How I AI - How Warp ships 2,000 PRs a month with AI factories | Zach Lloyd (CEO, Warp)

0:00Can I give you a hard time that humans really are the bottleneck? Because if you look at kickoff to PR time, it's 35 minutes. But if you look at PR to first human review, it's three and a half hours. And when you're doing, I think it was like over 2,000 PRs in the last month. How do you keep things in the team from going, as I say, like chaos reigns? What is a software factory? For us, at least it's an actual noun. It's like a product concept.

0:25where it consists of a bunch of repos, a bunch of like MCP servers, like a bunch of configuration, and then a bunch of agents, essentially. So like a code review agent design, different agents, different automations, and it's all defined in code. Scoring happens across all runs, but then there's a second loop.

0:45popular thing on Twitter right now called self-improvement where you have like an observer agent and it can then create updates to your factory that will try to prevent the particular failure mode. One of the things that's most helpful is like you can have these factory agents do computer use verification so in this case it made a video. I'm just like talking to this thing that is doing this job that I've done for the last 20 years and it's now it's like doing it kind of better than me.

1:17Welcome back to How Eye AI. I'm Clara Vo, product leader and AI obsessive here on a mission to help you build better with these new tools. Today I have Zach Lloyd, CEO of Warp, and he's going to show us exactly what he means by the software factory. He's going to show us how you can kick off tasks and Slack, what it means to go beyond the software development lifecycle, and how a technical CEO uses non-technical tools with AI. Let's get to it.

1:44This episode is brought to you by DX. In a recent study across more than 500 engineering organizations, DX found that spend on AI tools has grown 28x over the last year. The share of AI authored code is climbing, but overall innovation has remained flat. As teams generate code faster, new friction in code review and validation is offsetting those early velocity gains.

2:09DX tracks speed, quality, and cost together across the software development lifecycle, giving engineering leaders clear visibility into how AI impacts delivery, and whether those investments are translating into real value. Download the full report at getdx.com slash howiai. That's G-E-T-D-X dot com slash howiai. Zach, thanks for joining Howiai.

2:38Thanks for having me excited to be here. There are a lot of trends on the timeline right now But one that I think is going to be big for 2026 or seems to be big for 2026 is The factory the factory this like fantastical idea that we have that we're gonna you know input tokens and output Enterprise values something like that at least will output code so I you know I'm excited for you to show us as CEO as engineer as builder You know what what to you is the factory and how it looks inside warp the factory is definitely trending I actually don't love the term factory, but it is the sort of thing everyone is standardized on it feels a little bit sort of like dehumanizing to me but But yeah, the the idea is exactly what you said It's like how do you in a world where we have these sort of magical agents? Kind of harness their power in a more organized way to have them

3:37basically build software for you from your ideas. And so, yeah, excited to show you how I use factories and what it means to me. I was at Lenny's Summit recently and I think Marty Kagan also said he hated the word factory. I wonder if it's more like Santa's workshop, right? Like, we have magical elves that craft wonderful things that spark joy in our delivered gift wrap for us.

4:06I'm going to say the AI magical workshop. No, show us. What does this look like for you? Yeah, you just say you put in your ideas, you output product. Is that real? How does that really work? Yeah, so it kind of works like that. The way that I think of factories is like there's basically two types of personas who are using them. So there's, I'll show you like basically how we do this in warp.

4:35there's like the builder persona. So the builder persona is someone who is contributing ideas, wants to build stuff. And from that persona, it doesn't look like, at least the way that we have it said, it doesn't look that different from like how one of these engineers or designers or product people on our team might build with a local coding agent. The big difference you can see here, so this is like, this is our Slack, is that most work is starting in a public place. And so, the way we think of factories is like, you basically can say in a public Slack channel, you can tag, we named our factory Wilson, you can tag Wilson and be like, okay, I want you to build something for us. And when you do that, what Wilson will do is like, essentially, do not just like the direct build, which is what you might get if you're using like cloud code or codex, but we'll also like,

5:31do a few other steps. So what it will do is it'll kind of go through all the steps of like, first it will triage whatever this is. So it'll treat it as like an input to the factory, not just like a direct thing to build. Meaning it will, you know, for this one, Harry's saying he wants to change the way this feature looks. He gives like pretty detailed instructions. He, you know, attaches an image.

6:00He says use computer use. And this kicks off a flow where the first thing that the factory does is actually kind of open an issue. So you can see over here, it's like we use linear in addition to using Slack so that everything gets tracked. So the factory integrates not just with Slack, it opens an issue. Then it does the actual implementation. For this one, it was simple enough and ambiguous enough that we could actually implement it. Then it does, it will create the PR so it integrates also with like GitHub. Then it does the QA, which I think is like really important these days. Like if you want to not spend all your time doing code review, one of the things that's most helpful is like you could have these factory agents do like computer use verification. So in this case, it like made a video of the completed feature.

6:57So it's like showing the thing, showing all the keystrokes. And so what you get here is not just like, and then it gets merged, right? Is not just like the single step of build the thing. Like if you were to do this with like the coding agent in like the pre-factory world, what you would typically do is like pull up your local coding agent, do the change there, test it locally, and then like push it up to GitHub. But you get the whole thing of like the ticket, the...

7:27the code review, PR, the video, all done together. And then the other like really kind of magical thing is that it's all done in public. So if you are, you know, someone else wanted to come in and like look at this and see how the task was done or even contribute to it. And so we will have people like multiple people on these select threads. You get to a world where as like a builder, you're no longer sort of working in this local silo.

7:55Instead you're working in a public space where everyone can see what you're doing and so that's like a From the builders point of view how they like use the factory. Does that make sense so far? Yeah, and you know, I think what I'm reflecting for folks who are maybe still trying to grapple with okay Like what's a coding agent? What's a factory? What's the difference? I think what I'm from you is The factory quote-unquote is comprehensive comprehensively designed to reflect your version of what the software development lifecycle should be. And so it's not just like idea to code to PR to push. It is okay. An idea needs to go through several steps. It needs to go down the conveyor belt of product and into like the funnel of issue tracking. And then we need to code it and then we need to QA it and then we need to have these very specific verification loops where we can take our sticker and say quality controlled by, you know, number 123. And so

8:52to you and the way you're describing it, where it goes beyond a coding agent or a co-pilot is that it is actually designed to take the very specific NN product steps, not just the engineering kind of like input output. That's definitely part of it for sure. It's like it does more of the software lifecycle. So it does more of those steps. There's a whole other...

9:21bigger part of it to me which is So I showed you this from like the perspective of the the individual builder if you were to go into our slack you would see like This is happening over and over like all day long the people in our team are building in this way and sometimes by the way, it's not just like the engineers who were kicking off work like this it could be work that's being kicked off automatically so for instance we have I don't know if you know Sentry, but it's like a crash reporting system. And so we have signals when there are crash reports coming from like our terminal app that we try to automatically fix those. And those go into the factory too. So it can either be human initiated. It can be initiated by like an external system. And it can be initiated actually in any of these tools. So it's like you can initiate it like we could have started this whole thing in linear.

10:19We could have started this whole thing in GitHub, and so it's integrated into all the tools. But the bigger piece of the factory approach, in my opinion, is not like, it's not so much how the individual builders work, because it's not all that different from individual builders who might be going into the terminal, for instance, and using a coding agent to do something. It's different. It's in public.

10:47But what's really different in the factory approach is that everything is like centralized in the cloud. And there's a whole other aspect to it, which is for not the builders, but for the people who are like the managers who are like trying to scale software development on their team. Finally, something for the manager.

11:08But everyone's been wanting right too much attention on the builders No, but it all seriousness if you're like like my concern is someone who's running a company It's like I want I want soft like it's a super duper competitive market. I want to see how quickly we're moving I want confidence that The way that we're building software is actually improving over time I want to make sure that we're not like wasting too much money And in the world of like all, like every builder has their own individual local setup that's very, very hard to get. And so this is like an engineering manager's dream. It's like a, it's like a CTO's dream. Like, not that this is the coolest thing in the world, but it's like, now I have the ability to sort of centralize and see what everyone's doing. So for instance, on this screen here, it's like, these are

12:06This is actual data from our team in terms of like how we're using the factory. It's like there's a sort of sense of like how automated is the factory? What's our velocity? How long does it take us to like ship stuff? And so there's just all these measurements. Can we pause real quick on your productivity because I actually haven't seen this measure before and we've seen a lot of measures which is Human interactions per PR. Just yeah talk us through why that is honestly heard that one before and I like it You know this sort of instinct underlying this is that We are gonna be Not not to put this the wrong way, but it's like humans are a little bit of the bottleneck in terms of production itself They're also the the creative force But in general what companies want

12:57And we're, you know, we're trying to build for companies that warp largely is like, how do you automate more? How do you make things that can truly just be done agentically, be done in an almost fully automated way? And so, you know, the general instinct is like the more times you have the prompt, the more times you have to steer or like, like cajole your agent, that's like, that's going to be a limiter on throughput. So this is where you start to get into like.

13:24Factory world like this is like imagine you're running like a Tesla plant or something. It's like how many times do you have to stop the line? And so, you know, we're trying to give engineering leaders a view of like, okay How are you? Are you are you able to sort of make things more efficient over time? And quick question are those just because my mind I mean I you know as a once one-time CTO like yeah, this is exactly what I want Are these interactions, do you think of these interactions as like the prompts, the sort of like upfront steering? Are you thinking about like how many comments on PRs, how many loops? Like how inclusive is this like interaction per PR score? It's all of those. So because the, and again I think this can definitely be refined over time and bear in mind we're like trying to figure out so what is the right set of metrics, but this actual metric

14:20Because the factory is like integrated into all of your knowledge work tools it includes all those things like how many repromptons slack how many comments on linear how many times did you have to correct the thing in code review and so It's like a kind of like yeah, it's a proxy for how much work did you have to do? In order to you know get the thing to do the job Okay, wait, I want to I want to give you a hard time one more thing. Yes, please even before we started recording you said like how technical and I was like, okay Well, we're gonna put on the CTO at least the CTO hat right now Um, can I give you a hard time that humans really are the bottleneck because if you look at kickoff to PR time? It's 35 minutes But if you look at PR to first human review, it's three and a half hour three and a half hours and so it's like so funny that still cycle time man like it's

15:12It's the thing you really have to focus on. It's that number. Yeah. There's still the bottleneck. And we're, I mean, we're still doing human code review. All your PRs get human code review. Currently, all of our PRs get human code review. And so now this is like, I think of a team choice, an organizational choice. We have.

15:40The one thing that we have changed around this is that, like we used to require, like the workflow used to be like person A on our team would build something with an agent and person B would review the agent's code. We no longer require that, like the person who prompts the agent can also review its code. Okay. Yeah. You're making me feel better. That's a better thing, but it's still like we, you know, we don't have yet complete trust.

16:08I think the way this will evolve is like some percentage of stuff will eventually feel confident enough that we can skip that. Yeah, I did an episode recently. I built an Eve agent called MergeMommy. And this is the flow that I often see in even mature engineering organizations is what you do is you basically like risk score every PR automatically. So go through risk score it.

16:36And then anything that is low or extra low risk gets a stamped approval from Merge Mommy and then a human's allowed to just smash the button and merge. Anything that's like medium high or whatever or has some like outlier on risk requires human review and that just like lets you get that bottom tranche of the queue out. Also just so you have good capacity for high quality human review on the things that really matter. 100%.

17:05Think code review becomes an exercise and risk management. I think that's right I want to show you some other stuff in the factory just to show you like how this is different than just standard interactive agent so you get Cost is on everyone's mind right now. And so You get like this is Asian cause it doesn't factor in that sort of cost of the people at the moment, but it's like You know, you can see like we were really expensive a few weeks ago. We made some changes to our model configuration and we've driven this cost down and we want to continue to drive it down. But just like having the centralized view for this across your whole team. Can I ask you a question of cost? Quick question of cost. So I mean, this is a pretty, you can see the drop here.

17:53I see this a lot when I'm talking to engineering organizations. They often see a rise in cost per PR as they're adopting AI, which you all already have. And then we see this drop as you're doing optimization. Do you feel like the biggest lever here is model right now? Is that the lever? Yeah, it's model. I think model is the biggest, I think, context management.

18:24Matters as a secondary thing. I would say model is the biggest Yeah, and that though the way to really figure this out actually is to test which is something I want to show as well, but Basically, I think I think model is is the biggest one Any other questions on the just like to spend view so the the other thing like this is where it really gets kind of factory oriented is like the the way that we're changing development and This is I think this is most relevant for folks who are watching we're trying to manage like these teams and scale coding agents is like we now We're like measuring everything and so this last thing in here, which we call scoring basically gives you a view Across all your agent runs

19:22of like how they're doing on different dimensions. And so we, we basically, because the factory is like a closed kind of like closed loop system, like every, every time an agent does a task in the factory, that task gets recorded. And what that opens is the possibility for you to go and like, like go back retroactively and look at how well the task was done. And so you could do this as, as a person, you could literally just go back and look at tasks but the other thing that you can do is you can have agents do this which is what is what we do and so for instance let's see if I can find an interesting one like here's an interesting one like redundant tests so if you're working with every PR I push it's like I have run and set up 135 tests

20:19It's it's not it's like it's it's like in the reason it does this is because You know they're writing tests not to like Prevent regression is necessarily but also just like test behavior along the way and so you end up with a bunch of tests that you don't need and so we You know if you take the factory approach You kind of know this might be a failure mode and what you can do is you can write essentially a like a scorer that uses LLM as a judge to be like, okay, I want to go and look at, you know, all of the agent runs. And I want to see how often we're, you know, an agent thinks a different agent than the one that did the task thinks that there's redundant tasks. Does this make sense? Yeah, totally. And so you basically are like, okay, I'll pick a judge model. This is like a kind of medium smart judge model. You don't want it to be too expensive. Otherwise you end up spending a lot of money on scoring.

21:13you have it classified in terms of like for this task like how did it look? You pick like a sort of sampling rate in terms of how you want to do this and then you get over time a set of runs where you can see that like sometimes this agent thinks that there were some like surplus tests and so this is what I mean by like the real measurement then what you can do is like you can go and you can actually you know as a human You can go and kind of look at what's happening here, but I'll show you. There's also a better way to do this in the factory world where it's like, you can actually use agents to sort of identify what's gone wrong in these runs and try to improve the factory. Does this make sense? Yeah, I'm curious. Do you do this on a per run basis or on an aggregate basis across a set of PRs? Aggregate, great question.

22:10Yeah, so what we do is like the the scoring and this is what I call like this thing We call this like the score the scoring happens across all runs, but then there's a second loop Which is another like popular thing on Twitter right now called self-improvement where? You take an agent and you basically say okay for all of the failed runs and you need like you need like a real sample like maybe 20, 25 failed runs, you need some significant sample size, otherwise it starts to overcorrect based on single things. You have it look, you have like an observer agent look, and it can then create updates to your factory that will try to prevent the particular failure mode. And so let's see if I can find one that's like, I don't know, I'm just literally picking a random one here.

23:04But this is finding some issue with our skills that are driving the factory. It's presenting evidence and it's saying, okay, we should change the definition of one of our factory agents in a particular way. And if you go under the hood and look at this, it's changing this step 10 of what our factory agents should do. Does it make sense? Yep. And so to me, this is really exciting.

23:34The thing that's like enabling this whole thing to work is that you define the factory in code. And so, you know, what I mean by that is like, if, if you were to look at the sort of definition, you would say, okay, the factory, what, like, what is a software factory? It's like, it's like, for us, at least it's an actual noun. It's like a product concept where it consists of a bunch of repos, a bunch of like MCP servers, like a bunch of configuration and then a bunch of like agents, essentially so like a code review agent design, like different agents, different automations. And it's all defined in code and the value of doing it that way, like in warp factories is that you get the ability to actually, you can like.

24:30Test different configurations and know like you're basically freezing the state of the factory at a given point so you can be like Okay, if we were to change the factory definition then like run all these tasks again. We could see if things were better It also let makes it so that like An agent can actually because these are all it's all code like coding agents can actually update the factory to make it better This makes sense. Yeah, this episode is brought to you by open art arena the global leaderboard for creative intelligence. Every week, new AI models launch, and everyone claims to be the best. But best at what? OpenArt Arena is built to answer the question that actually matters. Which model is best for your specific job? Instead of one overall winner, OpenArt Arena ranks models across real creative tasks.

25:24from advertising and film to animation, product, graphic design, editing, and lip-sync, covering both image and video. And these rankings aren't based on hype. They're judged by professionals, industry leaders, and working creators through blind evaluations. So judges never know which model produced which output. That means you can see how models actually perform when it comes to the creative work you're doing. So stop guessing which model to use.

25:52explore rankings based on real creative work and find the right model for your project and save time and cost. See the rankings at OpenArt Arena. Yeah, I just want to like, you know, kind of sum up where we are so far because I think there's so much rich stuff in here, especially for engineering leaders and builders. And then I know we're going to get to some workflows that are not engineering focused, which I'm excited about. But the, you know, a couple.

26:17Trends themes that I've seen as you talk through this one work happens in public So I'm seeing you know this move towards instead of work being assigned to tickets and then tickets being worked on on laptops Work is happening in public whether it's slack or some other channel and then and then executed in the cloud So sort of anybody can interact with that The factory does have this software development lifecycle kind of like definition to it But on top of that it has this aggregate meta-analysis that you're doing across all the behaviors which is giving you know as we said giving the people the managers what they want which is are we getting more efficient over time is this factory actually effective how many humans how many agents what's the inner balance between the two spoiler alert the humans are the problem right now and then um and then what you're doing is you're also doing these evals against key behaviors in your factory that you want to correct

27:14And this is something that when I talk to engineering organizations, I tell them all the time, which is such a challenge when you're using something locally, like for example, cloud code, is I say you need session level telemetry because you need to be able to aggregate up the failures within sessions across your engineering team. And so some teams do this truly by like sucking up every local coding session to S3 and running their evals kind of like on their own in their own platform. But I do believe that if you do not have session, tool call, MCP call, test failure, computer use level, observability into every single coding session, you're missing a lot of opportunity to optimize efficiency, cost, model, just like how your team uses the tools. And so I think it's

28:08Super important that people do this. And then what you've added is this extra layer of great than take those insights and make the factory better. However, you define better. This is a great summary. Great. I did it. Professional podcast. There's, there's, there's what, just to give a sense of how you can continue to like, you can go even further once you have this data. I think your summary was awesome. The other thing that you can do and like, I think NJorgs are going to do this because this is This is how like, there's gonna be nothing more important than optimizing the way that you like build and ship software in the future. And so one other thing that is really powerful, if you set up everything you just said, where it's like, you have the, you have the tracking, you have the evals, there's one further way that you can make it even more powerful, which is adding the ability to basically take your own data and replay those sessions with different configurations.

29:06to actually measure like to your question earlier like well how would it have done from a cost perspective or a quality perspective if you'd done like different models and so for instance like again this is what we have built into our factories but there's lots of ways you could do this like the the idea is you can just like there are these public benchmarks like sweet bench and terminal bench that are on like generic data you can recreate on your own data, like from real past factory tasks, how would things have gone had you used a different model configuration, for instance. So this is like a kind of Pareto chart, which again, these things are on Twitter all the time, but it's like, what's cool here is like, if you take the factory approach and are like really scientific around, okay, I want to know, like, let's say you want to curate a bunch of front end tasks and then see like,

30:06Can I be using GLM 5.3 on those instead of using, you know, Opus? Yes, definitely. Should I be using Gemini 3.7 Flash? You're going to take a quality hit. Instead of like, you get to choose your own sort of trade-offs here and then you can feed this back into a model routing strategy where you actually have evidence that, okay, on your own tasks, for these types of the best model configuration for cost and quality is whatever you find. Are you comparing that to what actually shipped? How are you evaluating quality? There's seven ways to skin a CSS. How do you actually decide this is better quality or not on front end tasks, for example? Yeah, awesome question. So the way that we do it in more factories, and you're probably, you can

31:01do different things. Here's we use the exact same like scoring infrastructure that I showed you earlier. So for instance, you know, we over here, we have all these different scoring dimensions. So you can if you have confidence in this scoring infrastructure, basically you're replaying past tasks and trying to see if there was like, how it affected these scores. So it's it's it's primarily LLM as a judge, but you can also It's like, you could do this with human judges, you could do it algorithmically, but the thing that we have built this out while I'm as a judge. Got it. Super interesting. Okay, so you've given me so many ideas on how to take the factory idea further. I'm curious, just like take off our builder hat or CTO hat. Let's put on, you know, I was talking to you again before we came out, I was like, people love to see.

31:53how non-technical people can do technical things and how technical people can do non-technical things. So show us some of your other like AI use cases that are maybe less about evals and benchmarks and and MCPs and more about, you know, being a CEO. Yeah. So we'll get like, I think like zooming out. This is cool with all these charts. I still have a hard time making changes to Figma.

32:19And like, I don't know if you're the same way, but when I go to try and change like a, like a Figma thing, I'm like, it's like I have three thumbs or something. Like I just, I cannot figure out how to use it, but I do know that it's like, if you, like this is, this is how we like do our slide decks. For instance, it's like we, we are using Figma slides. You can make things that look very nice. So one thing that I do now is like, if I need to change the slide deck, I do it through the Figma MCP and the coding agent. And so like, just to kind of show what that looks like. We have this kind of semi-boring slide here on Cloud Execution. So I'll show you how I would do this just so you get a sense. So I'm going to do this. I'm going to do this in Warp. I use Warp as a coding agent. This would also work in Cloud Code or Codex. Anything that's big about MCP.

33:15I'll just paste this in and then I'm going to talk to it, which is another thing. I assume people are on the voice train at this point. Are you on the voice? Yeah, we give all credit to Hilary Gridley. She calls it the Yappers API, highest bandwidth way to talk to an LLM. Yeah. So I'm going to say I'd like to make a new version of...

33:38This slide, use the Figma MCP to get the context, duplicate the existing slide, rather than making changes directly to it. Let's have it be so that the host box contains the runtime box. Let's, let me see what else. I gotta switch back here. So we're gonna have host contain, sorry, host should contain sandbox. I'll go back and edit this.

34:09Let's make the context system something that's like kind of like you know cloud around these things that feeds into them True CEO put a cloud You're gonna see some bad design here Let's make the launch pad have a sort of like rocket type theme This is my this is not what my sales team wants by the way and Let's make tracking I don't know, why don't you come up with some ideas for how to make tracking better? The overall idea here is to make this slide more visually appealing than the simple, you know, five boxes and semantically show the relation of the boxes to each other. So I'll do this. Do you know what word I say to Figma? I say semantically. Now what? To Figma, MCP, all the time. Really? Oh my god, all the time.

35:09Semantic colors. Semantic. It is. It is my orthogonal. That's really funny. Yeah. I mean, we'll see. So I'm using I'm using rock a lot recently. Same. I don't know what your model of choice is. I think rock is pretty good from like the cost and speed and quality, quality trade off. I could show you how I could do some other.

35:39Yeah, while that's loading, why don't you show us something else? Yeah, I'll show you another one. So I'm a big granola user as well. And so again, if I were really trying to improve this sales deck and other things that I would want to make sure is that the sales deck is speaking to the things that customers are actually talking about. So I'm going to start a second task here using the granola MCP where I'm like, can you use the granola MCP?

36:06to look back over my last four weeks of sales meetings and try to build up a list of the top 10 frequently most asked questions in these meetings as they pertain to warp software factories. Don't list any specific customer info in the summary. Anonymize it because I'm doing a podcast.

36:36So we'll get this one cooking as well. I could do one more if you want. Yeah, let's I mean let's queue them up again I love to see a AI-pilled CEO just open tab after tab after tab and kick stuff off I mean this is stuff that this is stuff. These are all by the way real things that I am constantly using AI for so the last one is like A task that I use AI for is trying to rediscover potentially like cold leads that I might have talked to in the last like, you know, six months or so, you know, our product has changed a crazy amount and I might want to reproach them. And so the thing that I use for this, or had in the past been using for this, actually just started using instinct. Did you use instinct? Oh no, I had a bad experience with instinct. You had a bad experience with instinct.

37:30So the normal way I would do everything is still through coding agent, but I'll do one more prompt here. Can you use the GOG CLI to look for emails and calendar events I've had in the past six months with potential enterprise leads who might be useful for another outreach for warp factories?

38:00You can learn about warp factories at warp.dev slash factories and make me a Google sheet with the info on them and share the sheet link, but don't print out any specific customer email or name in this thread. What I like about this at the meta level is like, is this like your brain works where you're just like, I need to do the slide kick off the slide. I need to like.

38:28Update some of our sales position kick that off. I need to like follow up with cold leads like is this Yeah panel is this a reflection of your CEO brain because it's certainly a reflection of my brain Yeah, I mean if I were if I were in like Sales mode yeah go to market mode and like I am in in that mode quite a bit now unfortunately more more so than like Straight-up builder mode or engine manager mode. Although I do all these different things I'm constantly trying to find what is the right positioning? Are we communicating in these meetings in a way that lands? And it's so amazing to have this ability for me who can't design or draw at all to have this now superpower. And we can go, let's see how this figma is doing over here. Has it started to do it yet? Oh, it's starting.

39:22Oh, it's got some work to do. But it will do better. But yeah, if I was in sales mode, I'm trying to figure out, are we positioning right? What are people asking about? Yeah, and this is right. This is from our actual sales calls. And this is what I would say is the number one thing for the factory, the product category we're in, is buy versus build. And it's backed up by evidence, and it makes sense to me. Security comes up a lot.

39:51What's the workflow? What's the measurement? How do we manage costs? It's so cool. And so it's like what I would do is like, you know, I want to then go make sure that our sales deck, our website, all this stuff is speaking to the questions people have. I might turn this into like a literal FAQ. Like I think we have, you know, probably ability to improve that. Or I would just try and work this into our positioning, but.

40:19I'm constantly doing this and trying to understand if if what we're building is the right thing and we're positioning it the right way Rocket ship. Sorry. We're back at figure for those that are not watching we got a rocket ship We got a cloud of some sort. It's trying very good. Yeah, it will get better the rocket ships not terrible Um, Zach, this is, this is so fun. I want to go to quick lightning round questions and then we'll get you back to back on the factory floor. All right. First lightning round question. Everybody wants the factory. Everybody wants the go to market intern that will happily go through your call transcripts and the design intern that will happily make your ugly cloud slides as a CEO. But when you have the factory humming and when you're doing, I think it was like over 2000 PRs in the last month.

41:12Like, how do you keep things in the team from going, as I say, like chaos reigns? Like, how do you keep your arms around all that activity, all that work, all that context, all those tasks, and know at the highest level, you're doing the things that matter? It's a great question. Like, the kind of boring answer is like a lot of the stuff that we've always done as software engineers still applies, which is like, you know, we're dog fooding.

41:41So we're just like huge constant users of the thing that we're building and making sure that like the quality of the thing still works well. There's like cool knowledge transfer that's happening where it's I don't know if you've seen this too, but like the this there's like a kind of power law for like how these tools are used in terms of like we have some people on our team are super duper power users and other people are like kind of more at the average. And so there's this when you when you're working in this what seems like a very chaotic way in public with everyone slacking these factories all day you do get a chance to sort of see how like the the really expert people are using it and that kind of up levels other people on the team and then like I said earlier we're still doing you know it's not just like chaos like everyone like you know slop stuff into the machine all the time it's like we still have a product development process that

42:38You know is somewhat traditional a bunch of ways so it's like we do a whole bunch of user interviews we watch people use the product We do Design jams before we start building to not not so much like Figure out exactly like how the UI should look with just to make sure that we're tackling the right user stories Like because at the end of the day like doesn't matter how fast you build software It's like it's also solve some user problem and solve it in a good way and so we We're trying to figure out how to not lose the key parts of the human input here, but also use the fact that there's this magic technology that can make you just go much faster. I love it. Amen. I could not say it better. OK, last question, and then we will get you out of here. When your AI is not doing what you want? And also, I'm curious if this question is if you answer this question differently.

43:36when you're working with AI privately versus working in within Slack. With it's not doing what you want. What's your prompting strategy? Do you yell? I am lately, I will admit this to the audience. I am doing a lot of like, why are you like this? Why? Why? A lot of questioning. That's funny. I'm like a pretty level guy. I think if you ask the people on my team, I don't know. I've never really like...

44:05The yelling not my style I get like passive aggressive is kind of what I would say I Get I get like I rollie like really like this is what we're doing now Like you built this whole thing that no one asked you to build so I'll get like annoyed like in like subtle undertones, but I I'm not a I'm not a yellow and so I don't know. And I also try to just keep the perspective that this is just like a bonkers thing that I'm just like talking to this, talking to this thing that is doing this job that I've done for the last 20 years. And it's now it's like doing it kind of better than me. And so I don't know. I'm still like, I'm in like a little bit of like a wonder phase with it. I don't know if you've ever seen that Louis C.K. skit where he, he talks about.

44:59How when internet like Wi-Fi first got on to airplanes? Stop me if you know this, but it's like if the skitties like he's riding on an airplane It's like this like 20 years ago and there's Wi-Fi for the first time and he's just like this is incredible Everyone like this is like amazing and nobody's happy and he tells a story about how like the guy next to him is like trying to watch a YouTube video and like throwing his hands up like screw this like I can't get any signal and and Lucy case like Like this is bonkers like we're on an airplane. This thing is like going up to space give it a second And so I think it's it's so easy to lose perspective of like how wild this technology is like I'm I'm like I'm I'm generally like pretty Probably like kind of more patient with it than most I would say I love it. That's such a great perspective. Well Zach, this has been super fun Where can we find you and how can we be helpful to you? So you can find me personally like I'm on I'm on Twitter. I have

45:56Zach Lloyd tweets is my Twitter. You should obviously come check out warp at warp.dev. If you want to build software factories, I hardly even talked about it, but we have an extremely popular agentic terminal that's open source that you should also come check out and use. It's a great place to work with interactive coding agents. But yeah, this was awesome. I really appreciate you having me on. Yeah. Thanks for joining How I AI.

46:23Thanks so much for watching. If you enjoyed the show, please like and subscribe here on YouTube, or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiaipod.com. See you next time.