Every Harness Will Become A Claw — Sam Bhagwat, Mastra

I'll get us started. Um, so long day of I'll get us started. Um, so long day of talks and uh, how are you all feeling? talks and uh, how are you all feeling? talks and uh, how are you all feeling? >> Cool. Yeah, good to see we still have >> Cool. Yeah, good to see we still have >> Cool. Yeah, good to see we still have some energy. You know, I know there's a some energy. You know, I know there's a some energy. You know, I know there's a lot of like evening events. Um, we've lot of like evening events. Um, we've lot of like evening events. Um, we've heard a lot about the present and I'm heard a lot about the present and I'm heard a lot about the present and I'm going to talk about the future. Um, so going to talk about the future. Um, so going to talk about the future. Um, so my talk is called every harness will my talk is called every harness will my talk is called every harness will become a claw. Um, here's a little bit become a claw. Um, here's a little bit become a claw. Um, here's a little bit about me. Um, I am the co-founder CEO of about me. Um, I am the co-founder CEO of about me. Um, I am the co-founder CEO of Mastra. We are a Typescript agent Mastra. We are a Typescript agent Mastra. We are a Typescript agent framework. Um, I am also the author of a framework. Um, I am also the author of a framework. Um, I am also the author of a book that you may have gotten a copy of book that you may have gotten a copy of book that you may have gotten a copy of either outside or at a previous event. either outside or at a previous event. either outside or at a previous event. Um, we have seen a lot of agents running Um, we have seen a lot of agents running Um, we have seen a lot of agents running in production um, over the last 18 in production um, over the last 18 in production um, over the last 18 months. And I'm not I'm saying that as months. And I'm not I'm saying that as months. And I'm not I'm saying that as kind of context for and stage setting kind of context for and stage setting kind of context for and stage setting for the thoughts and ideas that I'm for the thoughts and ideas that I'm for the thoughts and ideas that I'm about to share right now. Um and uh the about to share right now. Um and uh the about to share right now. Um and uh the thing that I'm going to say is is thing that I'm going to say is is thing that I'm going to say is is welcome to the harness era. What do I welcome to the harness era. What do I welcome to the harness era. What do I mean by the harness era? Um well u let's mean by the harness era? Um well u let's mean by the harness era? Um well u let's just talk about the types of harnesses just talk about the types of harnesses just talk about the types of harnesses that we see right now. We see local that we see right now. We see local that we see right now. We see local harnesses. Um we use them every day harnesses. Um we use them every day harnesses. Um we use them every day daily driving our our coding, right? Um daily driving our our coding, right? Um daily driving our our coding, right? Um we see cloud harnesses. Um these are we see cloud harnesses. Um these are we see cloud harnesses. Um these are both products that we can purchase as both products that we can purchase as both products that we can purchase as well as if we work and some of these uh well as if we work and some of these uh well as if we work and some of these uh companies that have built their own companies that have built their own companies that have built their own internal coding agents that live on internal coding agents that live on internal coding agents that live on Slack. Um and then of course we have the Slack. Um and then of course we have the Slack. Um and then of course we have the your friendly local uh open source your friendly local uh open source your friendly local uh open source frameworks that have some of these frameworks that have some of these frameworks that have some of these primitives and give you the the tools primitives and give you the the tools primitives and give you the the tools that you need to build your own. Um and that you need to build your own. Um and that you need to build your own. Um and that's where we that's where we fit in.

that's where we that's where we fit in. that's where we that's where we fit in. Um now let's talk about where we are Um now let's talk about where we are Um now let's talk about where we are sort of collectively as an industry um sort of collectively as an industry um sort of collectively as an industry um and how things have evolved over the and how things have evolved over the and how things have evolved over the last we'll say year to to 18 months. Um last we'll say year to to 18 months. Um last we'll say year to to 18 months. Um last year at at AI engineer we were last year at at AI engineer we were last year at at AI engineer we were talking a lot about agents. We're talking a lot about agents. We're talking a lot about agents. We're talking about the agent loop. We were talking about the agent loop. We were talking about the agent loop. We were talking about agents versus workflows. talking about agents versus workflows. talking about agents versus workflows. Um so so I want to you know there's as Um so so I want to you know there's as Um so so I want to you know there's as we're thinking about um the agentic we're thinking about um the agentic we're thinking about um the agentic spectrum I often compare it to uh spectrum I often compare it to uh spectrum I often compare it to uh self-driving as a spectrum right there self-driving as a spectrum right there self-driving as a spectrum right there are different levels of self-driving are different levels of self-driving are different levels of self-driving autonomy whether that's like lane assist autonomy whether that's like lane assist autonomy whether that's like lane assist whether that's Tesla S FSD whether whether that's Tesla S FSD whether whether that's Tesla S FSD whether that's I I'm sitting in the back of my that's I I'm sitting in the back of my that's I I'm sitting in the back of my Whimo and there's nobody behind the Whimo and there's nobody behind the Whimo and there's nobody behind the steering wheel right um there are steering wheel right um there are steering wheel right um there are various aspects of the agentic spectrum various aspects of the agentic spectrum various aspects of the agentic spectrum between LLMs agents harnesses and claws between LLMs agents harnesses and claws between LLMs agents harnesses and claws and I'm going to talk about what we've and I'm going to talk about what we've and I'm going to talk about what we've seen and where we're going. seen and where we're going. seen and where we're going. What makes an agent different than an What makes an agent different than an What makes an agent different than an LM? Hopefully, we mostly know this, but LM? Hopefully, we mostly know this, but LM? Hopefully, we mostly know this, but just as a quick refresher, right? It's just as a quick refresher, right? It's just as a quick refresher, right? It's the agent loop, its tool calls, its the agent loop, its tool calls, its the agent loop, its tool calls, its memory, it's the ability to retry failed memory, it's the ability to retry failed memory, it's the ability to retry failed tasks, it's context engineering. Um, Dex tasks, it's context engineering. Um, Dex tasks, it's context engineering. Um, Dex is a close friend and an inspiration for is a close friend and an inspiration for is a close friend and an inspiration for this uh one of the inspirations for this this uh one of the inspirations for this this uh one of the inspirations for this talk. Um, and it's agent state, right?

talk. Um, and it's agent state, right? talk. Um, and it's agent state, right? These are some things that like hey I'm These are some things that like hey I'm These are some things that like hey I'm running an agent in a loop and I can't running an agent in a loop and I can't running an agent in a loop and I can't just do this with a oneshot call uh to just do this with a oneshot call uh to just do this with a oneshot call uh to to an LLM right I didn't I've tried to to an LLM right I didn't I've tried to to an LLM right I didn't I've tried to make these qualities I don't not sure make these qualities I don't not sure make these qualities I don't not sure what the quality of taking actions is what the quality of taking actions is what the quality of taking actions is active or something so I just put action active or something so I just put action active or something so I just put action but um you know qualities here are but um you know qualities here are but um you know qualities here are starting to emerge when we move from an starting to emerge when we move from an starting to emerge when we move from an agent to a harness durability and agent to a harness durability and agent to a harness durability and doggedness um a friend of mine was doggedness um a friend of mine was doggedness um a friend of mine was referring to an agent that he was using referring to an agent that he was using referring to an agent that he was using and he called it dogged which I really and he called it dogged which I really and he called it dogged which I really like and I'm taking that for this talk, like and I'm taking that for this talk, like and I'm taking that for this talk, right? So, durability just the sheer right? So, durability just the sheer right? So, durability just the sheer quality of like being able to run not quality of like being able to run not quality of like being able to run not for minutes but for hours or days. Um, for minutes but for hours or days. Um, for minutes but for hours or days. Um, you know, what what what encompasses you know, what what what encompasses you know, what what what encompasses this? Well, sometimes it's like, hey, I this? Well, sometimes it's like, hey, I this? Well, sometimes it's like, hey, I you know, I uh lost a connection in the you know, I uh lost a connection in the you know, I uh lost a connection in the middle of the turn and uh you know, but middle of the turn and uh you know, but middle of the turn and uh you know, but I persisted the stream and so now I can I persisted the stream and so now I can I persisted the stream and so now I can resume from the place where I started, resume from the place where I started, resume from the place where I started, right? There's planning mode. We all see right? There's planning mode. We all see right? There's planning mode. We all see this in cloud code. Um parallel sub this in cloud code. Um parallel sub this in cloud code. Um parallel sub aents being able to fan out multiple aents being able to fan out multiple aents being able to fan out multiple tasks at the same time. Uh we have more tasks at the same time. Uh we have more tasks at the same time. Uh we have more affordances with a TUI and slash affordances with a TUI and slash affordances with a TUI and slash commands. We have skills. Um we don't commands. We have skills. Um we don't commands. We have skills. Um we don't have to define all our agents up front, have to define all our agents up front, have to define all our agents up front, but we can dynamically create them on but we can dynamically create them on but we can dynamically create them on the fly. This is, you know, very the fly. This is, you know, very the fly. This is, you know, very powerful. Um you can sp the the harness powerful. Um you can sp the the harness powerful. Um you can sp the the harness can spin up background bash tasks, can spin up background bash tasks, can spin up background bash tasks, right? Um it will autocompact when it right? Um it will autocompact when it right? Um it will autocompact when it runs out of the context window. Uh you runs out of the context window. Uh you runs out of the context window. Uh you know, these are all things we'll see know, these are all things we'll see know, these are all things we'll see when we use cloud code or codecs, right?

when we use cloud code or codecs, right? when we use cloud code or codecs, right? Um it persists. it will persist threads, Um it persists. it will persist threads, Um it persists. it will persist threads, right? You can resume a thread once right? You can resume a thread once right? You can resume a thread once that's you've like disconnected from that's you've like disconnected from that's you've like disconnected from later. Um, you can cue, you can steer, later. Um, you can cue, you can steer, later. Um, you can cue, you can steer, you can interrupt. You're not just you can interrupt. You're not just you can interrupt. You're not just blocked waiting on the LM. Hey, I take a blocked waiting on the LM. Hey, I take a blocked waiting on the LM. Hey, I take a turn and then you take a turn. I'm turn and then you take a turn. I'm turn and then you take a turn. I'm playing playing Civilization here and I playing playing Civilization here and I playing playing Civilization here and I can't take a turn until all the other can't take a turn until all the other can't take a turn until all the other civilizations are playing. No, I'm civilizations are playing. No, I'm civilizations are playing. No, I'm playing Starcraft. I'm playing Age of playing Starcraft. I'm playing Age of playing Starcraft. I'm playing Age of Empires. And um, right. Uh, you know, Empires. And um, right. Uh, you know, Empires. And um, right. Uh, you know, session long um tool approval. So it's session long um tool approval. So it's session long um tool approval. So it's not just like yeah I approved this not just like yeah I approved this not just like yeah I approved this specific tool call but yeah you can run specific tool call but yeah you can run specific tool call but yeah you can run all instances of rmrf for slash right all instances of rmrf for slash right all instances of rmrf for slash right that you see in the session even though that you see in the session even though that you see in the session even though the first one will probably wipe your the first one will probably wipe your the first one will probably wipe your machine. Um okay so there there's like machine. Um okay so there there's like machine. Um okay so there there's like you know there's a um there's a few you know there's a um there's a few you know there's a um there's a few steps here and I'm I'm I'm about halfway steps here and I'm I'm I'm about halfway steps here and I'm I'm I'm about halfway through these and then afterwards we're through these and then afterwards we're through these and then afterwards we're going to talk about what it means and going to talk about what it means and going to talk about what it means and this is kind of a in between step. I this is kind of a in between step. I this is kind of a in between step. I think this is something we've seen over think this is something we've seen over think this is something we've seen over the last really 3 months. Um, and I the last really 3 months. Um, and I the last really 3 months. Um, and I think we're all still starting to think we're all still starting to think we're all still starting to grapple with what it means, which is grapple with what it means, which is grapple with what it means, which is this movement from a local harness to a this movement from a local harness to a this movement from a local harness to a cloud harness where the harness is cloud harness where the harness is cloud harness where the harness is always on. What do I mean by a harness always on. What do I mean by a harness always on. What do I mean by a harness that is always on? Well, that is always on? Well, that is always on? Well, you might be talking to it in Slack.

you might be talking to it in Slack. you might be talking to it in Slack. Maybe you're talking to it in Slack Maybe you're talking to it in Slack Maybe you're talking to it in Slack along with your colleagues, right? Um along with your colleagues, right? Um along with your colleagues, right? Um maybe you're each giving it instructions maybe you're each giving it instructions maybe you're each giving it instructions and has to figure out how to parse that and has to figure out how to parse that and has to figure out how to parse that and use user metadata. Uh maybe you have and use user metadata. Uh maybe you have and use user metadata. Uh maybe you have a mobile app. I was just uh uh you know a mobile app. I was just uh uh you know a mobile app. I was just uh uh you know maybe you have a mobile app. Maybe it maybe you have a mobile app. Maybe it maybe you have a mobile app. Maybe it tunnels to your local um to to your tunnels to your local um to to your tunnels to your local um to to your local machine. Some of these uh some local machine. Some of these uh some local machine. Some of these uh some harness mobile apps do this. Um often harness mobile apps do this. Um often harness mobile apps do this. Um often like cool. How is this running? Well, like cool. How is this running? Well, like cool. How is this running? Well, it's probably running in a cloud sandbox it's probably running in a cloud sandbox it's probably running in a cloud sandbox because it's maybe it's running locally because it's maybe it's running locally because it's maybe it's running locally in your machine. and you're tunneling in your machine. and you're tunneling in your machine. and you're tunneling into it, but maybe it's just running in into it, but maybe it's just running in into it, but maybe it's just running in a cloud in the cloud somewhere and it's a cloud in the cloud somewhere and it's a cloud in the cloud somewhere and it's got a bunch of sandboxes which enables got a bunch of sandboxes which enables got a bunch of sandboxes which enables more parallelism. You can get more um more parallelism. You can get more um more parallelism. You can get more um parallel sub aents beyond what you can parallel sub aents beyond what you can parallel sub aents beyond what you can do on your machine. This is always a do on your machine. This is always a do on your machine. This is always a trade-off and always something you get trade-off and always something you get trade-off and always something you get with distributed systems, right? You can with distributed systems, right? You can with distributed systems, right? You can do more in the cloud than you can do do more in the cloud than you can do do more in the cloud than you can do locally. You have more resources. It locally. You have more resources. It locally. You have more resources. It requires a different architecture. It's requires a different architecture. It's requires a different architecture. It's more powerful. Um and then lastly, more powerful. Um and then lastly, more powerful. Um and then lastly, you're not creating code, you know, on you're not creating code, you know, on you're not creating code, you know, on your just on your local machine or maybe your just on your local machine or maybe your just on your local machine or maybe even in a git work tree. um you're even in a git work tree. um you're even in a git work tree. um you're you're probably creating, you know, if you're probably creating, you know, if you're probably creating, you know, if you're writing code, you're probably you're writing code, you're probably you're writing code, you're probably creating a PR that that pushes right to creating a PR that that pushes right to creating a PR that that pushes right to to GitHub. Um so so you know, there's a to GitHub. Um so so you know, there's a to GitHub. Um so so you know, there's a shift, right, from from local harnesses shift, right, from from local harnesses shift, right, from from local harnesses to these always on kind of like cloud to these always on kind of like cloud to these always on kind of like cloud harnesses. We're still in the middle of harnesses. We're still in the middle of harnesses. We're still in the middle of this. You may have you may only be this. You may have you may only be this. You may have you may only be working with a local harness. You may working with a local harness. You may working with a local harness. You may have started to see cloud harnesses pop have started to see cloud harnesses pop have started to see cloud harnesses pop up in your your organization, right? You up in your your organization, right? You up in your your organization, right? You may be figuring out how to use them.

may be figuring out how to use them. may be figuring out how to use them. Your teams may be figuring out how to Your teams may be figuring out how to Your teams may be figuring out how to use them. Um, and then I want to talk use them. Um, and then I want to talk use them. Um, and then I want to talk about what the harness to claw about what the harness to claw about what the harness to claw transition is, which is imbuing these transition is, which is imbuing these transition is, which is imbuing these agents, imbuing these harnesses with agents, imbuing these harnesses with agents, imbuing these harnesses with initiative and and learning, right? What initiative and and learning, right? What initiative and and learning, right? What is initiative? Well, um, if you've used, is initiative? Well, um, if you've used, is initiative? Well, um, if you've used, let's say, a a personal assistant uh, let's say, a a personal assistant uh, let's say, a a personal assistant uh, agent, right? And that agent texts you agent, right? And that agent texts you agent, right? And that agent texts you and says, "Hey, I saw an urgent email and says, "Hey, I saw an urgent email and says, "Hey, I saw an urgent email come in. Is that email actually urgent? come in. Is that email actually urgent? come in. Is that email actually urgent? Was someone like, you know, spamming Was someone like, you know, spamming Was someone like, you know, spamming you?" you know, but like like the agent you?" you know, but like like the agent you?" you know, but like like the agent is listening um to external feed is listening um to external feed is listening um to external feed services. It has a heartbeat which means services. It has a heartbeat which means services. It has a heartbeat which means it wakes up every you know defined it wakes up every you know defined it wakes up every you know defined amount of time and um and does something amount of time and um and does something amount of time and um and does something right. Uh again like channels some uh right. Uh again like channels some uh right. Uh again like channels some uh you might be able to text it, WhatsApp you might be able to text it, WhatsApp you might be able to text it, WhatsApp it, telegram it where whatever you want. it, telegram it where whatever you want. it, telegram it where whatever you want. Um you you may persist the memory memory Um you you may persist the memory memory Um you you may persist the memory memory in a more accessible later place than in a more accessible later place than in a more accessible later place than just simple sort of like file storage, just simple sort of like file storage, just simple sort of like file storage, right? um you you might it might have a right? um you you might it might have a right? um you you might it might have a a Damon, it might have a a gateway uh a Damon, it might have a a gateway uh a Damon, it might have a a gateway uh for for sending in and receiving for for sending in and receiving for for sending in and receiving incoming outcoming requests. Uh it often incoming outcoming requests. Uh it often incoming outcoming requests. Uh it often will do continual learning, right? So will do continual learning, right? So will do continual learning, right? So this concept that you know the agent the this concept that you know the agent the this concept that you know the agent the harness runs and then you know based on harness runs and then you know based on harness runs and then you know based on the traces that it generates the traces that it generates the traces that it generates it it sort of autoimproves itself and it it sort of autoimproves itself and it it sort of autoimproves itself and there's different ways of doing this.

there's different ways of doing this. there's different ways of doing this. you see um skill automatic skill you see um skill automatic skill you see um skill automatic skill generation for example is a common one. generation for example is a common one. generation for example is a common one. Um it could modify the code driving this Um it could modify the code driving this Um it could modify the code driving this as well. Um we haven't figured out what as well. Um we haven't figured out what as well. Um we haven't figured out what the right way of doing it is yet. We're the right way of doing it is yet. We're the right way of doing it is yet. We're still exploring you know the industry is still exploring you know the industry is still exploring you know the industry is still exploring options. Um now the still exploring options. Um now the still exploring options. Um now the reason that and and maybe this is like reason that and and maybe this is like reason that and and maybe this is like our unique vantage point here but you our unique vantage point here but you our unique vantage point here but you know for the last three months as a know for the last three months as a know for the last three months as a framework we've just seen this as a f as framework we've just seen this as a f as framework we've just seen this as a f as the future. And so we furiously looked the future. And so we furiously looked the future. And so we furiously looked at the the you know the features that at the the you know the features that at the the you know the features that you know openclaw have that Hermes agent you know openclaw have that Hermes agent you know openclaw have that Hermes agent have and say and and we we've said like have and say and and we we've said like have and say and and we we've said like look you know a lot of people a lot of look you know a lot of people a lot of look you know a lot of people a lot of folks want these features but they want folks want these features but they want folks want these features but they want them with power and control. They don't them with power and control. They don't them with power and control. They don't want to just put a you know a claw on a want to just put a you know a claw on a want to just put a you know a claw on a box right they want to have more. And box right they want to have more. And box right they want to have more. And so, you know, we we've been thinking so, you know, we we've been thinking so, you know, we we've been thinking about this because about this because about this because we we you know, my I'm not doing my job we we you know, my I'm not doing my job we we you know, my I'm not doing my job well if I'm not giving everybody the well if I'm not giving everybody the well if I'm not giving everybody the tools that they need to build agents, to tools that they need to build agents, to tools that they need to build agents, to build harnesses as with the maximum build harnesses as with the maximum build harnesses as with the maximum power, right? Um so, so hopefully like power, right? Um so, so hopefully like power, right? Um so, so hopefully like again we hopefully I've walked a little again we hopefully I've walked a little again we hopefully I've walked a little bit through the step transition with bit through the step transition with bit through the step transition with actions, durability, doggedness, always actions, durability, doggedness, always actions, durability, doggedness, always on initiative, learning. Again, I I on initiative, learning. Again, I I on initiative, learning. Again, I I think I failed in like making them all think I failed in like making them all think I failed in like making them all the right tense phrase and making them the right tense phrase and making them the right tense phrase and making them all qualities, but I hope you get the all qualities, but I hope you get the all qualities, but I hope you get the idea here, right? Um, we're ascending on idea here, right? Um, we're ascending on idea here, right? Um, we're ascending on the agentic spectrum. Um, and what was a the agentic spectrum. Um, and what was a the agentic spectrum. Um, and what was a simple LLM 18 or 24 months ago is a lot simple LLM 18 or 24 months ago is a lot simple LLM 18 or 24 months ago is a lot more powerful. So, I've called this more powerful. So, I've called this more powerful. So, I've called this without sort of asking consent from without sort of asking consent from without sort of asking consent from Pete, but I've called this Steinberger's

Pete, but I've called this Steinberger's Pete, but I've called this Steinberger's law, which is I I believe every harness law, which is I I believe every harness law, which is I I believe every harness will expand until it becomes a claw. and will expand until it becomes a claw. and will expand until it becomes a claw. and and and that's a little bit um and and that's a little bit um and and that's a little bit um technological, that's a little bit technological, that's a little bit technological, that's a little bit economic, that's a little bit economic, that's a little bit economic, that's a little bit psychological. So, let me walk you psychological. So, let me walk you psychological. So, let me walk you through the reasoning here. Um the first through the reasoning here. Um the first through the reasoning here. Um the first thing that I've observed um that we've thing that I've observed um that we've thing that I've observed um that we've all observed um as a is that harnesses all observed um as a is that harnesses all observed um as a is that harnesses tend to expand. And they expand because tend to expand. And they expand because tend to expand. And they expand because we want them to expand. Um we want to DM we want them to expand. Um we want to DM we want them to expand. Um we want to DM them in Slack. We want to text them and them in Slack. We want to text them and them in Slack. We want to text them and like start overnight uh tasks before like start overnight uh tasks before like start overnight uh tasks before bedtime. We want this dopamine casino bedtime. We want this dopamine casino bedtime. We want this dopamine casino that we get when we put in tokens and that we get when we put in tokens and that we get when we put in tokens and get out code, right? Um or or whatever get out code, right? Um or or whatever get out code, right? Um or or whatever other actions, you know, um agent agents other actions, you know, um agent agents other actions, you know, um agent agents are bigger than just coding agents, but are bigger than just coding agents, but are bigger than just coding agents, but um we want our own dopamine casino. And um we want our own dopamine casino. And um we want our own dopamine casino. And this this image is thanks to uh to Dex this this image is thanks to uh to Dex this this image is thanks to uh to Dex Horty. Um Horty. Um Horty. Um but but but I see something else in our future. um I see something else in our future. um I see something else in our future. um which is that and and it's something which is that and and it's something which is that and and it's something that like I don't think we we sort of that like I don't think we we sort of that like I don't think we we sort of talk about as much uh but after this talk about as much uh but after this talk about as much uh but after this after this phase where where we're sort after this phase where where we're sort after this phase where where we're sort of making everything more and more of making everything more and more of making everything more and more powerful um there will be a shakeout um powerful um there will be a shakeout um powerful um there will be a shakeout um and and let me walk you through sort of and and let me walk you through sort of and and let me walk you through sort of uh through my reasoning here which is uh through my reasoning here which is uh through my reasoning here which is that that that in the 2010s we had these platforms we in the 2010s we had these platforms we in the 2010s we had these platforms we had Android, we had iOS. And all of a

had Android, we had iOS. And all of a had Android, we had iOS. And all of a sudden, there were all these things we sudden, there were all these things we sudden, there were all these things we could do on our phones that we could do on our phones that we could do on our phones that we previously weren't able to do. We could previously weren't able to do. We could previously weren't able to do. We could get directions, we could hail rides, um, get directions, we could hail rides, um, get directions, we could hail rides, um, we could send payments. Um, we could we could send payments. Um, we could we could send payments. Um, we could play music. Um, other ones emerged over play music. Um, other ones emerged over play music. Um, other ones emerged over the course of the decade. We could watch the course of the decade. We could watch the course of the decade. We could watch short form video. Um, we could short form video. Um, we could short form video. Um, we could [clears throat] watch long form [clears throat] watch long form [clears throat] watch long form documentaries. We could browse the documentaries. We could browse the documentaries. We could browse the internet. You know, some were kind of internet. You know, some were kind of internet. You know, some were kind of ported over from the desktop. We could ported over from the desktop. We could ported over from the desktop. We could browse the internet. Um, again, you browse the internet. Um, again, you browse the internet. Um, again, you know, some, you know, we could order know, some, you know, we could order know, some, you know, we could order food, right? Um, we could put book food, right? Um, we could put book food, right? Um, we could put book accommodations, but but if you look at accommodations, but but if you look at accommodations, but but if you look at most of these kinds of categories, and most of these kinds of categories, and most of these kinds of categories, and there are quite a few categories, there there are quite a few categories, there there are quite a few categories, there really only like one or two, you know, really only like one or two, you know, really only like one or two, you know, logos here that we use, you know, okay, logos here that we use, you know, okay, logos here that we use, you know, okay, how many maybe, you know, we use Uber how many maybe, you know, we use Uber how many maybe, you know, we use Uber and we we use Lyft, but like do anyone and we we use Lyft, but like do anyone and we we use Lyft, but like do anyone use another rideing app here, you know, use another rideing app here, you know, use another rideing app here, you know, like like like and and so when you talk to people that and and so when you talk to people that and and so when you talk to people that are smart about like consumer are smart about like consumer are smart about like consumer behavior, the the The reason they say behavior, the the The reason they say behavior, the the The reason they say that this is is because that this is is because that this is is because you only really have space in your brain you only really have space in your brain you only really have space in your brain for like a limited number of things.

for like a limited number of things. for like a limited number of things. Like if if think about something like Like if if think about something like Like if if think about something like Thumbtac. So uh Thumbtac didn't really Thumbtac. So uh Thumbtac didn't really Thumbtac. So uh Thumbtac didn't really serve a very high economic value. Like serve a very high economic value. Like serve a very high economic value. Like Airbnb like we only use it Airbnb Airbnb like we only use it Airbnb Airbnb like we only use it Airbnb occasionally, but when we use it, we occasionally, but when we use it, we occasionally, but when we use it, we like really want it. We really need it. like really want it. We really need it. like really want it. We really need it. You know, it's really valuable to us. You know, it's really valuable to us. You know, it's really valuable to us. Thumbtac like a little bit less so, Thumbtac like a little bit less so, Thumbtac like a little bit less so, right? Um and then it's also like not right? Um and then it's also like not right? Um and then it's also like not frequent, right? like maybe maybe like frequent, right? like maybe maybe like frequent, right? like maybe maybe like you know something like Door Dash or you know something like Door Dash or you know something like Door Dash or Uber people can use multiple times a Uber people can use multiple times a Uber people can use multiple times a day, right? So there's there's sort of day, right? So there's there's sort of day, right? So there's there's sort of like it either has to be very like it either has to be very like it either has to be very economically valuable or has to be very economically valuable or has to be very economically valuable or has to be very frequent. And if it's neither one of the frequent. And if it's neither one of the frequent. And if it's neither one of the two, um we just forget about it, right? two, um we just forget about it, right? two, um we just forget about it, right? It's like that, you know, college friend It's like that, you know, college friend It's like that, you know, college friend that like we haven't really talked to in that like we haven't really talked to in that like we haven't really talked to in years. It's not cuz like they weren't years. It's not cuz like they weren't years. It's not cuz like they weren't important at one point in our life, but important at one point in our life, but important at one point in our life, but like there's just nothing that maybe like there's just nothing that maybe like there's just nothing that maybe they moved to a new city or we moved to they moved to a new city or we moved to they moved to a new city or we moved to a new city or our lives, our friend a new city or our lives, our friend a new city or our lives, our friend groups, our careers diverged and all of groups, our careers diverged and all of groups, our careers diverged and all of a sudden like, you know, maybe we're a sudden like, you know, maybe we're a sudden like, you know, maybe we're calling them once a once a year or once calling them once a once a year or once calling them once a once a year or once every other year or or whatever. And every other year or or whatever. And every other year or or whatever. And you know, there's just nothing that you know, there's just nothing that you know, there's just nothing that makes them pertinent and brings them up makes them pertinent and brings them up makes them pertinent and brings them up in our our brains.

in our our brains. in our our brains. And so right now we're like really And so right now we're like really And so right now we're like really excited because there's all this energy excited because there's all this energy excited because there's all this energy and excitement and we're all excited to and excitement and we're all excited to and excitement and we're all excited to these harnesses that we're like, you these harnesses that we're like, you these harnesses that we're like, you know, putting in tokens and getting out know, putting in tokens and getting out know, putting in tokens and getting out like useful things that we all love. Um like useful things that we all love. Um like useful things that we all love. Um and and I think that in the notsodistant and and I think that in the notsodistant and and I think that in the notsodistant future there will be this very real future there will be this very real future there will be this very real shakeout and and these categories will shakeout and and these categories will shakeout and and these categories will kind of emerge and we'll realize that we kind of emerge and we'll realize that we kind of emerge and we'll realize that we only have space in our lives for so many only have space in our lives for so many only have space in our lives for so many of these claws. of these claws. of these claws. They're very powerful. We we love them They're very powerful. We we love them They're very powerful. We we love them very much. Um and so I would I would very much. Um and so I would I would very much. Um and so I would I would think about um what what what does that think about um what what what does that think about um what what what does that mean for you? So the the first thing is mean for you? So the the first thing is mean for you? So the the first thing is um the first thing is don't get um the first thing is don't get um the first thing is don't get this is the reason that like events are this is the reason that like events are this is the reason that like events are are are important that like staying up are are important that like staying up are are important that like staying up with like if the rate of change with like if the rate of change with like if the rate of change increases 3 to 4x that means you know we increases 3 to 4x that means you know we increases 3 to 4x that means you know we need to figure out what's going on even need to figure out what's going on even need to figure out what's going on even more frequently. That's why we're all more frequently. That's why we're all more frequently. That's why we're all here. Um, but if you're building an here. Um, but if you're building an here. Um, but if you're building an agent, make sure that it has the agent, make sure that it has the agent, make sure that it has the capabilities that your users need capabilities that your users need capabilities that your users need because if it doesn't and if there's because if it doesn't and if there's because if it doesn't and if there's newer things that come out, like they newer things that come out, like they newer things that come out, like they may just, you know, pick pick something may just, you know, pick pick something may just, you know, pick pick something that's more powerful because that that's that's more powerful because that that's that's more powerful because that that's happening very quickly. Um, and then happening very quickly. Um, and then happening very quickly. Um, and then keep in mind that if you if you if you keep in mind that if you if you if you keep in mind that if you if you if you aren't if you're the thing you're aren't if you're the thing you're aren't if you're the thing you're working on, um, if even if you climb up working on, um, if even if you climb up working on, um, if even if you climb up to the top of the hill, keep in mind to the top of the hill, keep in mind to the top of the hill, keep in mind there's going to be another wave of this there's going to be another wave of this there's going to be another wave of this sort of these like this this shakeout sort of these like this this shakeout sort of these like this this shakeout coming. and you know probably sometime coming. and you know probably sometime coming. and you know probably sometime in the later 2020s. Uh so um that I'm in the later 2020s. Uh so um that I'm in the later 2020s. Uh so um that I'm Sam um I'm the uh I'm the co-founder of

Sam um I'm the uh I'm the co-founder of Sam um I'm the uh I'm the co-founder of Monsterra the the TypeScript agent Monsterra the the TypeScript agent Monsterra the the TypeScript agent framework. I'm the author of Principles framework. I'm the author of Principles framework. I'm the author of Principles of Building AI agents. Hopefully you can of Building AI agents. Hopefully you can of Building AI agents. Hopefully you can get a copy of the book outside or I've get a copy of the book outside or I've get a copy of the book outside or I've got a few here. Um please stop by, say got a few here. Um please stop by, say got a few here. Um please stop by, say hi. Um it's great to see all of you. hi. Um it's great to see all of you. hi. Um it's great to see all of you. Thank you all for coming out. It's a Thank you all for coming out. It's a Thank you all for coming out. It's a real pleasure. Um enjoy the rest of the real pleasure. Um enjoy the rest of the real pleasure. Um enjoy the rest of the conference.