# SpaceXAI engineer @poteto

Channel: UninformedInvestors
Video: https://www.youtube.com/watch?v=Tb5GnV3Nxa4
Duration: 57 min
Language: English
Words: 11224
Transcript page: https://viewrankai.com/tools/youtube-transcript/Tb5GnV3Nxa4

---

[0:00] Personally, I think that uh the best use of you of AI is really as like a like a pair like someone you're pair programming with and not someone as not not a not a tool to just replace the act of writing code or worse outsourcing your thinking. And I think there's a tendency like, you know, because AI is so exciting, you want to put AI everywhere and be seen as someone who's very, you know, um, what do you call it? Like, uh, on the ball, I guess, with with AI. Uh, that you feel this pressure of like, you know, I'm just going to I got to increase my

[0:34] productivity. I got to ship like 100 PRs this week and barely understand what I'm doing and, you know, vive code my way to a million ARR or whatever. Um but I think you know um one of the things that I've personally seen is that although when I use AI I save some time you know writing the code I actually find myself spending more time reviewing

[0:59] what the AI did and like correcting it. So, you know, like I've I've tried the the thing that a lot of people say like, you know, you uh instead of prompting an AI to just build the feature outright, you sort of get it to uh build a spec for you first, then you review that

[1:15] spec, and then you do this whole thing. Then it's like it's such a time consuming process. Um, and if you don't really understand what the AI is doing, then uh I think you're doing yourself a disservice because it's um like the same way that in school you use a calculator or uh you know you have an open book exam. The the skill of being a developer is really in like the knowledge of using tools. And I think when you just completely outsource that, you know, thinking, I think that's like really dangerous. But I think I don't know. I don't know what other people will say to

[1:53] that. [laughter] But yeah, that's my personal thoughts because I wrote the PR, [laughter] but also it's it's like also the same feature that I don't like the most. [laughter] Should I should I save the answer for a later question or should Let's Let's hear it. Well, so user effect event is a is like a new API. We it's a little bit tough because we don't want people to abuse it. And I think if you start thinking about like, you know, where can I start throwing use effect across my codebase, I think the question you might want to ask first is, do I

[2:31] actually even need an uh effect here? um and then you know read the docs on you might not need an effect and only in the very rarest of circumstances where you do need a uh an effect uh the docs also do a really good job of describing the use cases where you might need a use effect. And so like the canonical example is where you have for example an effect that uh connects to some websocket like a chat room and um you might want to trigger some sort of event whenever the user like connects to a chat room like show a notification. And so use effect event will sort of uh let

[3:11] you uh issue that event from that effect without you having to define or declare that dependency in the dependency array. So, uh, yeah, it's a kind of a advanced API, so don't use it too much [laughter] is is the takeway. Use effect event is actually one of my favorite features of React 19 as well, because I can imagine a lot of code getting cleaned up. And you're right, like use effect gets abused a lot. So, I'm worried use effect event would also get abused a lot, but I'm hoping that people will stop uh doing that ESLint

[3:47] exception to avoid the dependencies. Yeah, exactly. Definitely use the llinter as well because the llinter the new version of the llinter will tell you um uh will give you the appropriate warnings if you're using use effect incorrectly. So definitely make sure to if you do have to use use effect event, use the the llinter. Yeah. And to to add to that, I think uh we we we talk about this in the doc as well, but you absolutely uh shouldn't feel pressured to go and like remove all your manual minimization because the compiler can you know uh just uh optimize your components anyway even if

[4:25] you've already used manual memorization. Um so yeah, there's definitely no rush to uh you know delete delete all of them. And are there plans to deprecate use memo and use callback in the fe uh f future in favor of react compiler? Uh no I don't think so. Uh maybe drove you want to add more to that. Yeah. So uh one thing we've definitely heard a lot is the fact that you know the compiler is still a Babel plugin and we know a lot of the community has moved on

[4:59] to like Rust based tooling uh like SWC. Uh so this definitely like one of the recurring questions we get is like when is you know compiler the compiler going to work uh like natively in my SWC uh build pipeline and for that I think that the team we've talked about it a lot I think our current plan is to uh so there's this project at meta that's called static hermes and it's a project to use Hermes which is our own JavaScript engine uh to pre-ompile JavaScript into like native code. And so the idea being that we can uh you know keep the very flexible development process we have in the compiler which is

[5:47] written in Typescript compile and get the benefits of a natively built uh binary. Um but that's still a bit uh like maybe I'm not sure like how far out that is. Uh but it's something on our radar and something we want to explore. But if that doesn't pan out, then we'll have to to think a lot about the like maybe another attempt at porting the compiler to Rust and then that can work with SWC. Uh but yeah, definitely though it's like a a question that comes up a

[6:19] lot. Yeah. Uh I suspect there'll be a lot of interesting answers [clears throat] from this from this this chairs here. Um hello everyone. I am 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

[6:58] really nice that they still let me do that. Uh and before Meta I was at Netflix uh where I was uh both a tech lead and uh I transitioned to be be an engineering manager um for about two 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

[7:26] skills and how to like manage agents. Uh, and that's actually a big part about what I wanted to chat with you and everybody else about today. And yeah, 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 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 look at it. Uh but I'm very excited because you know of the potential where you know

[7:56] it's not just this doesn't just benefit me it benefits everyone contributing to grabbot and it also empowers you know designers and product managers and you know uh even GTM people to add features to grabbot 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 like green field applications especially are you know like the brand new applications are like the biggest risk in 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 Grockbot

[8:30] you know Grockbot was spun up very very very quickly um and if you if you haven't heard of of Grockbot it's like our a new 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 u but yeah it's like a very it was a very green field application like most prototypes are. So it's 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

[9:06] maybe I'll find it. Uh but the idea is that uh when you have a completely vibe coded application, you essentially have no guard rails whatsoever. So uh your agents when you give them a task they will just solve it in whatever method is the most convenient and over time you get into this uh situation where you have a codebase that is spiraling out of

[9:30] 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'll have a lot of of issues with that application. Uh so I think starting your codebase with uh like very strong constraints is very much needed uh because like when you have a codebase 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 like I I said you know I

[10:09] woke up today and I had like 20 PRs merged u by my agents and that's because I invested a a a lot of time uh over 600 PRs I I I calculated yesterday uh when I refactored all of Grockbot to this new architecture that I've been building um right I have a ton of constraints and CI like it's actually very annoying to write code in in grabbot but like agents absorb all of that annoyance um but yeah I'm happy to talk about what exactly that is um yeah I think one question um before we get into the this part here is just around that element of like what

[10:47] 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 you know kind of a a glance. It doesn't have to be like mathematically average but just you know like what generally the size of the a PR is. Um if it's only a couple lines of code or you know um yeah um I think it depends. Uh let me I'm trying to do this in a way where I'm not going to like you yeah you don't have to share the actual number like an actual average this is fine

[11:16] benchmark but like we have so okay this is not that interesting but uh well fun fact is that virtualization in grabbot 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 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 doing. Uh

[11:53] so like here I'm actually like deleting a bunch of files. So I expect that it's just like mostly deletion. Uh but yeah, it kind of varies. There's no like Yeah, there's no like hard cap or hard limit. Are there all like 50 line PR? There's no hard. Yeah, there's definitely no hard cap, but I I do encourage my agents to split up their work into multiple PRs. Uh I do that mostly because uh I like I like the idea of the 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

[12:23] 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 just it's here, right? It's not in this 40,000 line PR where who knows what landed in there. Uh, but I don't have a

[12:46] 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 the screen share of like your CI does, but just generally would you describe what the CI kind of looks like uh or how strict it is? Uh yeah. So uh well specifically for Grockbot. So Dune is a is a sort of cheeky code code name for the architecture that we've built for Grockbot. 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

[13:23] the biggest foot guns in react is use effect. Uh so in uh Dune and in graphbot 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 Nex.js for uh electron apps and it's designed for agents to write uh and it's like custom for you know our agent powered 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

[13:57] eyebrows is like I actually ban code comments as well. Uh which is very interesting. Uh but I've noticed that 99% of the time agents just write code comments that kind of describe some historical thing that is 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 in a code comment like what like why 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 should change that part but agents don't really understand us that well surprisingly uh and or they kind of

[14:33] 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 if you've used agents window you've definitely seen performance issues and you know we're constantly trying to fix them. Uh but it's like a it's a never- ending struggle because there's so many pull requests that get merged. Any one of them could just regress performance or stability or reliability. Uh you know the agents window doesn't have this

[15:06] 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 just one example is like we have very poor um isolation between processes. So like on you know on on electron you have 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

[15:31] renderer. Um, but we do a poor job of separating those things. And so oftentimes you just accidentally have code that gets pulled into running on the renderer thread. 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. So very

[15:52] very small you know deadline per 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 and your your FPS really drops. You start uh you know losing frames. You get long tasks that take more than 16 millconds and you just get

[16:15] 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 Grockbot 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 directory to another. Uh so that's enforced by CI um as well as bug bots uh which is our which cursors um like code review tool that runs on CI uh you know in our agent MD it's everywhere like so

[16:54] I I I um I have this thing here where I I talk about like um you know like there are multiple layers I think for building a good codebase. Uh obviously the codebase 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 Rockbot is like we have this these concepts called like a feature and we have entry points and transcript cards like oh you know the cards that you see

[17:29] in the 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 coll-located in one place makes it super easy you know agents don't have to like uh grap around and try to figure 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 Grockbot. Uh I'm just going to work in this directory and

[18:01] for 80% of the work it's mostly just very encapsulated there. [clears throat] 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 right the the the one of the key principles I have for this framework is like the shortest the shortest path is

[18:18] the best path. So uh because that plays exactly to how agents love to write is that they like to take shortcuts really. You know they 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 probably won't get into all the specific details. Um and uh the this framework is really more of a collection of ideas and principles rather than something that will open 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

[18:52] too. Um yeah but it's really all about the layers uh you know like the the codebase is one part with features uh and directories and you know import or blocking import dependencies uh that shouldn't be imported uh but and and it 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 bugbot 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 agent can't just write code

[19:33] for rules and skills and bugbot. 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 codebase looks like complete trash. I'm sorry to say that, but uh I definitely recommend yeah, like you know, investing in, you know, things

[20:05] that can be hard and forced, right? Okay. And this is why you know maybe the choice of text 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 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 see it gives you that level of trust and

[20:39] confidence that you as a human engineer no longer need to go and check it yourself. You know you rely on code and static analysis to actually 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 invariance in your codebase by literally the human person saying, you know, reading the code and like, okay, you should not do this, right? Every time you have to do that, you should consider that as a code smell, like a anti-attern. And you should say, okay, instead of me

[21:16] 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 uh entirely? Uh okay, cool. Uh one question that had a couple of uh came up a couple times was

[21:34] 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 normal set of token usage. They don't have you know basically unlimited tokens uh to work with. I think that's a really good point. I mean like obviously you know I work at a

[21:52] 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 the bank. But you know if you're like an engineering leader or you know you're you have a startup that you lead um I think to me it's 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 like refactoring a code base is going to take a lot of tokens uh adding

[22:25] all these things uh is going to take a bunch 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 I mean that's a cool problem to have, but also you have so much overhead. There's like planning, you know, like you it's it's a personally I I wouldn't uh it it's not super fun, but

[22:55] um I think you want to stay very nimble, 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 storing 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 codebase 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 all the refactoring and test everything myself and verify, you know,

[23:28] like run imagine if there it was just me, right? in in pre- agent era just like running you know by 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 trade-off of do you hire someone to do this or do you spend the tokens to set up a codebase 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

[24:00] both size do an excellent job of writing code and this pays a lot of dividends as well for me personally where I've empowered not just myself but again like PMS designers engineers who are not familiar with art to just contribute in a way that is sustainable so 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 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

[24:37] 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 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 at like if you're shipping so quickly has 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

[25:06] in that role but just curious about how that works. Um I think this is where grabbot has been actually exceedingly powerful. Uh where so before grabbot like you know uh obviously cursor only had cursor like we only had agents window we had a CLI we had an IDE and these are really like power user tools right like de they're designed for developers so it's very very developerentric you can do knowledge work in them but it like the UI is not really optimized for 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

[25:40] cursor uh to do their work but it definitely wasn't like a delightful experience for them. Um I think now with grabbot uh it's become grabbot is basically like the kusher 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 to, you know, you can give your Asian a fun name. Uh, you can have you can kind of do orchestration with in a very like natural way where you can sort of, you know, each agent is like a person and

[26:14] now you got 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 and then now you know what I did, right? So, I think our PMs are leveraging that

[26:28] a lot. And they're shipping code, too. Uh so you know like oftentimes they will just say oh here's a bug I fixed 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 that 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 level. Uh so 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

[27:00] that just makes the Grockbot 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 to to ship more ship more 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 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

[27:38] found the smoking gun uh, for the hundth 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 most out of them. And for me, the parallel is like with management. Uh so if I'm an 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

[28:08] have to spend a lot of time looking over my reports shoulders and checking that they're doing their work well. You know, like they're not shipping bugs to 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 know get into this mode where you are in very heavily in the loop with one or

[28:50] several like a handful of agents and you find yourself just constantly fig uh you know trying to understand what your agents are doing uh and you're very very in 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 a 100 agents uh like spawn 100 agents when you don't even trust the

[29:13] 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 makes me sound like a sloth artist, but I I promise I'm not. But I actually have

[29:32] my agents now um automerging 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 Maine like they were already landed and they were good. Uh, so how did I get to that point is basically what I wanted to talk about

[29:51] 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. [laughter] Uh where uh no do not trust to someone requested to control my computer. Uh probably won't do that. Uh but yeah, so this chart I think 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 to land at cursor. So I joined five months ago and five months ago like

[30:29] I you know my first month I was like not very productive because I was ob you know I was learning the codebase 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 of ramp up my productivity uh and again like yeah like last month I shipped a thousand 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 sure a lot of you will definitely be questioning like how how much of this code is actually good. Um,

[31:04] 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 call in your experience as well but uh for me I think the most important skill that you should have in your toolbox when you 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

[31:48] 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 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

[32:12] really big stop within cursor. Uh oops. Where? Let me open this.

[32:27] Uh make me full screen. There you go. Uh so for the for cursor's agent window uh so this is actually an interesting story but uh when I joined cursor five 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 the agent window Uh but um there wasn't really a lot of like skills to help me. So I just found myself like okay uh agents window is

[33:08] going to launch in like a week 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 dev tools and just like pick 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 where you know I mean I had some idea but you know the code base was completely fresh to me uh and I realized like my agent had no idea

[33:35] either you know, like I would take a screenshot of the tree, I'll download trace. I would send it to it and it 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 turns out that's not the actual thing.

[33:48] So, this was a very very slow process. And if you've ever done any like performance work yourself or you just even development with an agent where you don't have a verification skill, you are the verifier, right? You you're the bottleneck. you you you tell your agent to do something and then it goes off and write some code. Then you open up your you know local dev build and then you start to say oh you know it 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

[34:17] with that and then tries to understand it and um 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 skill is like one of the first skills I built. uh for cursor uh and glass by the way is the code name for agents window that we use internally but it's just cursor I guess um and so this skill uh is I guess that the 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

[34:49] web app or even iOS uh applications uh you can teach your agent how to use like the chrome dev tools protocol or through uh Apple has some utilities as well for running the simulator and taking traces and controlling programmatic control as well. Uh so that's really useful. Uh but one thing I 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 a 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

[35:32] actually run the agent window and take traces and whatnot. Uh but it had no idea what what the agents window was. So um you know like someone would say like oh the the left sidebar 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. and it would spend a lot of time trying to like look up the

[35:54] 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 build uh but then it just be turnurning like I 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 been really useful, uh, because it teaches the agent how to get to all of the features that

[36:27] you have. Um, and in PAC, the plugin that I I've made, uh, if you search for PAC cursor on Google, you you'll find it. Uh, but there is a create 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 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

[37:03] have this uh internally at cursor where uh we have a slack channel with you know lots of people giving us feedback on the agents window and rockbot and whatnot. Uh, and often times the report is very bad, like very low quality, like someone will 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 without this your agents like 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 the different

[37:36] features. Uh so like you know example like I guess like the 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 how do I 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

[37:58] things through the CDP uh are all there. So uh again yeah this is like really really powerful uh for for agents uh and pstack ships uh that create verification skill but also a maintain verification 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 Pstack and maybe just what Pstack is for the folks who aren't familiar? Yeah. So, Pstack is pretty interesting because uh well,

[38:28] first of all, the name is kind of goofy. Like the P the P in P stack is like potato potato stack because I um so uh uh there is a pretty uh famous person Gary Tan who is the CEO of Y Combinator and he's come up with this plugin called GSAC uh Gary Stack and uh funnily enough we share the last name. We have no relations. Uh, but I thought it'd be funny to kind of, you know, poke fun at Gary and make Pack my version of of of of his plugin. Uh, but kind of tailor it

[39:02] to my own set of practices. Uh, but I honestly actually never set out to build PAC. Uh, it just started with a bunch of skills, right? Like I started with that control glass skill and then I started with another skill like called how which I also noticed 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 like I would tell it um you know this feature has stopped working. Here's a bug report. Like why

[39:35] 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 like, I'm not going to I can't trust any this agent anymore cuz it's just 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

[40:08] know, you don't know how to help your agents succeed. But like again I think the the the management analogy is super helpful because like imagine if you were a manager of an engineering team and you had an engineer on 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 you know like 5 seconds ago. Uh and so how do you actually teach that person to be effective? So how you do that is through a skill. uh skill being just you know it's just markdown right by you know it encodes a lot of information

[40:39] 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 LLMs are sort of like they 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

[41:05] that's you know smarter. Um so that's like a very interesting model there. But yeah I built PAC very very incrementally. Uh so uh started with just really observing how agents you know all the fail 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 right like stop hallucinating actually go and search up look up the code use a lot of sub agents uh and yeah stop guessing 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

[41:40] product changes over time obviously there's a lot of people are shipping against the codebase So how do these skills get maintained? Uh and then second to that is like how do you know when your verification is is good enough? Uh like and you know you can trust that the ver verification loops that you've built are going to I guess you trust that the outputs uh when

[41:56] they're done. Uh yeah maybe I'll talk about um I think some really 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 is essentially like a way to, uh, well, I think the mental model I have is like it's like a unit test for an agent. Um, and, uh, you can actually make your own evals. You don't

[42:23] 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. Do you mind like disabling the drawing or something? I I can't see 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

[42:45] troll. Yeah, the little drop down. How do I clear? Yeah, you got it. Perfect. Yeah. So, eval test your skills basically. And actually in Pstack, we ship uh 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 um, essentially what I do is I spawn a lot of different sub agents. I have like my main coordinator agent uh, come up with a rubric for uh, what I want the skill to do. Um, and then it spawns all these sub aents and it it creates

[43:29] individual directories for them uh which are cleverly named to not let the sub agent know that it's being evaluated because uh agents can actually tell and 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 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

[44:05] across that different matrix. Um 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 uh like the eval playbook uh 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. Uh it requires I think a lot of taste and observation. So you kind of need to be very good at being a

[44:33] backseat driver. You know what I mean? Like if you do pair if you ever done pair programming for example uh and you watch a co-orker code and you just like you you could probably do this better. You know you could do you know 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 of your agent. you want to be very in the driver seat in the initial stages when you're building up your own set of skills. uh you know obviously you

[44:58] can use something like PAC 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 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 a skill for 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 I actually did the same process for verifying the

[45:29] verification skill where I actually get um so one thing that's interesting about eval 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 comp uh you can have a judge agent of a different model to uh kind of cross reference and make sure that the first model is not being biased right the model that's judging all of the sub aents that are running the thing. Uh but you can also like hill climb. So meaning that you can you can use like /loop in cursor and you can say okay keep looping

[46:04] 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 actually. Uh so you know I uh I kind of built I built that skill that way like the CLI and 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

[46:38] drawing here. Uh but I think of it like uh you know as a as a engineer now you're sort of more like uh like maybe a manager or the analogy I like is like you're like a a chef in a 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 sue chef, you have, you know, all these different stations. Um and it's your job to really design the environment. You know, you you're in charge of setting up the kitchen. You're in charge of, you know,

[47:08] 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've basically built uh these verification skills. Yeah, just just one thought there on like to go try to go one layer deeper. So, are you let's say we wanted to build um an eval or a skill for for something and we wanted to kind of get better on its own which is is what I think you're suggesting. Are you doing that in like a work tree kind of isolated with like the sub agents and and then the reviewer agent and and all that? Is it happening like in some type

[47:43] 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 would I do or where would I start? Um I think that uh the best place to 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 a desktop app or whatever. And so, you can actually observe, right? You can see how the agent is interacting with

[48:16] the the application. You can see it, you know, how it calls like the different APIs that that allow it to interact with the 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 dividends because it's not just something that makes you as a single engineer better. It actually levels up your whole team uh and even your whole

[48:56] company because uh you can actually start thinking about cloud agents. You can start thinking about automations that automatically do things like uh I I get I kind of 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 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 its desktop it runs cursor in its own computer and it uses the same control skills to interact with the application

[49:30] and try to reproduce the bug uh or the user report right and this is so so powerful because at once I can immediately I I get so much information from this automatically like here in this example you can see that uh the Benny actually reproduced a 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

[49:52] 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 like is this fixed, is this not fixed. So you you you gain back so much time. Uh but you know,

[50:05] 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 almost impossible. And I would definitely encourage you not to try to jump from, you know, like if you're still in this zone, you don't want to jump to like I'm going to spawn hundred of thousand or thousands of cloud agents right now because you're

[50:39] 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 to start with verification 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 it's it's technically solving the problem by looking at you know stack traces looking at you know the actual behavior in the app and so on. Um and

[51:06] 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 it's like a bug report that comes in or something, they can go and pick it up and solve the problem and give us back a PR. And then maybe the last step is like automerging the PRs, which uh is where you're at,

[51:23] maybe not where you want to go. Um and then and reviewing the one main, but um is that is that about right? Yeah, exactly. I think yeah, that's why I drew this this uh 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 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? Um obviously, you know, as a as engineer, you don't want to just slop code into production. So, how do you

[51:52] 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 uh get up to speed much quicker. Uh and so I guess it's like if you trust me and you trust PAC 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 PAC and kind of fork it make it your own improve the skills

[52:27] definitely encourage that uh but for me yeah 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 codebase. And uh when you are able to encode all of that into skills and you can verify that your agent is actually doing them that allows you to really kind of ascend this curve and um uh you know start automating

[52:53] things. Yeah. I think there's a third part 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 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 terrible I want to rewrite the whole thing is a very common inclination and I think a lot of

[53:27] you know before agents um and I guess arguably even now people will definitely discourage you from re 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 uh 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 was just observing I I just noticed this parallel which is that a lot of big tech company problems are now everybody's problems. Um, and the big tech company problem, you know, like

[54:04] when I was working at Meta, like we had this giant monor 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 quality is actually not that good. Um, and so I often joke that like, you know, before AI sloth, we had human sloth. 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

[54:36] companies are actually designed for that where 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 guard rails you know you restrict credentials so that you know your intern doesn't wipe your production database um there's uh you 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 guard rails are already in place for agents to not cause havoc or not cause too much

[55:11] havoc uh in your codebase. Um and you can always add more, you know, guard rails. Uh but I think I think yeah, it's definitely like a trade-off for sure. You know, like nothing is like free for sure. Uh and tokens are pretty expensive. Uh but oh actually uh I I I don't know how many of you have seen this but we actually announced Grock 4.6 today so very exciting finally out. Um so yeah G 4.6 would be like a great it was very very smart uh it's really good on the on the benchmarks uh and it's the same the tokens uh well uh I hopefully I'm not saying this incorrectly but uh I

[55:44] believe the cost per token is the same 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 heredto frontier of you know cost versus intelligence. Uh you know we don't necessarily want to build the biggest model ever because that is 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

[56:15] for inference. Uh but uh yeah that's awesome. We are at time. So, uh I guess Lauren, if if folks want to support you, maybe go try out Grockbot, try out 46 and uh you know, 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. Lots of good questions. I know we didn't get through everything, but as I kind of said at the top, way more questions than than we could get through, but uh yeah, really

[56:39] really thanks thanks for for joining. Thanks everyone for joining and hopefully you enjoyed the session. Yep. All right. Yeah, I see. Thanks for having me in. Uh if you have any more questions yet, just DM me on Twitter. I'll I'll open them up. I guess I'll let the let the You're going to get a lot of DMs. I'll open up. So yeah, DM me. Maybe I'll

[56:56] do like a Twitter space at some point. That's all for more questions. But really appreciate everyone for showing up. Uh you know, taking an hour out of your day. Yeah. All right. Thanks. I'll see you the next one.

---

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