# Lauren Tan @poteto is an engineer at Cursor. Previously, she worked on the React Compiler at Meta...

Channel: UninformedInvestors
Video: https://www.youtube.com/watch?v=Zc07HI9Ppxk
Duration: 60 min
Language: English
Words: 10775
Transcript page: https://viewrankai.com/tools/youtube-transcript/Zc07HI9Ppxk

---

[0:00] Everyone, I'm Lauren, Lauren Tan. I guess not many people know my last name. Uh I am potato on Twitter. Uh potato with spelled with an E. Um and I have been at Cursor for about 5 months. Uh previously I was at Meta where I worked on the React team, uh specifically working on the React compiler, uh which was a whole lot of fun. Uh I'm still on the on the core team and and uh contributing to open source here and there. Uh so that that's really nice that they still let me do that. Uh and before Meta I was at Netflix, uh where I was uh both

[0:40] a tech lead and uh I transitioned to be be an engineering manager um for about 2 years. So I've had a I've had a lot of experience going between engineering management and being an individual contributor. Uh and I think something I've noticed actually, which is quite interesting, is that there are so many parallels with you know, management skills and how to

[1:05] like manage agents. Uh and that's actually a a big part about what I wanted to chat with you and everybody else about today. Um but yeah, that's that's me. Uh I do have some like very light slides, but uh it's not going to be um just rambling. So let me just share my screen.

[1:25] And hope that I don't leak anything. Uh

[1:33] Oh no, I need to allow permissions. No worries. All good, take your time. There's always tech tech tech trouble. Uh give me 1 second to rejoin. Yeah, go for it. I see many of you already know Lauren from the looks of the chat here. Um so yeah, it's exciting to to get a chance to chat with her uh and and go through some of her her recent work. As you guys heard, you know, a lot of recent experience from from Netflix to to Meta

[2:02] and then now over at Cursor. Uh we're going to chat a little bit about Grok Bot as well. So, uh that'll be exciting. I don't know if you guys saw that was a recent release. I think literally maybe yesterday or the day before uh from the Cursor team, which is kind of like um let's call it like agents for everyone. You can go check it out if you want and learn a little bit more about the product. But um but yeah, we'll we'll explore that a little bit today as

[2:23] well. All righty, welcome back.

[2:40] And Lauren, you're just on mute there if uh you want to hop off and mute and we'll start chatting. Yeah, sorry. No worries. It's 2026 and I still don't know how to use Zoom. [laughter] That's all good. Uh okay, so I assume you can see my screen. Yes, yeah. So yeah, today yeah, I think I think the big theme for me as I've been using agents to write code, and I'm sure a lot of you have had the same experience as well, is how do you trust it? You know, especially if you are an engineer that's been writing code for a very long time, you have

[3:13] a lot of opinions and lessons that you've learned about doing good engineering. And when you see agents just, you know, winging it and, you know, guessing, hallucinating, uh you know, confidently stating that they found the smoking gun uh for the hundredth time, uh but it's actually not the real problem, you lose a lot of trust. And when you lose when you don't have much trust in your agents, I feel like you you really can't get the

[3:40] most out of them. And for me, the parallel is like with management. Uh so, if I'm an a manager, an engineering manager of a team, and I have a bunch of, you know, I have a team of engineers uh on my team and I don't trust them, then the mode of operation I'm going to be in is going to be like micromanagement, right? I'll have to spend a lot of time looking over my reports' shoulders and checking that they're doing their work well, you know, that they're not shipping bugs to

[4:10] production. And so, I drew this chart because uh it's not it's not a very scientific chart, but like this is how I imagine myself and my journey through using agents. So, you know, like fast forward or back forward uh or fast back uh fast backwards like a year or so when, you know, nobody was or not many people were using agents to code. Uh I think you uh you get into this mode where you are in very heavily in the loop with one or

[4:47] several like a handful of agents. And you find yourself just constantly uh you know, trying to understand what your agents are doing uh and you're very very in the loop. You're watching every single output. You are sitting there prompting um and you really can't parallelize beyond that because you don't again you don't have that trust, right? You can't go to 100 agents uh like spawn 100 agents when you don't

[5:13] even trust the output of one agent. So, over the past 5 months I feel like I've really been able to uh like ascend this trust curve and now I'm at the point where uh I actually have This sounds kind of scary to say this and it it makes me sound like a slot artist, but I I

[5:33] promise I'm not. But I actually have my agents now um auto merging PRs for me. Uh which is like a wild thing to say, but um like I woke up today and there were like 20 PRs landed and I just reviewed them on main like they were already landed. And they were good. Uh so how did I get to that point? It's basically what I wanted to talk about

[5:56] today. Uh and again like yeah, feel free to jump in if you have questions, Colin. Um but uh Oh yeah, of course I got to show this this chart. Uh where uh Oh do not trust to read Someone requested to control my computer. Uh probably won't do that. Uh but yeah, so this chart I think I I I'm sharing this chart not to kind of like flex but to kind of show like the journey. Like so you can see like the curve like it sort of like inversely matches the contributions I've been able

[6:34] to land at cursor. So I joined 5 months ago. And 5 months ago like I you know, my first month I was like not very productive cuz I was you know, I was learning the code base. Didn't know what the heck was going on. And as I got more confident in in my agents uh I've really been able to kind

[6:52] of ramp up my productivity. Uh and again like yeah, like last month I shipped 1,000 PRs which is ridiculous. Uh and then this month we're only on the 12th, I'm already at like almost 800 PRs landed. Uh so the velocity is definitely high and you you I'm I'm sure a lot of you will definitely be questioning like how

[7:16] how much of this code is actually good. Um and I think yeah, like that's definitely fair to question. Um but uh yeah, I think I think if you set up your agents well, you can definitely get to a very similar level. Um and so I'm going to talk about how we do that. Uh so for me I think I'm curious like I guess calling your experience as well, but uh for me I think the most important skill that you should have in your toolbox when you

[7:52] work with agents is verification. Uh and by verification I mean the ability for an agent to actually run the code uh or take CPU traces or heap snapshots or uh you know, open an iOS simulator, whatever you know, however your application is exposed to your users it can do the same thing and uh run it for real and actually test

[8:20] and verify it'll work. Because that's the thing that really closes the loop. Uh it doesn't guarantee your agent writes good code, uh but it allows them to at least write correct code. Uh which is a big a really big step forward for being able to trust your agent. Um I will I can share one example that we have uh within

[8:45] cursor. Uh oops Where let me open this.

[8:59] Let me just make this bigger. Uh let me full screen. There you go. Uh so for the for cursors agent window, uh so this is actually an interesting story, but uh when I joined cursor 5 months ago uh they're actually uh well, I was supposed to join a different team. I was supposed to join like the cloud agents team. Uh but then since I have a lot of experience working on React and agents window is a React application uh I was uh I was asked to basically help out with uh uh, the

[9:36] agent window work. Uh, but, um, there wasn't really a lot of like skills to help me. So, I just found myself like, okay, uh, agent window is going to launch in like a week. All right, we have a really tight deadline. And, um, there was, uh, you know, I was just sitting there like, okay, I'm going to open up the performance the the Chrome DevTools and just like take a trace, look at it myself, and try to make sense of this flame graph. And keep in mind, I was just like in my first week. So, I had no idea what I was looking at. No idea what, you know, I mean, I had some

[10:09] idea, but, you know, the the code base was completely fresh to me. Uh, and I realized like my agent had no idea either, you know, like I would take a screenshot of the trial download trace, I'll send it to him and it'd be like, yeah, it kind of looks like this, you know, uh, and it would like confidently state like it's this thing, and then I try to fix that, and it turns out that's not

[10:29] the actual thing. So, this was very very slow process. And if you've ever done any like performance work yourself, or, you know, just even development with an agent where you don't have a verification skill, you are the verifier. All right, you you're the bottleneck. You you you tell your agent to do something, and then it goes off and writes some code, then you open up your, you know, local dev build, and then you start to say, oh, you know, that doesn't work. Then you got to copy paste screen, uh, you know, screenshots or console errors or whatever, uh, and then your agent like slowly kind of like uh, you know, works with that,

[11:05] and then tries to understand it, and, um, uh, fix the thing. But then you're constantly just in the loop and and being a bottleneck. So, there's really no way to parallelize. So, the control glass goes like one of the first skills I built, uh, for Cursor. Uh, and glass, by the way, is the code name for agent window that we use internally, but it's just

[11:27] Cursor, I guess. Um, and so Well, skill, uh, is I guess that that the code itself is not super interesting. Your agent can very easily make one for you. Uh where if if you're building an Electron app or a web app or even iOS uh applications, uh you can teach your agent how to use like the Chrome DevTools protocol or through uh Apple has some utilities as well for running the simulator and taking traces and controlling programmatic control

[11:58] as well. Uh so, that's really useful. Uh but one thing I want actually want to talk about is uh the this thing. Uh where is the read me? Uh so, this skill comes with this very unique feature called or not feature yet uh unique file called a feature map. And so, the story then is like I built this skill and so now the agent was able to uh actually run the agent window and

[12:30] take traces and whatnot. Uh but it had no idea what what the agent's window was. So, um you know, like someone say like oh, the the left side bar is like laggy or something like that or you know, the right side the the PR tab is not working. And the agent would just be like kind of flailing around. It would spend a lot of time trying to like look up the code and you know, where is this feature? How do I actually get to it on the UI? Which made it basically completely useless. Uh you know, like we would I would run this skill locally and you know, it would spawn a dev

[13:06] build. Uh but then it just be churning. Like it would just try to click here. It wouldn't know how to get to things. Um and it was just an awful experience. Uh so, who was putting arrows on my screen? Um so, uh yeah, this this feature map has has really useful uh because it teaches the agent how to get to all of the features that you

[13:30] have. Um and in P-SAC, the plugin that I I've made, uh if you search for P-SAC cursor on Google, you'll find it. Uh but there is a creative verification skill in that plugin where it actually helps you set up something like this for yourself. Um including the feature map, so it will actually explore the code and build up this initial feature map that tells your agent how to get to all of the different

[13:57] features that you have. Uh and this is extremely powerful because now that you have these user reports that come in, uh you you can actually map even like a vague report or even a screenshot. So we have this uh internally at Cursor where uh we have a Slack channel with, you know, lots of people giving us feedback on the agent's

[14:19] window and rock bar and whatnot. Uh and oftentimes the report is very bad. Like very low quality, like someone just put very often we get like a screenshot like and then someone just says question mark question mark question mark, like what is this? And you know, like the without this, your agent says, "I have no clue." Right? But with a feature map like this, it has a lot more context and understanding of how to actually navigate, how to get to all of the different features. Uh so like, you know, example like, I guess like the

[14:51] sidebar, like what is the sidebar? Uh you know, like all the different sub features that are present in it. Um like from the user point of view, here's where to how to get to it, all the different keyboard shortcuts. Uh even like the the what do you call it? The DOM elements or yeah, like the attributes that you use for selecting things through the CDP uh are all there. So uh again, you know, this is like really really powerful uh for for agents. And uh and a piece that ships uh that create verification skill but also a maintain verification

[15:28] skill. Uh so you can keep this up to date. Cool. Yeah, I was just going to ask how you created that. So do you mind sharing a little bit more about um that that process in the context of P stack and maybe just what P stack is for the folks who aren't familiar? Yeah, so P stack is pretty interesting because uh well, first of all, the name is kind of goofy. Like the P the P in P stack is

[15:51] like potato potato sack. Uh because I um So uh the uh there is a pretty uh famous person Garry Tan who is the CEO of Y Combinator and he's come up with this plugin called G stack. Uh Garry stack and uh funnily enough, we share the last name. We have no relation. Uh but I thought it'd be funny to kind of, you know, poke fun at Garry and make P stack my version of of of [laughter]

[16:21] of his plugin. Uh but kind of just tailor it to my own set of prac engineering practices. Uh but I honestly actually never set out to build P stack. Uh it just started with a bunch of skills. All right, like I started with that control glass skill. And then I started with another skill like called howl which I also noticed

[16:41] through like observing agents. Um so like, you know, in the early days of me, you know, trying to climb this ladder, I was like super in the loop. And I was basically nitpicking my agents to an extreme degree. I was uh like I would tell it um you know, this feature has stopped working. Here's a bug report. Like why

[17:01] isn't it working? And very often the agent would just like confidently state like, "Oh, it has to be this, right? It has to be this thing." And I noticed like when I looked at the actual tool calls, I noticed it wasn't actually reading the code that I thought should be affected. And that made me just extremely suspicious. And at that point I was just like, I'm not going to I can't trust any this agent anymore because it's just

[17:26] it's just completely hallucinating. And I think I think it's very easy to just, you know, like build up that distrust and not and kind of feel helpless. Like, you know, you don't know how to help your agents succeed. But like again, I think the the the management analogies super helpful because like imagine if you were a manager of an engineering team and you had an engineer in your team who was a really good coder, no business context whatsoever, you know, they they just you just hired them and they they onboarded,

[17:58] you know, like uh 5 seconds ago. Uh and so how do you actually teach that person to be effective? So how you do that is through skill. Uh skill being just, you know, it's just markdown, right? But you know, it it codes a lot of information, instructions, a lot of uh you can really draw out a lot of intelligence from an agent by well, some people on Twitter call it like, you know, pull the agent to a different latent space. Which is kind of like a fancy way of just saying, like since uh you know, LLMs are sort of like they

[18:31] predict the next token. Uh when you give it some high-quality tokens uh to begin with, then, you know, it it can kind of pattern match on like a higher space that's, you know, smarter. Um so that's like a very interesting model there. But yeah, I built Pstack very, very incrementally. Uh so uh started with just really observing how agents, you know, all the failed different failure modes of of that agents were having. And every time I saw that, I just, okay, I'm just going to make that a skill. All right, like stop hallucinating, actually go and search up look up the code, use a lot of

[19:09] subagents, uh and yeah, stop guessing. Yeah, that makes sense. One one kind of follow-up question here, both for myself and for a bunch of people in the chat. So, I guess it's two two parts. So, one is like, how do you maintain these skills? So, like the product changes over time. Obviously, there's a lot of people who

[19:27] are shipping against the code base. So, how do these skills get maintained? And then second to that is like, how do you know when your verification is is good enough? Like in you know, you can trust that the very verification loops that you've built are going to I guess you trust that the outputs when

[19:43] they're done. Uh, yeah, maybe I'll talk about um, I think I have something really down. Maybe I'll start with this one first. So, like how do I maintain these skills? So, um, if you're not familiar with this concept, an eval [clears throat] is essentially like a way to Uh, well, I think the mental model I have is like it's like a unit test for

[20:08] an agent. Um, and you can actually make your own evals. You don't need like a special framework for them. You can build you can you can build one depending on like, you know, how scientific and how rigorous you want to be. Uh, my screen is red. Yeah, there's a little button. Um, sorry. Are you going to like disabling the drawing or something? Like I can't see

[20:32] my screen. Yeah, sorry. If you guys could not draw on the screen, that'd be great. But, um, there's a little button in the troll. Yeah, the the little drop down. Um, how do I clear? Yeah. Okay, yeah. You got it. Perfect. Um, Continue. Yeah, so evals are a way to unit test your skills, basically. And actually in P stack, we ship

[20:57] under potato mode, there's a playbook. If you search for it, called eval playbook. Um, and it's uh, Uh, it's like not It's actually pretty pretty rigorous the way it's done. Uh, But essentially what I do is I spawn a lot of different sub agents. I have like my main coordinator agent come up with a rubric for what I want the skill to do. Um and then it spawns all these sub agents and it it creates individual directories for them which are cleverly named to not let the sub agent know that it's being evaluated because agents can actually tell and

[21:40] when they do they change their behavior. Uh but it does a bunch of stuff like that to um essentially yeah like test whether or not the skill I'm making or changing is actually doing what I think it does. Um and one of the really nice things about cursor is that we are we have we support so many different models. So you can actually eval your skill across all sorts of different models. Um and you know get a sense of how well it performs across that different matrix. Um

[22:12] especially for the models that you use. Uh so I do this a lot. Every time I I modify a skill I will run one of these like the eval playbook and make sure that you know it's actually leading to a result I want. Uh but I will say like maintaining skills is actually pretty hard. It requires I think a lot of taste and observation. So you kind of need to be very good at being a backseat driver. You know what I mean? Like if you do pair if you've ever done pair programming for example and you watch a coworker code and you just like you could probably do this

[22:49] better or you know you could do you know do you like why did you not do this? Right? You you ask a lot of questions to your coworker and it's kind of a similar thing here. You like you don't want to just be a passive observer agent. You want to be very in the driver seat in the initial stages when you're building up your own set of

[23:05] skills. Uh you know, obviously you can use something like P set, but if you're building your own set of skills, it's very I think you know, opening up the all the tool calls and like reading the code and reading all the uh the agent behavior and their thinking blocks is uh a really great way to see where they they fail, right? Like what what you know, where are they being done? And then you can go and build the skill for

[23:30] that. And then with verification, how you trust it is it's I think it's also a very similar iteration loop uh where you know, like I actually did the same process for verifying the verification skill where I actually get um So, one thing that's interesting about evals is that you can sort of hill climb them, meaning that uh your eval can produce a score, right? Uh a score that you can get your coordinator to produce, uh but also uh you can have a judge agent of a different model to uh kind of cross-reference and make sure that the

[24:08] first model is not being biased, right? The model that's judging all of the sub agents that are running the thing. Uh but you can also like hill climb. So, meaning that you can you can use like {slash} loop in cursor and you can say, "Okay, keep looping on this eval, right? Until everything is 10 out of 10." As an example. Uh and I did the same the basically the same approach with the control skill. And so, I kind of it was very it was very hands-off

[24:33] actually. Uh so, you know, I uh I kind of built I built that skill that way, like the CLI in that skill. Um and over time it's gotten really good. Uh but yeah, it was definitely not super smooth at the beginning. It required a lot of iteration. And I think there's an analogy here for me, which is um Well, I make this analogy later in a different slide on my drawing here, uh, but I think of it like uh, you know, as a as a engineer now, you're sort of more like you like maybe a manager or the analogy I like is like you're like a a chef in a

[25:14] restaurant. Uh, you you're the head chef. Uh, you're not cooking all the food yourself anymore. You have a team of cooks, right? You have a line cooks, you have a sous chef, you have you know, all these different stations. Um, and it's your job to really design the environment. You know, you you you're in charge of setting up the kitchen. You're in charge of, you know,

[25:34] like giving tasks to different people. So, um, yeah, it's a very interesting way of working. Uh, but yeah, that's that's how I basically built uh, these verification skills. Yeah, just just one follow up there and like to go try to go one layer deeper. So, are you, let's say we wanted to build um, uh, an an eval or a skill for for something and we wanted to kind of get better on its own, which is is what what I think you're suggesting. Uh, are you doing that in like a work tree, a kind of isolated with like the sub agents and and then the reviewer agents and and all

[26:11] that? Is it happening like in some type of cloud hosted environment? Like what's the the more the practical steps? If I wanted to go do this, uh, and like set up a verification system for something, what would I what would I do or where would I start? Uh, I think that uh, the best place to

[26:27] start is local because you can observe. You can definitely observe what your agents are doing. So, uh, if you're building a verification skill for yourself, uh, I would definitely start local and just have your agent bring up the application, whether it's like a CLI or uh, desktop app or whatever. And so, you can actually observe, right? You can see how the agent is interacting with the the application. You can see it, you know, how it calls like the different APIs that that allow it to interact with the

[26:59] uh the application. Um but uh for me personally, uh I have basically been kind of all in mostly all in on cloud agents because they're extremely powerful. Uh and the really powerful thing about Cursor is the the cloud agents actually. Where if you spend a little bit of time setting up your environment, these control skills, these verification skills pay a huge amount of dividend because it's not just something that makes you as a single engineer better,

[27:31] it actually levels up your whole team. Uh and even your whole company because uh you can actually start thinking about cloud agents being that thing about automations that automatically do things like uh I'll buy I get I I cannot talk about this a bit later, but I'll just kind of get into it. Uh where where, you know, for example, like I talk a lot about

[27:53] this agent we have called Benny, right? Who who uh you know, takes all of the bug reports that we get and it automatically goes off in the cloud, opens up a cloud uh it's, you know, it's desktop. It runs Cursor in its own computer and it uses the same control skills to interact with the application and try to reproduce the bug uh or the user report. All right, and this is so so powerful because at once I can immediately I I get so much

[28:22] information from this automatically. Like here in this example, you can see that uh the Benny actually reproduced the bug, uh but it's already fixed on main. So, it actually confirms that we fixed this problem already. And all I need to do is just release another build of of Cursor. Uh so, that's like huge information there that I didn't have to go off and sit with an agent, you know, and spend an hour trying to figure out, like, is

[28:47] this fixed? Is this not fixed? So, you you you gain back so much time, uh but, you know, everybody on my team benefits from this. Everybody in the company benefits from this. Uh so, definitely think that, uh you know, keeping these uh using cloud agents is super powerful. Uh but, yeah, it's like a journey. You have to trust it first, right? Before you you get to this point. And that's it goes back to what I was saying here, where, you know, it's very hard it's it's almost impossible, and I would definitely encourage you not to try to jump from, you know, like, if you're still in this

[29:22] zone, you don't want to jump to, like, I'm going to spawn a hundred a thousand or a thousand of cloud agents right now, because you're just going to waste a lot of tokens, um and it's going to be extremely expensive. Yeah, so just to kind of recap so far, basically the if we wanted to go on the journey that you've kind of gone on, it would be just start with verification, uh building some some skills and some some ways of determining that the agents are producing at least like correct code, whether like you said, whether it's good code or not is maybe a separate question, but like

[29:52] it's it's technically solving the problem by looking at, you know, stack traces, looking at, you know, the the actual behavior in the app, and so on. Um and then once we trust it locally, then we can start to think about scaling into the cloud and running more agents that are picking up signals, I guess, on their own, right? So, whether that's like a bug report that comes in or something, they can go and pick it up and solve the problem and and give us back a PR. And then maybe the last step is like auto-merging the PRs, which uh

[30:18] is where you're at. Yeah, yeah. Uh and then reviewing them on main, but um is that is that about right? Yeah, exactly. I think yeah, that's why I drew this this uh this this curve, right? Because that this this basically describes my journey of, you know, when I started barely could use a couple agents, and I

[30:36] was just observing every single thing. I think there's really no shortcut for going from here to there because this is really about your personal level of trust in agents. Right? Obviously, you know, as a as engineer you don't want to just slop code into production. So, how do you actually build up that trust? Takes um a lot of uh I guess taste and judgment. Um but uh you know, like I think plugins like Pstack definitely kind of help you

[31:05] get up to speed much quicker. Uh and so I guess it's It's like if you trust me and you trust Pstack, then in by extension you can maybe trust your agents. But if you don't trust me and I I definitely would not encourage people to blindly trust me. Uh uh you know, if you build up your own set of skills that you can obviously, you know, take a look at Pstack and kind of fork it, make it your own, improve

[31:31] the skills. Definitely encourage that. Um but for me it's really all about it just keeps coming back to trust. You know, every one of us here in this chat have a different standard for engineering. Uh and there are different things that are important for us in our code base. And uh when you are able to encode all of that into skills and you can verify that your agents actually doing them, that allows you to really kind of ascend this curve. And

[31:59] uh you know, start automating things. Uh there's another piece I wanted to talk about. Um if there's Yeah, go for it. I'll I'll think of more questions as I go, but yeah. Yeah, I think there's a third to this which I haven't talked about yet, which is kind of an interesting one, which is like refactoring and rewriting. Like one of the uh I guess most controversial one of the most controversial topics in the industry, I think, is like should you

[32:25] rewrite your app or not? Um because I think engineers are very prone to this where especially when you join a company, you come in and you see like the code base and you're like, "Man, this is Like who wrote this code? You know, it's it's terrible. I want to rewrite the whole thing. There is a very common inclination and I think a lot of, you know, before agents, um and I guess arguably even now, people will definitely discourage you from re-

[32:51] rewriting stuff. But I'm actually here to make a case for why you might want to consider it. Um because I think it really depends. Uh you know, brownfield applications I think are actually in a pretty good spot, especially if they're set up well already. Uh and like recently I've been talking to some people, but uh you know, I I I was just observing. I I just noticed this parallel, which is that a lot of big tech company problems are now

[33:23] everybody's problems. Um and the big tech company problem, you know, like when I was working at Meta, like we had this giant mono repo. We had like, I don't know, tens of thousands of engineers just, you know, like banging on their keyboards and and shipping code. And a lot of really great engineers at Meta, uh but uh I'll say like, you know, you'll be surprised that the code

[33:46] quality is actually not that good. [laughter] Um and so I often joke that like, you know, before AI slop, we had human slop. Um and so uh you know, I think a lot of big tech infra, like uh like what Meta has or Google, you know, you know, really big tech companies, are actually designed for that, where you you're sort of like, you're catering to the the you know, like uh this sounds so bad to say, but like the the least capable engineer on your team, right? You build you build frameworks, you build conventions, you build guardrails, you know, you restrict credentials so that, you know, your

[34:21] intern doesn't wipe your production database. Um there's uh you know, if you have that level of infra already, I think your agents can actually already do a very solid job. Right? Because they have the the guardrails are already in place for agents to not cause havoc or not cause too much havoc in your codebase. Um and you can always add more, you know,

[34:46] guardrails. Uh but I think like greenfield applications especially are you know, like the brand new applications are like the biggest risk in my opinion. Uh and also the greatest opportunity. Because, you know, if you vibe code a project uh a prototype um like we did for Grokbot, you know, Grokbot was spun up very very very quickly. Um and if you if you haven't heard of of Grokbot, it's like our a new

[35:11] application we just launched yesterday. Uh it's it's really cool. Uh lets you orchestrate your create like individual agents that have their own identity and you can kind of orchestrate them. It's super cool. Definitely check it out. Um but yeah, that was it's like a very it was a very greenfield application like most prototypes are.

[35:30] So, it was like vibe coded very quickly. Humans were not reading the code at all. And uh I had this tweet recently uh where I said something about organic architecture. Um Let me I'll find it. Uh but the idea is that uh when you have a completely vibe coded application, you essentially have no guardrails whatsoever. So, uh your agents when you give them a task, they will just solve it in whatever method is the

[36:03] most convenient. And over time, you get into this uh situation where you have a codebase that is spiraling out of control because you don't understand it. Uh your agents understand it, I guess, in a way, but like they've built something that is, you know, optimized for short for shortcuts. Uh and uh you know, it will you will suffer you have a lot of of issues with

[36:27] that application. Uh so, I think starting your code base with uh like very strong strains is very much needed. Uh because like when you have a code base that you can trust, right? When you have guardrails that actually help you uh uh help your agents write good code, you can get into the you know like into this part of the curve where I I where I like I I said, you know, I woke up today and I had like 20 PRs merged uh by my agents. And that's because I invested a lot lot a lot of time uh over 600 PRs I I I calculated yesterday uh

[37:09] when I refactored all of GrokBot to this new architecture that I've been building. Um and yeah, I've I've gotten to a point where I I don't really look I really don't look at the code anymore. And um I say that not just, you know, to sell you tokens, but because I you know, it it it took a lot of work to get to that point. I spent a lot of tokens to get the code base to this point where I no longer have to

[37:34] look at it. Uh but I'm very excited because you know, of the potential where, you know, it's not just it this doesn't just benefit me. It benefits everyone contributing to GrokBot. And it also empowers, you know, designers and product managers and, you know, even GTM people to add features to GrokBot. And I don't have to worry, you know, I don't have to to wake up at night in in the middle of the night and worry like, "Oh, Someone's just merged a perf regression." Right? I have a ton of constraints and CIs like it's actually very annoying to write code in in GrokBot, but like agents absorb all of

[38:11] that annoyance. Um but yeah, I'm happy to talk about what exactly that is. Um Yeah, I think one question um Yeah. before we get into the this part here is just around that element of like what your your your CI looks like or maybe some of the constraints and then also like the average PR size. I saw a question about that earlier. Just to give people a you know, kind of a a glance. It doesn't have to be like mathematically average, but just a you know, like what generally the size of the PR is um if it's only a couple lines of code

[38:42] or you know, um yeah. Uh um I think it depends. Uh let me I'm trying to do this in a way where I'm not going to like Yeah, yeah, you don't have to share the actual number. If you like the actual number just this is is fine. benchmark But like we have So okay. This is not that interesting, but uh well, fun fact is that virtualization in Grokbot and in uh Cursor is actually powered by uh Pretext, uh which is a sort of new library that someone's built. Um that's really interesting. You should You should check

[39:20] it out. But that's not really that important. Uh I think the average PR size I actually don't know I I don't know if I want to click on these. Uh I probably can, but I would say like they can range anywhere from a few hundred lines or 50 lines to like a thousand depending on what the thing is

[39:39] doing. Uh so like here I'm actually like deleting a bunch of files, so I expect that it's just this like mostly deletion. Uh but yeah, it it kind of varies. There's no like There's no like hard cap or hard limit. They're all like 50 line PRs. there's definitely no hard cap, but I I do encourage my agents to split up their

[39:57] work into multiple PRs. Uh I do that mostly because uh I like I like the idea of but I guess maybe this is much harder to do now as in the world of agents and you have like so many commits. But I like the idea that you know, the Git history is a very rich source of context. Uh and I like the I like each PR to sort of atomically describe what that small piece of thing is doing, which also makes it easier for me to revert changes and like figure out, you know, oh, I shipped a bug and it's this it's here, right? It's not in this

[40:32] 40,000 line PR where you who knows what landed in there. Uh but I I don't have a hard cap on PR size. Cool. And then um yeah, also quick question on like CI. So again, you don't have to go into like uh the screen share of like your your CI does, but just generally, would you describe what the CI kind of looks like uh or how strict

[40:54] it is? Uh yeah, so uh well, specifically for Grokbot, so Dune is the is the sort of cheeky code code name for the architecture that we've built for Grokbot. Um the CI looks pretty annoying because there's checks for everything. So, like literally, I have um uh well, if you've written any React for example, you know, you know that one of the biggest foot guns in React is use effect. Uh so, in uh Dune and in Grokbot, we've banned use effect. So, Dune is just you can the the mental model of what Dune is, uh you can kind of think of it as like Next.js for uh Electron apps and it's designed for

[41:40] agents to write uh and it's like custom for, you know, our agent for the applications. Um so, the CI checks are very like specific to that, like, you know, don't use use effect. It's it's it's banned, like, CI will fail uh and yell at you. We have like some of the more interesting ones that people might raise eyebrows is like I actually banned code comments as well, uh which is very interesting. Um but I noticed that 99% of the time agents just write code comments that kind of describe some historical thing that is

[42:14] actually totally irrelevant to the code. Um, like it will often say like, you know, "Oh, Lauren said you should never do this." and it's now in the in the code comment. I'm like, "What? Like, why what that that was I didn't say that as like a durable, you know, global rule. I just meant like your this PR sucks and you

[42:31] should change that part." Uh, agents don't really understand us that well, surprisingly. Uh, and or they kind of assume too much and they kind of do things in like very stupid ways. So, like yeah, we just ban everything everything you can imagine like the agents are bad at, we ban. Uh, so one example that we actually suffer a lot in the agents window is we have, uh, you know, you know, if you've used agents window, you've definitely seen performance issues and, you know, we're constantly trying to fix

[43:02] them. Uh, but it's like a it's a never-ending struggle because there's so many pull requests that get merged. Every any one of them could just regress performance or stability or reliability. Uh, you know, the agents window doesn't have this architecture yet. I plan to do bring this learning back there and kind of refactor everything there. Uh, but uh, it just regresses super often uh, because uh, there's there's just one example is like we have very poor um, isolation between processes. So, like on you know, on Electron, you have

[43:37] a renderer thread that renders your UI. But you also have like a main thread that you can run other code that, you know, doesn't need to block the renderer. Um, but we do a poor job of separating those things. And so, often times you just accidentally have code that gets pulled into running on the renderer thread. All right, and then all of a sudden you're competing with the the renderer that you know, that has a very If you want like 60 FPS, you have to every frame that gets drawn has to be done in 16 milliseconds. It's a very, very small, you know, deadline per

[44:09] frame. Uh if you want, you know, a very smooth product. Uh and when you start building bringing in accidentally bringing in, you know, things that are like very computationally heavy or they have a lot of IO, uh then you just get into like a lot of jank. Uh your your FPS really drops. You start uh you know, losing frames. You get long tasks that take more than 16 milliseconds and you

[44:33] just get this really choppy experience. So, all of those patterns that we've learned basically building Electron apps, we've encoded into this framework and it becomes like a hard failure. So, I literally in in Grokbot, we literally have a directory called Electron main, Electron renderer, and we have uh import uh CI, I guess, where we actually check the dependency graph to make sure you're not accidentally importing code from one

[45:02] directory to another. Uh so, that's enforced by CI, um as well as Bugbot, uh which is our which cursors um like code review tool that runs on CI. Uh you know, in our agents MD, it's everywhere. Like so, I I I I um I have this thing here where I talk about like um you know, like there are multiple layers, I think, for building a good

[45:28] code base. Uh obviously, the code base is one where uh if you have an architecture like this, where it's extremely strict, uh you know, the the the way to build features is very conventional. That's like the strongest strongest level of enforcement because agents just love to copy existing patterns. So, uh one example of this in Grokbot is like we have this these concepts called like a feature and we have entry points and transcript cards. Like all of you know, the cards that you see in the

[45:57] chat. These are all like like nouns, I guess, in in the framework. And so, there's a very conventional way of creating them. And so, like a feature is all in in a single directory, as an example. And so, all of the code that contributes to that feature lives in one directory. So, it's all co-located in one place. Makes it super easy, you know, agents don't have to like uh grep around and try to figure

[46:22] out like where all the things are. It just looks at the feature and like, "Oh, okay, I'm working on the onboarding feature in Grokbot. Uh I'm just going to work in this directory." And for 80% of the work, it's mostly just very encapsulated there. But uh like it's like very It's like designed again for, you know, like the dumbest agent. Like, you don't have to think. All right, the the the One of the key principles I have for this framework is like the shortest the

[46:51] shortest path is the best path. So, uh because that plays exactly to how agents love to write code. Like, they like to take shortcuts, really. You know, they'll they'll find the quickest way to solve the problem. So, why not make that the best way to solve the problem? Uh so, I I I I probably won't get into all the specific details. Um and uh the the this framework is really more of a collection of ideas and principles, rather than something that we'll open

[47:20] source. Uh you can you can, you know, screenshot this, I guess, if you want and uh tell your agent to uh do some build build something like this for you to um Yeah, but it's really all about the layers. Uh you know, like the the code base is one part with features uh and directories and you know, import uh blocking import dependencies uh that shouldn't be imported. Uh but and and it

[47:47] all enforces that and static analysis. So, like uh there's CI checks. We have a lot of lints for bad patterns that we observe. Uh compiler diagnostics. Uh, there's also rules and bug bot which are um, I think like three, four, five are more soft, right? These two actually make make CI red, right? So, that you know, there's a hard constraint where the

[48:13] agent can just write crappy code. For rules and skills and bug bot, your agents can still forget, right? You can still or it may not always consistently apply them. So, I like to layer them, but I don't I don't like to rely on them as the only source of enforcement because it's very, very soft, right? And if you if you only have rules and bug bot and skills and a style guide for your code, you will it's only a matter of time before your code base looks like complete trash. Uh, I'm sorry to say that, but uh, I definitely recommend you all like, you know, investing

[48:51] in, you know, things that can be hard enforced. Right? And this is why, you know, maybe uh, the choice of tech stack that you use is also very important. Um, like I think for example, Rust is sort of making, you know, it's like getting super popular again, uh, because the compiler is so strict, right? The compiler enforces so many different things, you know, there's a borrow

[49:14] checker that you have to appease. And if as long as you make sure your agents don't write unsafe code blocks, uh, you can more or less feel somewhat confident that if the code compiles, it probably works and it's good. Uh, but you know, you see, it gives you that level of trust and confidence that you as a human engineer no longer need to go and check it yourself. You you know, you you rely on code and static analysis to actually

[49:43] make that uh, a lot smoother. Um, and I I guess the worst part the worst place to be in is if you are stuck in code review land where you actually enforce all of the constraints, the invariants in your code base by literally the human person saying, you know, reading the code and be like,

[50:03] "Okay, you should not do this." Right? Every time you have to do that, you should consider that as a code smell, like a uh anti-pattern. And you should say, "Okay, instead of me commenting on the PR, how do I turn this into a hard rule? Right? How do I turn this into a lint rule? How do I turn this into a CI failure? Or how do I even categorically eliminate this problem

[50:25] uh entirely? Uh I I can talk about another migration I've done, but I'll probably pause here. Sure. Yeah, I feel like that's that's where I am, to be honest, is is what you're describing right now, which is that like I don't have all of these rules. Uh so, I have some things to go do after this session in terms of being able to scale my agents. I'm I'm definitely on like the uh you know, maybe a couple of parallel ones locally stage, so like two to three locally. And I'm sure most people here are on the same, so uh yeah, I know we only have a couple

[50:55] minutes left. Uh Lauren, was there anything else that you wanted to to highlight? I obviously there's lots of questions, so I can grab more, but I want to give you a few minutes uh if there's anything else you want to talk about. I think I've been yapping for quite a lot, so I'm Maybe let's just do

[51:06] questions. Okay, cool. Uh one question I had uh a couple of uh came up a couple of times was just around like token usage. So, the the question is like is is what you're describing a realistic thing for people who are on, you know, uh a a normal set of token usage, they don't have, you know, basically

[51:25] unlimited tokens uh to work with. Well, I think that's a really good point. I mean, like obviously, you know, I work at a AI lab where we have unlimited tokens, so uh I definitely cannot say that, you know, this is something everyone should do in the exact same way that I did it. I think it's possible to get to this point without, you know, breaking

[51:47] the bank. But, you know, if you're like an engineering leader or, you know, you're you're you have a startup that you lead, um I think that may be a question of ROI. Um and it's like uh yes, you spend a lot of money on tokens in the upfront stage. You know, you like refactoring your code base is going to take a lot of tokens. Uh adding all these things uh is going to take a bunch

[52:11] of tokens. But, if we're heading to a world where agents are writing all the code, and you know, you want to be very lean, right? You don't want to have to hire You don't want to be You don't want to become like meta, right? Like I mean like in terms of You don't want to become a 10,000-person engineering org because I mean, that's a cool problem to have, but also you know, you you have so much overhead. There's like planning, you know, like you it it's it's uh personally I I wouldn't uh it it's not super fun. But, um I think you want to stay very nimble,

[52:45] right? And you want to you want to be like agents are all about allowing you to do things that you couldn't do before. That's really to me like the value of agents. You know, it's not just throwing tokens on every single little thing. But, um to me like the thing I couldn't do before is like enforce this level of constraints in a

[53:05] code base by myself. Right? Like I'm just a single person, you know, uh it would have taken me years to build this framework uh and do it all the refactoring and test everything myself and verify, you know, like run Imagine if there was just me right now in in pre-agent era, just like running, you know, by my It would take me so long, right? And my salary is pretty high, right? Like So, you know, the the question I think an engineering leader might have is just then, you know, like what is there's a tradeoff of do you hire someone to do this, or do you spend the tokens to set up a

[53:44] code base so that even the the most naive, right, the dumbest agents can do a good job. And when you actually get to this point, like even agents that are not, you know, Fable size do an excellent job of writing code. And this pays a lot of dividends as well for me and personally where I've empowered not just myself, but again, like PMs, designers, engineers who are not familiar with Grok but to just contribute in a way that

[54:14] is sustainable. So, I think yeah, it's definitely like a trade-off for sure. You know, like nothing's like free for sure. Uh and tokens are pretty expensive. Uh but oh, actually, I don't I I I don't know how many of you have seen this, but we actually announced Grok 4.6 today. So, very exciting. Finally out. Um so, yeah, Grok 4.6 would be like a great It's very very smart. Uh it's really good on on the benchmarks. Uh and it's the same the tokens Uh well, uh I hopefully I'm not saying this thing correctly, but uh I believe the cost per token is the same

[54:50] as 4.5. So, you're actually getting more intelligence for the same cost. Uh I think this is an area that Cursor tries to Cursor and SpaceX AI try to really optimize for like that Pareto frontier of, you know, cost versus intelligence. Uh you know, we don't necessarily want to build the biggest model ever because that is

[55:12] extremely expensive to run. It's really about like how do you find that sweet spot, right? You don't You don't need a giant model, but it's just super smart, right? And it's not very expensive for inference. Uh but um yeah, I think to kind of round it up, um I think it's like a it's it's there's a If you do your own analysis, I feel like

[55:33] it's pretty positive. It It'll be pretty positive that the ROI you get from investing in stuff like this uh just empowers not just yourself, but your whole team to be so much more productive. Right? Like imagine if you have an army of engineers like me who are shipping so much improvements and and bug fixes uh you know, every day. Right? Like

[55:57] that is pretty exciting. Cool. One last question before we wrap up. This one is for the people in product on the on the call. So, let's say we do have an army of engineers who are shipping like Lauren. I'm just curious like how is the product team or other functions of your company keeping up given that like if you're shipping so quickly, have have are they using AI more to do their jobs? Like as much as you can speak to that. I obviously you don't have like you're not in that role,

[56:23] but just curious about how that works. Um I think this is where Grokbot has been actually exceedingly powerful. Uh where so before Grokbot like you know, obviously Cursor only had Cursor. Like we only had agent window. We had a CLI. We had an IDE. And these are really like power user tools, right? Like the they're designed for developers. So, it's very very developer-centric. You can do knowledge work in them, but it like the UI is not really optimized for

[56:52] that. So, we actually didn't really have uh well, I think like a lot of people like you know, GTM, product, like they might have used Cursor uh to do their work, but it definitely wasn't like a the like full experience with them. Um I think now with Grokbot uh it's become Grokbot is basically like the Cursor moment for people who are not in tech in my opinion. Like it's like it's like a very very accessible way to use agents in a very comfortable, very familiar interface. It looks like iMessage. Um and it's very fun too, you know, you can give your agent to be name. Uh you can have you can kind of do

[57:33] orchestration with in a very like natural way where you can sort of you know, each agent is like a person and now you're on a team of agents like working on you have one one agent per account that you manage as an example. Or if you're a PM, you have you know, you can have an agent that summarizes all the work that Lauren did last night

[57:49] and then now you know what I did, right? So, I think our PMs are leveraging that a lot. And they're shipping code, too. Uh, so you know, I often times they will just say, "Oh, here's a bug. I fix it. Can you look at it?" And then I'll go review it and actually it's just perfect. I'm like, "Okay, stamp." Uh, so uh, I think that shows that you know, the the Dune architecture is holding up, right? The all the the really strict constraints allow people who are not experts in engineering to contribute at a high

[58:19] level. Uh, so I'm I feel like I'm already seeing that pay off a lot where uh, you know, designers and PMs are just able to to to ship features directly. Um, and that just makes the Grock bot team super fast, right? Where we can ship so quickly. Um, and we have a lot planned, so I'm very excited uh, to you know, uh,

[58:44] to to ship more uh, ship more stuff. Yeah, that's awesome. Uh, we are at time, so I I guess Lauren, if if folks want to support you, maybe go try Grock bot, try out uh, 46 and uh, you know, just get to get provide some feedback. But yeah, this was awesome. Really appreciate you taking the time. Uh, thanks everyone for all the messages in the chat. Uh, lots of good questions. I know we didn't get through everything, but uh, as I kind of said at the top, way more questions than than we could get through. But uh, yeah, really really thanks thanks for for joining. Thanks

[59:11] everyone for joining and uh, hopefully you you enjoyed the session. Yep. All right. Yeah, I see see you thanks for having me and uh, if you have any more questions, yeah, just DM me on Twitter. Uh, I'll I'll open them up, I guess. I'll let the I'll let the floodgates to get you're going to get a lot of DMs. Yeah, I'll open the floodgates. So, yeah, DM me. Maybe I'll do like a Twitter Space at some point as well for more questions, but really appreciate everyone for showing up, uh you know, taking an hour out of

[59:36] your day. Yeah. All right. Thanks, all. I'll see you in the next one. Okay, thanks, everyone. Bye.

---

About this transcript
Read from YouTube's own caption track and laid out by ViewRank AI (https://viewrankai.com).
ViewRank AI finds the videos already beating a creator's own average on Instagram, TikTok and YouTube Shorts, transcribes them from the audio itself in more than 60 languages, and turns what worked into new ideas and scripts.
Free transcript tools, no account needed: https://viewrankai.com/tools
How to read any video this way: https://viewrankai.com/llms.txt