The AI Agent Every Company is About to Build | Vercel CEO Guillermo Rauch Transcript, AI Summary & Key Points

00:00 really important thing about open [music] claw which is soul.md. So it's like the soul of your agent that's going to help you run your company. For example, what I believe will happen in the future is that even before you build a website, you're going to build that agent [music] that's going to help you build a company. Most of the world still thinks about agents as something you prompt.

00:16 Can we sort of automate even the prompting such that the agent can be doing useful work for me while I'm not in the computer? Today I'm having a conversation with GMO Roush, the CEO of a multi-billion dollar company, Versell. And today we're talking about agents, specifically how companies are [music] using agents within their business. In this video, we talk about Verscell's internal agent that almost 1,000 people use within the company.

00:40 We also talk about whether companies need one god agent or a team of many agents. We also talk about the challenges of setting up agents right now and how to get started building agents that actually improve your business workflows. We also talk about open- source models like Kimmy K3 and a lot more. My goal with this conversation is to answer [music] the following question.

01:01 How do we as business operators, employees, and individuals use AI agents to [music] be more productive? And if you like videos like these, please consider hitting that like button and subscribing to this podcast. It helps me out a ton. Let's dive in. GMO, thank you so much for joining me on this on this episode of Agent Native. >> It's great to be here.

01:27 >> My first question to you is, you know, obviously we have all these models coming out, right? You we have Kimmy models from China, models built in the US, Claude, Fable, now Claude, Opus 5. Um, we have all these different platforms people can use. And my audience are most people are business operators. They work in a big company. They want to use agents in their business to become more efficient and to become like a better team.

01:51 Where are companies at in terms of implementing AI agents in their business? >> Yeah. When I think about we can call it the agentic revolution. Um just like any new platform that has hit the internet or the software landscape, you think about the killer apps, right? when the personal computer came out, you know, what were the killer apps? The word processor, uh, you know, um, uh, for some of us playing video games on our personal computers and things like that.

02:22 Then mobile came along, right? And, um, I think the killer app of mobile in many ways was um, you know, not only shrinking interfaces from things that we used to use and putting them in a smaller screen, but enabling entire new use cases. And I think with agents we see a similar thing. So number one clearly one of the killer apps of agents is uh building software and building software or you know what you could call coding agents happens to be a core capability of solving a number of knowledge worker tasks because when

02:58 you think about okay I'm I'm preparing a presentation for somebody you occasionally will say well we have to do some data science over here in order to then you know get a report or get some data back and put it into a slide or you'll say I'll automate a bunch of different steps and summarize some documents and then I'll put some other information into a slide and and so I think clearly one of the foundational parts of this uh new period of time where we do a lot of our work increasingly with agents is coding as a

03:28 capability and I think that's this has transformed everyone's jobs right you can think of it as a number of sort of um levels of expertise I guess when it comes to coding so there are people like myself that can do agentic engineering meaning you know I've been programming for 20 years and now if I sit down and and face a really hard engineering task I will use a coding agent to enhance my engineering then there's this new emergence of what you would call vibe coding right which is everybody building a prototype of

03:59 software or even a full stack application depending on sort of where your ambitions are and maybe even how ambitious the application itself is and so you have products like Vzero and uh lovable and things like this that are making it more um I guess they're democratizing building software or even building uh the the creative act or enhancing the creative act of coming up with new software.

04:26 I also think agents are uh one of the killer apps is what I would call the run your company better agent or um the um knowledge base plus data analysis plus um uh project management agent. the the sort of brain agent that uh sits alongside of you and disseminates knowledge, business intelligence, even day-to-day tasks like you know who should I talk to within the company that is an expert in a certain task like navigating the org chart, navigating the what is to many overwhelming amounts of information that reside in

05:07 the internal systems uh of a sort of think of this as like making the company's backend more efficient. And as I mentioned, I think coding is this omniresent capability. So to give you a concrete example from within Verscell, what we noticed pretty quickly is that um anybody that's helping a customer, anybody that's trying to close a sale, anybody that's even building new software needs to needs to ask questions about, you know, what are our customers doing?

05:42 When did they first reach out? How much um uh time do we spend with them? How much do they use our platform? How many SQS of our of Verscell does this customer use? And so this internal brain agent has sort of emerged as uh I think one of the killer apps of AI. And maybe for a lot of people this still seems foreign like what are you talking about? There's an agent that can run my company.

06:04 Uh so excited to make that more of a thing. >> It all sounds like amazing in theory, right? Like the this brain agent that everyone at a company can talk to. It kind of understands kind of the SOPs and the rules of the company, the best practices, that type of thing. And I've been trying to implement this, you know, I have a nineperson marketing team now that like helps me create content on my channels, on other channels.

06:27 And my question to you is like, you know, for me, when I use AI personally, I'm inside codeex. That's just the tool that I've been using because I think it's good for knowledge work because I can ask it to create basically any type of document or something and it'll kind of open up in the side window. But what I can't figure out personally is like how do I enable this for a team?

06:49 You know, if I were to onboard someone new and I want them to have access to my skills and but also like a lot of my skills involve my personal connections like my personal email. So they can't actually get access to that skill because there's all these like permissions that I need to keep separate, but then at oftent times I want them to be able to use the same skills that I can.

07:12 And so I'm wondering like at Verscell like are you guys kind of trying to create this internally and like how do you get across these barriers and like what is the actual interface of using agents within a team? Yeah, even if you have a team of 10 people or a team of hundreds of people like Verscell, I think the way that I think about tools like Codex is that or CHBT is they give you a taste of what AI can do.

07:37 But your job, the new job of someone that runs a company is to actually enable their workforce with agents and to work on the agent. I think the future of what you would consider to be your intellectual property at the company or your edge against competitors is the ability to create, tune, optimize and disseminate these agents internally and and and you know while you can have this sort of aha moment when you use something like Chad GBD uh maybe to give you an example of our internal agent is called V.

08:10 So anyone within Versell can go into our Slack workspace and say at V and sort of navigate their day-to-day whether it's you you give a great example. So if I need to create new content for example our marketing team needs to help u promote a new product that we worked on or communicate a product change or write an engineering blog post in in collaboration with an engineer that worked on a certain capability.

08:38 All of this goes through this V agent and this V agent has a number of skills that we continuously sort of update and improve. It has sub aents. It has sort of imagine the ability to create like a virtual uh employee team. So there is the content agent that is really good at writing marketing materials. There is the data an analysis agent. Um it we we internally call this D0ero but it's one of the it sort of think of it as like the the nexus of intelligence within our company like anytime we need to get information

09:18 about how a customer is doing or um you know how they could use more versel or things like this we have this sort of DZero agent that is connected to our data warehouse um and so the experience of using an agent actually ends up being extremely user friendly why because all you need to do is you join Verscell, you join our chat workspace and now you sort of have this omniresent intelligence that can help you.

09:45 And now you might, you know, you might go to V and say, "Hey, can you change um uh some information on the website?" And so V can still sort of coordinate with other agents. It could it could delegate a a task to codeex if it wanted to. uh if it can create a prototype with v0ero it can query versel to get information about our production systems but I think what's um what's key is enabling every company in the world to sort of deploy this brain and this intelligence and continue to sort of optimize it over time >> I

10:18 have a lot of questions based on this my first one is do you have like a team that manages V like that where okay you have a team what what does that team >> look like how big is it and like what do they do on a day-to-day basis? >> So maybe to back up I wanted to share a little bit about our product development philosophy at Verscell. Um when we have a vision of the future uh that can be informed by you know pains that our customers have or things that we notice internally could be better we try to solve that problem

10:51 ourselves first. So this idea of let's have an agent that can help with every aspect of our job sort of emerged pretty obviously like you mentioned like anyone that uses chachd notices oh it can reason but chachd doesn't have access to my internal knowledge base and customer records and the set of best practices of how we build software etc and so the inspiration was anytime you talk to somebody could there have been an agentic intelligence layer that could have gotten you that information sooner.

11:27 So that was sort of like the inkling, the inspiration for it. Next thing is how do we build this? And so Versell has built a number of agentic infrastructure services and tools, right? So we built the AI SDK that helps developers talk to any model in the world. uh we built um uh AI gateway which helps you get tokens from any model in the world at the end of the day you know what we realize is that okay if there's an agent like V I don't want it to necessarily be clawed or codeex or open weight at the end of the day the

12:03 customer doesn't matter and ideally we autonomously choose the best model for each task so we almost thought of V as a superset of all agents in the world um and so we designated a few folks to sort of like try it out and build this conversational experience. First, it started out as a support assistant and that alone was extremely useful. Why? because we are hiring new people and also in Slack we talk to a lot of our customers and so anytime that you have a question about how Verscell works, we wanted to have an at

12:37 Verscell functionality that could know anything about Versel and that itself was super super super helpful because it became sort of like this easy way of giving support to our customers. But the difference between an AI assistant and an agent is that an agent can do things for you. And so we started thinking in terms of skills and in terms of jobs to be done.

13:01 So this uh we gave it a name. So V for our internal purposes. And so we wanted to have a clear distinction between the customerf facing agent the agent we give users of versell which is adversel and the agent that runs our company. So V is sort of the shortand for this. So we created the V team. The other thing we realized in this process, and maybe this goes at the heart of your question, is it's actually pretty hard to assemble all of the tools, all of the frameworks, and all of the infrastructure to make something

13:34 like this happen and to improve it over time. And so that gave uh inspiration for us to we built V and then we shared the framework that we used to build it back to the world. We call this EVE. You might sound like we're super creative with our names. V, Eve, Verscell, but Eve is sort of the, you know, uh, Nex.js or React, what they did to the web. They made it really easy to build websites and web applications.

14:02 The thing that I think every, uh, knowledge worker, every individual, every entrepreneur will want in the future is to have an agent that they can call their own. Uh, and this is, uh, what we're helping people enable with with Eve. >> Gotcha. Yeah. I think, you know, this is something I've spent a lot of time thinking about, like how do you give the normal person the access to not only just have an agent that has a bunch of context, but to also kind of like customize it.

14:29 And I think although it feels like now that OpenClaw was kind of a fad, you know, you know, if you look at the Google trends, it's like gone way down. I do think it unlocked kind of a magic moment or there's a reason it went viral in the first place. It wasn't because there was some secret paid promos by OpenClaw. I think there was a genuine um desire for people to put an agent on a computer and let it do things for you.

14:57 >> I had a lot of epiphies uh from Open Claw that informed the development of Eve. I think you're absolutely spot on. One of those things is that OpenClaw showed how just how much a coding agent can do. back to my uh initial point like what is open claw fundamentally it's the raw intelligence of the model plus every tool at its disposal right like >> a full full access yeah >> it can write code it can run it and it can have access to everything and that's magic >> to the point where it could do things accidentally and

15:30 like I think that's I remember listening to Peter who created OpenClaw he said something like that he like asked for something and then it like gave it found an API key on his computer and it did something that he didn't even ask for. And I think that was kind of the magic moment. You know, they added like the heartbeat which was this thing that kind of like initiated it.

15:51 >> Another really important thing about uh open claw which is soul.md. So when you when you create an open claw or when you use open claw you're not just taking the offtheshelf agent that somebody else built. Clearly Claude for example, it's a great agent, but Claude is anthropic agent. It has its own set of principles and and sure they will they give you ways to customize it and whatnot, but it's not truly yours.

16:18 It doesn't have a a soul of its own, right? And so I think that was another really big unlock, which is what is the soulm file? It's just it's just literally markdown text that defines the genesis of that model. So when you create an agent with Eve, we we basically learn from that and and basically an EVE agent at its most basic is a folder with an instructions.mmd file in it.

16:48 So it's like the soul of your agent that's going to help you run your company, for example. And then the other thing that we learned is it's awesome that it can run code, write code. It has a computer for it, right? Like the the whole like Mac mini uh thing was actually quite meaningful, right? Like people realized, okay, this Asian can do anything under the sun, but it's dangerous and it needs a space.

17:16 He needs his own like thing and give the agent some space, right? like and so people bought Mac minis and and and that basically giving an agent a computer massively improves its performance, its reasoning performance and its ability to deliver outcomes for you. And so what's really fascinating is it's not too unlike hiring a knowledge worker. What is the first thing a modern firms does when they hire a human?

17:48 Here's your computer. it gave us a MacBook. It has a bunch of programs installed. It's logged into all of your key systems and so we wanted to give you that as well uh for your own agents that you build. But we wanted to build a secure and efficient environment for it to run. And so the security part is that you define the tools, the human in the loop approvals and the data access controls for anything that the agent can do.

18:16 And the other aspect of it is it doesn't assume that the agent is always running in a computer which is actually kind of uh counterintuitive. I just said an agent gets better if it has a computer but not every agent is a computer is running 24/7. And so in in in our in our lingo of the versel in in cloud world we call this serverless. The idea is that if the agent is not doing anything it can go to sleep.

18:45 Maybe another metaphor is imagine a Mac Mini that hibernates when the agent doesn't have anything to do so that he doesn't use electricity. And so because we at Verscell we run you know billions of deployments we needed a mechanism such that agents can be very very very efficiently operated and run. Um and so that's another sort of ingredient that we learned from the the open clause of the world.

19:09 Okay, if we're going to run these things at massive scale and we need to run them securely, how can we create infrastructure that enables that? >> Gotcha. That makes sense. Yeah. I think I think all of the the big AI labs who've re who are like kind of releasing a product that is an agent on a computer is trying to shake it into people. They're like this is a computer.

19:30 It has a computer and it's not easy to communicate to the average people. you know, OpenAI is struggling with that right now where they're like literally tweeting. They're like GPT work is an agent with a computer and it's not easy to convey that as you interact with a chatbot, you know, like it's like what does that even mean, you know, and I'm even I'm even struggling with it, you know, and I think, you know, and I think you can kind of divide whether you look at Anthropic or OpenAI, like you can kind of divide their

19:58 products into like how much computer access they have. It's like the chatbot doesn't have any computer. GPT work has some computer it doesn't it can't run terminal commands but then codecs can run terminal commands but you can only get it on your computer because they don't have and so I think that is actually the computer aspect of agents I think is one of the parts that makes it really confusing at this stage right now >> I agree and and my goal with uh the agents that we build in in V is that you know whether you're

20:27 an intern that just joined Verscell or you're a super experienced engineer or you're somewhere in between I don't think whether I I think that's sort of the implementation detail that the agent builder needs to know about. You need to what I want for the future is that someone that's building an agent can very carefully define governance data access control in the security model right for because agents are interacting with customer data.

20:53 So you can't just be like I don't know man it runs a computer and it has access to like all of the databases of everything. you have to be really really really thoughtful about it. That's literally our new job, right? Um and uh but whether it runs one or it runs a million computers completely inconsequential to the end user. In fact, you know, you can think of this agents as being orchestrators.

21:17 In fact, when when someone goes to our Slack and says at V, they're really talking to the orchestrating agent, the one that could delegate a task to a million computers, to one computer, maybe even no computer. You know, we have customers of Versel that have built agents that have so much usage that they figured out ways to make the computer smaller and smaller and smaller just for the sake of cost efficiency.

21:43 And so I I think the my hope for the future is that the very technical people can sort of know like oh this particular conversation with this agent resulted in all of this usage of computers and whatnot. But for the most part it's all about getting high quality outcomes, high quality analysis, high quality uh you know accurate information. Uh performance is becoming more and more of a the dog tug of town, right?

22:11 like people really care for fast models and fast execution. So that's another aspect of like how do you get your agent to be delightful. >> Okay. So let let's say for a sec I wanted to create a V agent for my team. >> Yeah. My first question with this and and this is something that I've realized talking to a lot of business owners who are like kind of know about agents and they're they're trying they they're they're confused on whether you want one agent that's like a god agent that knows everything or if you want a

22:38 team of agents that sort of like share a knowledge base because the conversation that I'm having with a lot of business owners is like well the marketing team has access to these things and the finance team like I don't even I don't even want the marketing team to know about certain finance documents. >> Totally. >> And so like that's my question is like how if I were to be creating my own V agent for my company, how do I think about that?

23:05 You know, God agent or >> Yeah. >> So first of all, I'm a user experience guy. You know, I started Versell because I was frustrated with how slow creating software was and how slow the average website and web application experience was. So I always try to work backwards on the user experience. The ideal user experience with an agent is the Star Trek computer or the Iron Man Jarvis.

23:33 It's ambient computing and I don't need to target a specific capability. That's why we have we're reasoning with agents to begin with. is like there's probably like hundreds if not thousands of internal tools that people at Versell have built that I don't even know they exist frankly there's just too much right and so when you have this intelligent agents they can act as routers v our internal EVE agent is a router so if you ask it about versel knowledge it goes to the you know capability that we have for looking up

24:10 our documentation our knowledge base etc ETA if you ask about if you need to help a customer with a support case, it has a support agent within it that has access to our support ticket infrastructure. Okay, so that answers sort of my perspective is that it's more on the god model. And maybe to give you a metaphor because I really think that what we're doing here is we're redefining how companies of the future will work.

24:37 When you join a a corporation, they might give you a corporate phone and that corporate phone is already preconfigured with your identity and with a set of applications. You have the application for the I don't know internal chat. You have the application for this and that. So I think the internal agent that helps you run the company is not not unlike that is the job of the new sort of IT department is to say what are the capabilities that we're bundling into this agent and also crucially how do we manage identity and

25:09 who gets to access what information which is also extremely businesses specific. It depends on how regulated your business is. If you're a small startup, I can believe that you know your nine person team, they all have pretty equal access to most of the information of the company. maybe two have information to the financials or or maybe the distinction I remember when I started forcell was like some of us had you know read write admin [laughter] uh and but I think most of the first 10 personel team had read access to

25:43 almost everything right um and so the job of the person that works on this foundational agent is to determine uh the the access control the tools uh um the guard rails uh the the audit trails and and and like I said, this is actually pretty hard work to do. Uh and and and why we wanted to create a framework that made that the fundamental job because you know wiring up the model, wiring up the infrastructure and all of that we can sort of customers can offload to us.

26:17 >> That makes sense. And so I yeah I guess the agent would also be able to see where the message is coming from. So it's like okay if it gets sent in this channel it'll delegate um to this sub agent or access these certain files. That makes a lot of sense. >> Totally. I just get I guess cuz what you're telling me is like so appealing. Um like being able to create your team's agent and I don't think anyone's cracked the interface for this yet.

26:39 Um and I know you guys are building a framework. You deal with a lot of developers. I guess what I'm dying for is like a way some sort of interface to understand it because even the technical people like I've even showed technical people Eve where like I'm like can you help me make sense of this and I think it's still at a stage where it's not super easy to like fully understand and so I guess yeah I just wish there was like an interface where I could go in and like set these rules.

27:06 Maybe I'm talking to an AI and it's configuring it. I I guess >> the way that most of these agents are built is that you're talking to an AI that is helping you maintain your EVE project. You'll hear me use the word file system or folder a lot. I find that it's it makes the world really easy to understand if you think it if you think about it as a hierarchy of files and folders.

27:30 So the way that a ne agent works is that you start with that instructions file that says you are the agent that helps run Riley's business. You can even have some context about who you are like uh our business isn't you know we disseminate information about AI and uh our values are transparency we're not opinionated and we love shipping things like something like that right um okay but that agent still knows nothing it's a tabula rasa it just has the raw intelligence that comes from the model and it has a a basic set

28:06 of instructions how can it do something useful for you well you talked about okay let's help the marketing team create content and let's say that one of the things that you really care about is posting uh on your blog okay so in an EVE agent the first thing you do is you can create a tools folder and you can now start exposing tools to the agent and so you can say let's say that your blog is running WordPress or some system like that now I can say to the agent now you have a tool to read didn't write blog posts to

28:41 WordPress. Okay, great. You you created that file WordPress uh.ts on on that folder and then you ship your agent. You you use the word channel also very important that this agent needs to communicate to your team in some channel. So Eve supports every channel under the sun. It can be WhatsApp, it can be Telegram, it can be Slack, it can be Microsoft >> iMessage, >> it can be iMessage.

29:06 Yes. >> Amazing. And so the next question is okay I created the agent I gave it this sort of soul I gave it access to WordPress. Now you hire an intern. [laughter] Can the intern ship any blog post that it authors together with your internal agent to prod? You probably don't want that. And so this is the job of like you at some point maybe Riley you were working on your EVE agent or someone in your team you designate as sort of the agent administrator.

29:37 You're gonna say okay if the person lives within cert a certain part of the organization we let them write directly to WordPress. Another approach that I've seen people take is that when they interact with the intern over Slack or over Telegram or whatever you have to authenticate with WordPress. So you delegate to an existing permission system that you already have.

30:02 So the EVE agent ends up being sort of the facilitator of the transaction but it doesn't have direct access to WordPress itself. Uh it it it will help you sort of draft up the content. So this is just an idea that we cooked up in this conversation. But imagine that every day you start realizing hm that's really powerful. I just unblocked my entire team to be able to draft up blog posts that go directly to WordPress.

30:25 But next time tomorrow you hear an escalation and you hear, "Hey at Riley, I just saw your blog post. It's I read your most recent blog post. It reads like complete claw slop. What do you do?" And you go you go into your team and say, "Guys, what do we just do?" We became really productive and we started shipping a lot of slop. You know what you do next?

30:46 You work on the content writing skill of your EVE agent. And so this is the meta work that we will all be doing in the future. We're not working on the blog post itself. You did not go to the intern scold at him for like hey what what do you do? You shipped a bunch of slop. You're putting that intelligence into the agent in the form of skills in the form of tools.

31:09 Uh and uh of course over time you can get more sophisticated and and uh it's not just about blog like how can we infuse the content writing capability with uh what people are saying on X about your business. >> I was going to say that like a lot of the skills that I find very useful for content ends up just being like grounding in some relevant source.

31:32 And so you can put I call them like plugins like where like there's one called scrape creators. It's some API that I found that scrapes content from certain channels. And so like before it ever writes anything or before it ever idiates an idea for YouTube or or a packaging concept like a title and thumbnail, it'll go and like look on social media and find those things.

31:56 >> Totally. >> Yeah. And that's another thing like okay so if I'm creating a V agent um yeah I'd I'd want to add certain APIs and you can add I would yeah call you can call them plugins or like how do we distinguish between plugins and skills? Can you add plugins to skills or how or are they all just skills? >> Text. >> So going back to you you got that escalation that says Riley, you just shipped you're shipping a lot of blog posts but they all they have too many m dashes.

32:24 >> And so this is what's beautiful about that idea of it's just a folder. You go into your EVE agent and in the folder skills you say contentwriting.mmd and you say this is how we write. This is what I like. This is what I don't like. Um, you also talked about I I think that the future of work will be the agent becoming a lot more proactive as well.

32:47 So, Eve can have a schedule. For example, every day at night, it reads social media. It parses keywords. It gets replies from your posts. And from that, it can do something. It can draft up new content. It can even give you a report inside of Slack. And this we actually have found to be extremely helpful at Versell. The idea that our agents proactively give us information.

33:16 So every Monday I have a I have my internal agent give me a download of what's happening across every product area. What are the key metrics that I care about? So you can have the agent be doing thinking in the background on your behalf. And I think it's not just about I think most of the world still thinks about agents as something you prompt but I think there's a lot of alpha in thinking about can we sort of automate even the prompting such that the agent can be doing useful work for me while I'm not in the computer.

33:52 >> I think one of the limitations for me and I've been able I I have a lot of automations set up that trigger an agent to do certain task and it is really useful. One thing that I'm struggling figuring out how to set up, especially at my at the team level, is to get outside things to trigger the agent, you know. Um, and there's many ways I think you could do this, but um, yeah, like do you guys have any of of that set up?

34:15 Like if some event happens totally, >> it automatically Okay. Yeah. Can you talk about that? >> So, I think events that originate in systems like Stripe, like there is a refund request, we make it really easy to connect all those systems. In fact, when we sat down and we thought about what makes it really hard to build an agent, it's actually not the proof of concept part because anybody in the world can sit down open cloud coder codeex and build an agent in the sense that like when you're prompting it, you realize

34:49 what it becomes capable of. What we talked about with open claw like the raw intelligence is already there. What's hard is securely connecting it to your systems. So we built a capability on Verscell called Verscell connect that gives your agents access to 100 plus systems but it doesn't just give them full readr everything access right away. It gives you the developer the control and that might mean that you subscribe to an event and then you send it to your agent.

35:20 You can say, "Hey, every time Stripe has a failed payment, let the agent know. Every time we get an email, let the agent know." And so you start thinking about the world in terms of events. In fact, I mentioned that a lot of our agent interactions are happening on in Slack. Slack is just another event is someone said something and the agent that gets fed into the agent's brain.

35:48 And so any any connector of this sort of repertoire of connectors can originate some kind of behavior in the agent. >> Gotcha. That makes sense. Yeah, that's just something we've been thinking about a lot. Um because you're right, everything is just an event. It's just things happening and then when something happens, if an agent can take care of it, they it should take care of it.

36:07 And I think I'm like I've automated none of that in terms of what I could possibly automate, which is really >> mental a mental model. So I mentioned that the the thing that I'm excited about with Eve is that when when I started Versel the most imminent thing that I needed to build was a website like it felt like how do I put my fingerprint in the world?

36:28 What is one of the earliest things that you do when you create a company? You register in Delaware if you're in the United States or even internationally you incorporate. You choose a name and so you register the domain name and you ship a website. even a website says like hey we're in business or welcome to the minimum viable sort of identity of your company on the internet.

36:50 What I believe will happen in the future is that even before you build a website you're going to build that agent that's going to help you build a company. The it's going to be your factory. It's going to be the the trusted partner and advisor in everything you do that's constantly learning about the trajectory of your business. And so it's extremely critical that as you sort of evolve your business, this agent gets access to more of these data streams of knowledge and information.

37:21 And everything really is an event in this world. Um, another important factor there is self-improvement. So when whenever you start a company, you're constantly learning. You're you're teaching your employees. you're helping them, you know, learn from mistakes, learn from incidents, learn from customer feedback, etc. It's going to be very important that your agent over time can improve.

37:46 And so with Eve, we thought about, okay, if there is a baseline of information that your agent has, how do you evaluate the agent? Can you write tests or can you give it exams so that you actually know that you're making forward progress as you as this agent sort of gets uh um more sophisticated and more capable over time. >> Um and so >> think of this as sort of uh even more fundamental than the dot of your of your of your company.

38:20 >> Yeah. And do you guys like put evals into Slack? Are there any ways to like evaluate whether an agent does well or doesn't do well? Like could you res like based on someone like could a employee who got a response from V could they say like oh this wasn't a good response and okay they can do that. >> Yeah. So the every response that we give on Slack has a and by the way maybe to also give kudos to the Slack team like Slack is kind of becoming like an agent operating system of sorts right because like it used to be

38:52 for messages between humans now it's humans and agents and so they have built UI that is just really easy for the developer to add right so like the thumbs up thumbs down thing super easy to add and so every EVE agent we create for example at night we can have a job that aggregates all of the negative feedback >> and proposes the next stage of self-improvement.

39:17 We can say hey >> we got five thumbs down on these answers. What are the things that the agent itself can even propose how to improve itself? Oh, I missed this. Oh, this person critiqued this part of my response or they said I hallucinated or whatnot. I do think it's very important that humans are still involved in that loop. But I think increasingly more and more of the job of get the agent getting better is also being done by the framework.

39:48 So the framework itself comes with evalu um um you know are basically test cases right when you build a web application or a website you write unit tests and you make sure that the logic is sound when you create an EVE agent you write evals also to assertain that the logic is sound but that the information it gathers is is sound and and u uh it's accurate.

40:13 There can be evals about personality. At some point we were hearing from people that our internal company agent was too verbose. It was speaking too much. Uh and so you we kind of basically gave it a better personality and and you can create evals around that as well. >> So do you do you view this like in the near future like over the next few years?

40:33 Do you think it's just going to be mostly technical people building agents for companies or do you view this as something that whether you can code or not you you'll be able to create agents for your team? So because building software is being so democratized um think of it as like again let's go back to that idea of like I'm starting a company and like the first website I built is sort of like I could have used any service on the planet drag and drop uh give me a free website with my domain name like anything like

41:02 that. And so I think >> that first building block of your agent everybody's going to be able to to create. I think over time, I mean, the whole business runs on this. Hundreds of millions of dollars of revenue are dependent on the well-being of this agent because our sales reps depend on it, our support team depends on it, I depend on it. And so you this is a very important piece of software.

41:30 And so I think it's a combination of everyone can contribute to the agent information skills critique feedback and then there is engineers that are working on the core system loop the access to data the governance security all of those pieces um that I think need to be more technically minded but I don't think that the codew writing part is as important these It's I think I would describe it as people that really understand data flows uh threat models and architecture of systems design so that they can like carefully

42:13 think about the the again the operational excellence of the agent and the security model of the agent. >> Very interesting. Yeah. Um because yeah, I think there's a lot of people, business owners, not all of them are technical, who are reaching out and they're trying to create agents. And so I'm just trying to like leave people with like a te a tangible thing that they can do like a point to a place where they can go to kind of build their first agent or build their V.

42:37 Um because I think with what I've realized with these agent tools, all of them is I we we can have conversations about it. We can talk about it. I can learn. I can use AI to like learn about it. But nothing hits like doing it. And I think that's kind like like once you do it, then you're like, "Oh, I can do that. That means I can do this thing, this thing, and this thing."

43:00 And like kind of your world opens up as you do even the most trivial things. And so, yeah, I >> recommendation there would be, you know, what I've seen give people an aha moment is create an EVE agent. Go to eve.dev, deploy your first agent, but connect it to your favorite chat medium. If you if your company works in Slack, connect it to Slack. If you like WhatsApp, connect it to WhatsApp.

43:26 and pick one boring or you know kind of pick a toil task of your business that has a system to it but it's not you know it's something that if you could automate it away you'd absolutely automate it away and write down the scale of that task. Uh, it could be, for example, something we do a lot at Verscell is we put a lot of work into drafting up our product change log.

43:59 When you go to versel.com, it says change log. Every piece of content there narrates the storytelling or evolution of our product. And in many ways, that change log is a grounding for my engineering team. How do I know if an engineer is being productive or not? or whatever like well one of the things that I do is I I measure it by have you shipped something that we can communicate to customers is an improvement to our platform.

44:28 So one change log that's about to go out maybe by the time you watch this it's already gone out is we we improved the end toend deployment process of an application or agent to versel by 7 seconds. seven seconds we've shaved off uh over a lot of infrastructure work. So when you go to verschange you're gonna find that we improved our product and we shaved down 7 seconds.

44:55 So it used to actually take a lot of work for an engineer that is in the depths of infrastructure to collaborate with a marketing team and get that thing out into the world. Because we have an agent internally, we've cut down that process into one Slack thread that the engineer creates. The agent refineses what they're telling me because, you know, engineers are sometimes so in the weeds that they struggle to communicate things in a way that is I call it contextf free.

45:27 you know, maybe they start talking about, you know, computer science or like I'm just, hey, can we boil it down to the business benefit? Simple, seven seconds. Uh, it's enabled for every customer, it's free. So, that's kind of like a little formula that I have. People want to know what's the benefit, how much does it cost, and what do I do to get it?

45:54 Mhm. >> And so that formula that I developed over many years of product marketing skill, I put into that Eve agent. And so for the listeners, think about something like that. Maybe it's like quote unquote a secret sauce of something you do really well, but takes a lot of time and you want to do more of it. And so start with that skill, connect you to a communication channel, ship it on for sale.

46:20 >> Gotcha. Okay, that makes sense. Yeah, I think um to kind of I know we're we're running up on our time here, but um what are you most excited about um in ter could be a model, it could be computer use or some browser use. Like what unlock do you think we're going to get in the next like three to six months that will make using agents way more fun or way more effective?

46:43 >> Very simple. Um cost of intelligence continuing to go down. M >> more intelligence to for more people, more variety of models. One of the great things about building with Eve and building in Verscell generally is that we give you access to every provider of models and every model in the world. >> It's model agnostic. >> Yeah, >> totally model agnostic, right?

47:05 Um and that plays into your benefit because you retain ownership of your data, of your skills. You get to choose models and you get to benefit from the competition. There is some news that's going to go out tomorrow about models getting dramatically cheaper. >> Literally tomorrow. >> Tomorrow and if you were building in this way, you're going to benefit.

47:32 Um so the other one is fast models are going to get way faster. I think we're going to start seeing what happened with the personal computing and mobile computing revolution, which is that, you know, we got the iPhone. If you were if you could travel back in time and or even pulled out the first iPhone out of a drawer, you'd be astonished at how slow it was, the refresh rate.

47:58 Like you would open an app, it would do nothing for several seconds and then slowly at maybe 10 frames per second, the application would show up in front of your eyes, >> right? >> That's where AI is at today. >> Yeah. I think for most knowledge tasks, like I just want faster, you know? I my biggest problem isn't like, oh, I wish this was better. It's just like, why did I have to wait 14 minutes for this, you know?

48:26 And like if it was 10 times faster, it it would be insane. And I feel like we're pro like >> how long do you think it'll take for the models at like a 5.6 level like um so like soul level >> days if not week. Well, I mean maybe days is the most like optimistic. Uh I I think we're literally like weeks single digit months away. >> Uh one of the data points that I can share is on the open weight and this is why I'm excited about open weight models.

48:54 The competition between the inference providers around open weight is so extreme that GLM dropped. We added it versel AI gateway. It's an incredibly good model GLM 5.2. Within days, we had a fast variant that was four times faster. There we have more providers coming online for GLM that keep raising the bar of token per second performance. >> GLM 5.2 too fast is astonishingly fast and it's only getting faster.

49:26 >> What did you think of >> Kimmy K3 is gonna happen to Kimmy? I think we're still in the early innings of that. >> What did you think of the model like in general? Like do you think it's you think it's really good? You think it's up to par with like an Opus 48? >> I think GLM 5.2 was already in that category. I think Kimmy raises the bar. I think Kimmy can do things that perhaps only you know uh fable class models could do.

49:52 Not quite in all in all of its dimensions but for example when we evaluated it for cyber security it outperformed OPUS 4.8 8 clearly um and it was almost at uh you know soul level. Soul's still at the frontier. But again, this is the beautiful thing about having choice is that depending on what you're doing, you're going to choose different price performance ratios.

50:17 Grock for fast and highly accurate. Like if I have to choose today a model that's going to be my workhorse model, that would be like the default. If I have an agent that is my Slack and needs to do a wide variety of tasks and has to do it quickly because there's another person waiting on the other side, I would absolutely go with Grog 4.5 or GLM in terms of like price performance.

50:43 >> Um, now I mentioned proactivity. What about for example at night finding opportunities in our business uh crunching data and extracting novel insights for the executive team? Well, those things I can throw more reasoning power and it can take more time. >> I might even want to take throw a consortium of models at it. Why not have Kimmy and Saul and Grock come up with three points of view and then give you the summary?

51:18 And this is why I find it so interesting, right? Like we're still in the early innings of understanding what are the principles of design and user interface engineering. But for agents, >> yeah, >> if I'm talking to an agent interactively, I want fast. If the agent is doing an asynchronous job, I want accuracy. >> Yeah. You don't care if it takes all night.

51:43 Like it it doesn't make a difference if you're Yeah. Yeah. That's true. I I didn't think about that. Um >> we're about to launch a capability in AI gateway which is um you as a developer >> or even your agent can say please do inference please like get me tokens but in batch and I don't care how long you're going to take. like you communicate. It's a little bit like putting in a buy order >> and you're not worried when it gets fulfilled, right?

52:14 Like you're just willing to wait >> and then anyone in this market can fulfill your order. >> Almost like a spot market for intelligence, right? >> That makes sense. Yeah. And uh and this is extremely exciting because you might say hey like come up with a proof or disproof the Jacobian conjecture for two dimensions and I don't really care when but spend this many tokens uh and someone at some point is going to say hey I already paid for the GPU it's connected to the internet yeah >> no one is using it let's throw some

52:51 capacity it's a little bit like uh SETI at home uh for those who remember, rent out your spare comput capacity, solve hard problems. >> Yeah, because if you get it next week, it doesn't matter. You know, you're still solving a really crazy thing. Anyway, I really appreciate uh you joining. Um I think you guys are going to do great. I one thing I didn't realize is how much business owners don't want to get locked in to a certain provider.

53:16 I mean, you know, like Claude Tag is their kind of I don't want to say it's their version of V, but it's like kind of an agent you can add to Slack. and so many people are resistant to it because they don't want to get locked into only Claude's models. Um, so I think that is something that you guys will have going for you. That's really cool. >> And it goes beyond, you know, the the model.

53:35 I think it's not about having Claude in your workspace. It's about having an intelligence of your own, >> right? >> So there's almost like an element of like baptizing your agents like this is our agent. This is our company. It's, you know, I actually liken it to the web because the web was all about I own my domain name. Mhm. >> I'm the I'm the king of my own domain.

53:55 Uh and I think we're now seeing we're living through the version of that for the intelligence age. >> 100%. Yeah, I agree. I thank you so much for coming on. This was this was a lot of fun. Let's do it sometime soon. >> Anytime, Riley. Thank you. [music]