's basically just headless commands and command execution in there, or you can actually teach it To do things in the real world. And then it does have to fire up a, you know, Windows, a Mac, a Linux sort of desktop or a browser to go through the thing. So code and command execution and browser computer use are like two ways an agent can work…

AI assessment note: “I've structured it better since that tweet, which is right now we have two major use cases”

Q So the sandboxes are fundamentally new. Primitive. Is that, is that correct? Is it like a history of sandbox or did sandbox exist before?

A So I, I would argue, I would say that the, the person that kind of nudged, although he said he did and someone else did, but anyway, there was a company called Code Sandbox way back in the day when we used to compete with our company Code Anywhere, which also was in the, in the realm of like Replet, it's all these cloud-based IDs. And so they called it Code Sandbox because I, I believe it sounded cute. It's like a box where your code, you know, for ID, um, lived. And they were actually one of the firsts. So the team there that actually used micro VMs, did snapshotting, forking, all these things that we do use today. And so that is sort of, and this is maybe a decade ago, but the utilization or the usage from, or the value that it was giving human developers was not there. There's this whole article about like the end of local hosts and people have been talking about this for I've been talking about this for 20 years. Um, and basically developers would say, like, you'll take my local hosts, like, out of my cold dead body. But now that agents are here, local hosts no longer actually, one, you don't want that for a number of reasons. And so we're finally getting to that. So that technology and that thesis around sandboxes originally now seems to be coming to fruition.

AI assessment note: “they were actually one of the firsts... and this is maybe a decade ago”

Q Yeah, because, uh, again, to unpack it, like the, uh, open claw as, as a, as a, uh, framework and system to help an agent do all sorts of things on your computer. Basically, you want to be able to kill it if it goes rogue, and therefore you can unplug the Mac mini, uh, the way you could sort of kill a sandbox. Is that, is that?

A Kind of. So there's a, there's a couple of things that I personally thought about, and so my open claw runs on a Not a physical Mac mini essentially, but a sandboxed, um, virtual, uh, Mac mini. And the reason why I didn't, so the way people usually run these things and cloud code or open claw is usually on their own computer because it helps them, you know, organize emails, you know, search whatever documents they have and whatnot. There there's a one, there's a high security risk there because at one point we were doing our board meeting presentation. And I would ask Claw, can you go fetch the data from our bank? And then it was like, oh yeah, just log in and give me access. I'm like, Log in and give me a, no, I will not give you access. Right. Um, and so right away, fundamentally for me, that was like broke the entire thesis of it. So you give it its own machine. I personally gave it its own, like Daytona account to give it its own phone number. And the reason I have to give it its own phone number is because it has to do two FA to get into the bank. Like there's no other way except for two FA with the phone number for this particular bank. And so it has to have all these things like a employee, like a digital employee to be able to go and access these things. And so The risk now that, now that it has its own computer, it has its own account. These accounts have the limitatio…

AI assessment note: “my open claw runs on a Not a physical Mac mini essentially, but a sandboxed”

Q Yeah, because, uh, again, to unpack it, like the, uh, open claw as, as a, as a, uh, framework and system to help an agent do all sorts of things on your computer. Basically, you want to be able to kill it if it goes rogue, and therefore you can unplug the Mac mini, uh, the way you could sort of kill a sandbox. Is that, is that?

A Kind of. So there's a, there's a couple of things that I personally thought about, and so my open claw runs on a Not a physical Mac mini essentially, but a sandboxed, um, virtual, uh, Mac mini. And the reason why I didn't, so the way people usually run these things and cloud code or open claw is usually on their own computer because it helps them, you know, organize emails, you know, search whatever documents they have and whatnot. There there's a one, there's a high security risk there because at one point we were doing our board meeting presentation. And I would ask Claw, can you go fetch the data from our bank? And then it was like, oh yeah, just log in and give me access. I'm like, Log in and give me a, no, I will not give you access. Right. Um, and so right away, fundamentally for me, that was like broke the entire thesis of it. So you give it its own machine. I personally gave it its own, like Daytona account to give it its own phone number. And the reason I have to give it its own phone number is because it has to do two FA to get into the bank. Like there's no other way except for two FA with the phone number for this particular bank. And so it has to have all these things like a employee, like a digital employee to be able to go and access these things. And so The risk now that, now that it has its own computer, it has its own account. These accounts have the limitatio…

AI assessment note: “my open claw runs on a Not a physical Mac mini essentially, but a sandboxed”

Q So the sandboxes are fundamentally new. Primitive. Is that, is that correct? Is it like a history of sandbox or did sandbox exist before?

A So I, I would argue, I would say that the, the person that kind of nudged, although he said he did and someone else did, but anyway, there was a company called Code Sandbox way back in the day when we used to compete with our company Code Anywhere, which also was in the, in the realm of like Replet, it's all these cloud-based IDs. And so they called it Code Sandbox because I, I believe it sounded cute. It's like a box where your code, you know, for ID, um, lived. And they were actually one of the firsts. So the team there that actually used micro VMs, did snapshotting, forking, all these things that we do use today. And so that is sort of, and this is maybe a decade ago, but the utilization or the usage from, or the value that it was giving human developers was not there. There's this whole article about like the end of local hosts and people have been talking about this for I've been talking about this for 20 years. Um, and basically developers would say, like, you'll take my local hosts, like, out of my cold dead body. But now that agents are here, local hosts no longer actually, one, you don't want that for a number of reasons. And so we're finally getting to that. So that technology and that thesis around sandboxes originally now seems to be coming to fruition.

AI assessment note: “Code Sandbox way back in the day... they were actually one of the firsts.”

Q No, that's, uh, super interesting, right? For any, um, AI builder or AI founder. So the, the, the, PLG motion ultimately to like to create inbound is a combination of all the things. So we talk about conferences and meetups. Um, Twitter is important. Is there anything else that people should know? We talk about customer service. You mentioned no salespeople as of now.

A We have no salespeople now. Yeah. So I think like the, how do you experience the product, right? So like, like once you've seen the product, how do you experience the product? It's like your door to the product, like the website, the login, the whatever, we can fix a lot of these things to be very clear. I'm not saying we're the best at these, but there's, That. And then what are the feature sets are in there? Can I get things easily? Our SDKs are really, really, really good. Like people really like, like the ergonomics of them. So it's like really good. That part is great. And then the thing that, and this is even public on Twitter, all our case studies that we've done, and we outsource the case studies to third parties. So we're not part of this is that we reply very, very fast. And so this is a very public thing and it's something just Core to who I am and how I learned to work. Cause one of the, let's call it first real jobs I had was a system admin. So my job was like to fix the printer and computer and whatever. And so one thing that I learned and I tried to talk to my entire team is like, one thing you have to do is like, one is the first response very fast. Just the first response very fast. Like people are then calm. They know they have transferred their problem to someone else. And someone has acknowledged that. And so when they do that, they feel rested, right? And t…

AI assessment note: “how do you experience the product, right? So like, like once you've seen”

Q Do all agents need a sandbox or is that a specific category?

A My, my argument is that every agent will need at least one sandbox, sometimes more, and we get to that. Again, there are places where you don't need, and I analogize agents with humans for the most part. And again, we can have, we can do productive work without computers. And so there is, and that was the original sort of like chat bot where basically you would just talk to an agent and it would Inference. So we just think and give you value. So I don't know, you know, a lot of people use it for like emotional support or whatever. For the most part, it doesn't need a computer. It has enough data from you going back and forth, and then it can sort of understand and give you feedback, but that's a smaller subset. If we think of where all productivity gains are among the biggest verticals, healthcare, financial services, whatever, most of that is done via a computer. And so if you want agents to do all these things, then agents will need these computers to do.

AI assessment note: “My, my argument is that every agent will need at least one sandbox”

Q Do you think of, uh, customer support and customer service as all of that?

A It's all go to market. All that is go to market. And we've seen this, we've chatted about this where we've been getting users and customers just because we are so good at that. And so all of it is an experience. So if you think of any experience as a human, you go to like store, restaurant, whatever, it is the entire experience. It is from Your, the way, what is a brand? It's the perception of the, that brand itself is just a perception. And the perception is like, if you go into whatever store, pick your brand you want, the, the smell, the music, the people, the smile, that whatever you get, all of that together is the perception of that brand. And so if you think of that through the lens of a product, which might sound counterintuitive, I don't know, or not obvious to people, Like I think about that altogether. Let's say we were selling sneakers, right? Like we don't sell sneakers, but the, the, the sneaker, which we won't, man, we won't say other brands, but if you do, you can always, uh, pivot to GPU. Yeah, exactly. Like if you go to the store here in New York, it's like a beautiful store. The people are very nice. Every, everything's aesthetically pleasing and you just like enjoy that entire experience. And it's a good sneaker, right? And so you have to have that all together, and so that's how I think about this as well, which is, you know, you have to have a good product…

AI assessment note: “It's all go to market. All that is go to market.”

Q And in this all, um, uh, kind of agent harness, I guess, everything that you described cannot fault under the current, uh, concept of, of, of harness. Where do sandboxes fit long-term? Do you think a lot of this gets eventually built into the sandbox or does the sandbox remain the, the, the execution layer for it all?

A Two, two things. So if you look, there's like The sandbox itself, and again, restating, I'm saying so many times in this conversation, but if we take like an average worker in Goldman, for example, right, you have the, you have the worker, the person, which let's call it the model in this sense, you have the computer, which it logs in into, um, and the harness is a set of the way it shapes that model that it can and cannot do things and track things. So it's almost like hands sort of to speak, um, of that. A bit deeper, but basically the sandbox does support it. And so if you think of a computer, again, I'll pick on, I'll pick on Goldman. For example, I've never worked at Goldman, but it's my just assumption I've worked at a bigger company. So my assumption is that when you log into that computer, there's so much software in that computer that logs what you do, restricts what you do, make sure that you don't leak data and do these things. Again, no prior knowledge of Goldman, just assumptions on these things. And so those are the types of things that we as a sandbox provider will most certainly incorporate into that, but that harness still has its function in that which it guides the Model like, oh, I now know how to interact with this machine. Oh, I know how to do a tool call. Oh, I know how to, this is how I work with memory. This is how I change with a model. And so there's …

AI assessment note: “We don't take on the harness. That is something we pretty sure that we never do”

Q So what is it, first of all, what does a scheduler do? And then how did you go about it?

A Every cloud that exists today, Neo cloud, hyperscaler, whatever, they are all built on servers, right? Like metal machines and like historically way back in the day, we actually stacked these data, these data centers, um, me and my co-founder a long, long time ago. But they're all just like servers, like CPU, RAM, disk, they're computers, basically. Um, and on top of these computers, there is a software stack that everyone has built for their own reasons. So AWS has their software stack. Um, Cloudflare has theirs, which is very different. Everyone has, has their own on top of that. And so basically what you're trying to do when you think of these machines, these servers, basically what we do is we cut them up into small little machines. And then give you that sandbox. And so you have these small, on these big servers, you have these small little machines that can run for a minute, a second, three hours, whatever, and you don't have to worry about this. And so basically the scheduler or the orchestrator is the one that, that basically says, oh, after you send me a request, I send you to this server and turn on that sandbox, a little computer there. And then I turn it off or I kill it or I snapshot it, or it's the management of all these things there. And most of our other companies in the space basically have off the shelf schedulers. So it can be like Kubernetes or nomad or wha…

AI assessment note: “basically the scheduler or the orchestrator is the one that, that basically says”

Q And in this all, um, uh, kind of agent harness, I guess, everything that you described cannot fault under the current, uh, concept of, of, of harness. Where do sandboxes fit long-term? Do you think a lot of this gets eventually built into the sandbox or does the sandbox remain the, the, the execution layer for it all?

A Two, two things. So if you look, there's like The sandbox itself, and again, restating, I'm saying so many times in this conversation, but if we take like an average worker in Goldman, for example, right, you have the, you have the worker, the person, which let's call it the model in this sense, you have the computer, which it logs in into, um, and the harness is a set of the way it shapes that model that it can and cannot do things and track things. So it's almost like hands sort of to speak, um, of that. A bit deeper, but basically the sandbox does support it. And so if you think of a computer, again, I'll pick on, I'll pick on Goldman. For example, I've never worked at Goldman, but it's my just assumption I've worked at a bigger company. So my assumption is that when you log into that computer, there's so much software in that computer that logs what you do, restricts what you do, make sure that you don't leak data and do these things. Again, no prior knowledge of Goldman, just assumptions on these things. And so those are the types of things that we as a sandbox provider will most certainly incorporate into that, but that harness still has its function in that which it guides the Model like, oh, I now know how to interact with this machine. Oh, I know how to do a tool call. Oh, I know how to, this is how I work with memory. This is how I change with a model. And so there's …

AI assessment note: “we don't take on the harness. That is something we pretty sure that we never do”

Q No, that's, uh, super interesting, right? For any, um, AI builder or AI founder. So the, the, the, PLG motion ultimately to like to create inbound is a combination of all the things. So we talk about conferences and meetups. Um, Twitter is important. Is there anything else that people should know? We talk about customer service. You mentioned no salespeople as of now.

A We have no salespeople now. Yeah. So I think like the, how do you experience the product, right? So like, like once you've seen the product, how do you experience the product? It's like your door to the product, like the website, the login, the whatever, we can fix a lot of these things to be very clear. I'm not saying we're the best at these, but there's, That. And then what are the feature sets are in there? Can I get things easily? Our SDKs are really, really, really good. Like people really like, like the ergonomics of them. So it's like really good. That part is great. And then the thing that, and this is even public on Twitter, all our case studies that we've done, and we outsource the case studies to third parties. So we're not part of this is that we reply very, very fast. And so this is a very public thing and it's something just Core to who I am and how I learned to work. Cause one of the, let's call it first real jobs I had was a system admin. So my job was like to fix the printer and computer and whatever. And so one thing that I learned and I tried to talk to my entire team is like, one thing you have to do is like, one is the first response very fast. Just the first response very fast. Like people are then calm. They know they have transferred their problem to someone else. And someone has acknowledged that. And so when they do that, they feel rested, right? And t…

AI assessment note: “how do you experience the product, right? So like, like once you've seen the product”

Q Yeah. And there is a, a phenomenal concept of, um, stateful versus, uh, stateless. Uh, can you, can you unpack that for us?

A So that basically comes when we talk to people about what we are building, they're like, oh, doesn't this already exist in any of the hyperscalers? Right. And so the answer is no. And the answer is no is, is because everything that they were built for, which was deploying apps, they were very, they were stateless. Like if you have, Let's, let's pick any of your websites or whatever you want, web apps. You do not want that to change on the fly. You, if you, if you are the company, we'll pick like eBay because they're in this building. So they're, they came to mind. And so if you're eBay and you're an engineer there, you're like, oh, you have this new, you know, update, a button is here or does this thing. You want that state that you do. You don't want that to be changed on the fly, right? The database might change. Information might change, but you don't want the app To change. Right. And so with those things in mind, that is how people had built the hyperscalers. Like that is the fundamental architecture you came into and built on top of that. And the simplest analogy I give people is let's say you're building a truck, right? You are a factory for a truck. There's like the, the weight, the type of the engine, the chassis, um, all of that is made to very slowly, but surely Securely transport some sort of goods, right? On the other hand, you can have a sports car, which is still…

AI assessment note: “everything that they were built for, which was deploying apps, they were very, they were stateless.”