EVERY SPOKEN WORD
50 min read · 10,239 words- 0:00 – 2:38
Intro: five people, 10 weeks
- EKEddie Kim
We had no meetings, we had no tech specs, we had no Figmas, we had no Jira board where we tracked stories or tracked work. We had nothing. We used Cloudflare Worker for the actual agent loop and Vercel AI SDK. That's it.
- CVClaire Vo
People get really intimidated by the idea of building an agent, and I'm like, "Literally, it's an agent SDK running somewhere in the cloud, and if you use AI SDK, you get to switch your model." That's it. It can look up files. It can have tools. It's really not that scary and complicated.
- EKEddie Kim
Cofounder was primarily built by five folks over the course of 10 weeks from initial idea, zero code, to a tier-one launch at Gusto.
- CVClaire Vo
How did you all make those precious decisions that only genius product managers can make about in or out of scope, will this matter?
- EKEddie Kim
We would build features, and we'd just have a discussion, like, "Does this make sense to have or not?" If it is, then it would get code reviewed right then and there, and if not, we would just delete it.
- CVClaire Vo
I call this the trash-can method of software engineering right now, where you can actually trash all the code, start like a /V2 branch, and rebuild it from scratch, and it's totally reasonable to do because the cost of the code is so low. Welcome back to How I AI. I'm Claire Vo, product leader and AI obsessive here on a mission to help you build better with these new tools. Today, I have Eddie Kim, CTO and cofounder of Gusto, and he's gonna show us how he, three engineers, and one designer completely rebuilt their app in just 10 weeks. This is not a small company, and yet they're shipping like they're a startup. Let's get to it. This episode is brought to you by Magic Patterns. Today's engineers use Cursor and Claude Code to ship features in hours that used to take weeks. If you're a designer or PM, you've probably felt a shift, too. The pressure to move faster, validate sooner, and keep up with a team that's operating at a completely different speed. You've already tried AI prototyping tools to close that gap, but if your prototypes don't look like your actual product, it doesn't matter how fast you can build. You still end up redrawing it by hand. Magic Patterns takes your product team from idea to production and works from your real design system. When you build a prototype, what you get back actually looks like your product. You'll validate faster, get alignment sooner, and when it's time to build, engineers can connect your prototype to Cursor or Claude Code with the Magic Patterns MCP to pick up where you left off. Your eng team has their AI advantage. Make Magic Patterns yours. Try it today at magicpatterns.com/howiai.
- 2:38 – 8:32
The origins of Cofounder
- CVClaire Vo
Eddie, thank you for joining How I AI. I'm so excited you reached out to chat because one of my favorite themes that I'm seeing right now is CEOs, CTOs, founders, executives getting back to building product. And you're here to tell us how you built some product with the team both very fast and in a completely different way.
- EKEddie Kim
Yeah. Thanks for having me, and, uh, great to connect again.
- CVClaire Vo
Yeah. So tell us the story of Cofounder and why you think this is, you know, given all your experience, you know, running this company, being a leader, being a builder, why this is so different than what you've seen before.
- EKEddie Kim
So first of all, the product is really different from anything that we've built before, but, uh, what I'm r- actually really excited is kind of more of how we built this and how we can take the learnings that we had, um, in building Cofounder is the quality and the speed in which we built this and apply this to, you know, the, the rest of our R&D organization here at Gusto, of which, you know, we have over 1,000 people. And so I think we're just... You know, I feel like I just discovered on something, like-
- CVClaire Vo
[laughs]
- EKEddie Kim
... really incredible, and I just wanna, like, kinda figure out how do we spread the word to not just our company to, but to any kind of engineering, um, design, or product management discipline person.
- CVClaire Vo
And so you say you have about 1,000 people in your R&D organization, but remind me, how many people did it take to build this product?
- EKEddie Kim
Gusto Cofounder was primarily built by, uh, five folks: myself, three engineers, I count myself as an engineer, so four engineers, and one designer. So we had one designer and four engineers, and we, we built it over the course of 10 weeks from initial idea, zero code, um, to 10 weeks shipping it to a tier-one launch at, at Gusto.
- CVClaire Vo
It's gotta feel so mu- so fun. I don't know if you're like me. I spent the past couple years, uh, pre-AI spending so much of my time, like, prioritizing and planning out quarters and saying, "Can this come in Q1, or is this gonna be a next fiscal year thing?" And now where you can take, you know, peel off less than half a dozen folks and ship-
- EKEddie Kim
Yeah
- CVClaire Vo
... a real product line completely net new in less than a quarter, it's pretty amazing.
- EKEddie Kim
It is incredible, and the origin of this was not on... It wasn't on any roadmap. It was not anything that we really thought about. It, it kinda just came about because, um, I was actually on vacation in February, and I was flying back from, uh, Madrid. Uh, my flight had a layover in London, and my f- m- the mid- the flight from Madrid to London was delayed, and I, I just barely missed my flight from London to San Francisco. And I had this, like, five-hour layover now because I missed the flight, and they had to book me on the next flight, and I was kinda pissed about it because I was so close. [laughs] And so I was just like, "Okay, now I have, like, five hours to, like, waste. I'm gonna get home super late in San Francisco. What do I do?" And I had been, like, kind of playing around with Claude Code. I was probably one of those, like, tech leaders that you sometimes hear about that, like, vibe code something over a weekend and then come to their engineering team and is like, "Look, I built this whole thing." Why can't you do it yourself? You know, like, and then just kinda like pisses people off because, you know, first of all, that was like completely vibe coded. It's not production ready. Um, but that was, that was my start into it, as I started using Claude Code a lot more, first to prototype things, and just kinda like, you know, materialize random ideas that I would have. And so in this, like, five-hour layover, I just took out my computer and started Claude coding this, um, idea that had been percolating in the back of my mind, and just seeing how far I can get with it. And by the time I had actually landed in San Francisco, um, I had this, like, prototype of, of what ultimately became Gusto Cofounder. And, um, I just took it to a few engineers that I talk to regularly, our, our senior engineers, and I talked to Katie Kovalcin, our designer, and we just started, like, riffing on the idea a little bit. The ultimate, uh, materialization of Gusto Cofounder is a little bit different from that prototype that I had made. Um, but that was the really the origin of this all, of this all. And 10 weeks after that, like, we, we shipped this thing.
- CVClaire Vo
So what I love about this story, I'm gonna take a little detour, because I've heard this over and over again from friends, is you know what I think companies need to give? Just a little bit more time off. Parental leave and, like, long flights. That is where I have heard the vibe coding magic happens over and over again. Like, "I was on vacation-"
- EKEddie Kim
Yeah
- CVClaire Vo
"... but [laughs] I, I Claude coded-"
- EKEddie Kim
Right
- CVClaire Vo
"... something awesome," or, "I was on parental leave and I've got, like, a baby in one arm and, like, Codex in, in the other, and I've shipped something." I just think it's gonna, it's gonna trickle down into, like, maker schedules a little bit more, where if you can give people just a block of time where they're not in meetings, we can move product forward-
- EKEddie Kim
Yeah
- CVClaire Vo
... a, a lot more meaningfully. So that's a little, a little hypothesis that I have about how, how some of our work might need to shift.
- EKEddie Kim
I, I totally agree. Like, now after c- going through this experience, I mean, I, I kinda wanna take more vacation, honestly [laughs] 'cause, like, I actually, I actually went to my wife, like, "We should take another vacation because, like, this huge thing came out of the last vacation that, that, that we took, and so maybe, like, another thing will come out of it. So let's go, like, let's figure out where to go." And then, you know, if I have a five-hour layover, I'm actually gonna be really, really happy about that.
- CVClaire Vo
Okay. This is how every, uh, CEO or executive can land the AI adoption pitch. It's like, "Look, if you go on vacation and vibe code something awesome [laughs] , we're, we're happy to give you,
- 8:32 – 12:50
Inside the 10-week build process
- CVClaire Vo
happy to give you more." Well, let's go back to how you built this. So you were on a layover. You had this idea. It was kinda, like, percolating in the back of your mind. You built a prototype. You brought it back to this, like, council, I call them the council of elders, like, this council of, of product builders or engineers just saying, like, "What, what would it take?" Tell me, though, how you, how those 10 weeks actually happened, and maybe show us some of the process and some of the artifacts along the way that were a little bit different.
- EKEddie Kim
Yeah. I mean, there was no, like, official council. It was, like, just senior engineers that I regularly, like, ICs that I regularly would talk to. And, you know, I, I recorded a Loom of this thing and I just started sharing it around. Um, and these were the folks that kinda, like, engaged a little bit more in the conversation, like, "What about that? What about that? That's pretty cool." And then so we have a, at, at our company this thing called Anchor Week, uh, which happens quarterly. We all, like, kind of the senior leaders and senior ICs, um, across the company, they, they meet in one of our offices. This particular one, uh, was in March, uh, in, in Denver, Colorado, in our office out there. And so we just reserved a room that Thursday, I think it was, like, March 20- 20th or something like that, and we just started, like, whiteboarding with this, like, group of five that I had sort of, you know, had, that had expressed some interest in this. Uh, we just white boarded, like, what this would potentially look like. And it was just, like, literally a, a, a page of the Gusto Cofounder app, and we just got to building. The crazy thing is this was more defined, our build process was more defined by, like, what we didn't do versus what, what we did. Uh, we actually just zeroed everything out. We had no meetings. We had no tech specs. We had no Figmas. We had no Jira board where we tracked stories or tracked work. Uh, we had no standups, no retros. We had nothing.
- CVClaire Vo
Yeah.
- EKEddie Kim
The only thing we decided to keep was a 24/7 perma-Zoom, which is basically a Zoom room that we just keep, 'cause every, 'cause every- everybody's remote o- on, in this particular group, and we just had this Zoom room that's going 24/7. And some people like, like to honestly stay in there all day and just, like, do their work. They just kind of, like, sit there quietly. Um, and some people will, like, kinda pop in and out when they need something. That was the only structured thing that we had, was this Zoom. It was, like, literally just Zoom, a lot of Claude Code tokens, and some, like, really passionate people about turning this thing in- into a reality. And that lo- that whiteboard, um, which I took a photo of, was, like, literally the only documentation that we ever produced in this whole 10-week process. And I can't tell you how many times I loved, as people, like, caught wind of this thing getting built, they were like, "Oh, can you send some documentation on how this works?"
- CVClaire Vo
[laughs]
- EKEddie Kim
And, uh, I love just saying, "We don't have any documentation."
- CVClaire Vo
Okay, so this is the whiteboard. And just for folks that are not listening, it's a scribble, a wire frame that says chat. It's a chart. It's a thing that says task name, and then, like, a couple components on the side that are not very well specced out. And what you're telling me as CTO is we built the entire product basically off this Claude Code in a perma-Zoom.
- EKEddie Kim
Yeah, totally. And, and if you look at... Obviously, things have evolved a bit, but if you look at sort of the core primitives and core functionality of Gusto Cofounder, um, it's largely the same. They kinda, like, changed the names of things, but one of the main things in- Gusto Cofounder is what we call now an automation, and it's basically you just create these automations that, like, run these workflows for you. Um, that's what you see here on this whiteboard called tasks, right? So it's like tasks have task runs, um, and that- that's exactly what we have in Cofounder today. Um, we have assets. So, so tasks runs can produce these, um, charts or documents or markdown files. We called those in this whiteboard here assets, but, uh, eventually those got, got, got, got renamed to artifacts.
- CVClaire Vo
Mm-hmm.
- EKEddie Kim
Um, and then you obviously have chats. You have, like, suggested tasks. So like, basically this, like, if you look at Cofounder today, it is, like, the, the actual, like, materialization of what you have on this whiteboard. Looking back on it, I, I'm actually kind of surprised right now how, how close
- 12:50 – 14:38
Building with no PMs
- EKEddie Kim
we-
- CVClaire Vo
[laughs]
- EKEddie Kim
... we stuck to this.
- CVClaire Vo
So I have to ask you a couple tactical questions about how you pulled th- this off, because that's what people listening are gonna wanna know. So my first observation is you said you had four engineers and a designer. I don't, I don't hear a product manager in there. So how did you all make, uh, you know, those precious decisions that only genius product managers can make about in or out of scope, will this matter? I mean, this sort of feels like the thing where you just had conviction and knew you needed to build it. But, you know-
- EKEddie Kim
Yeah
- CVClaire Vo
... in this world where there was no actual titled product manager on the team, how did you approach product decisions across this team of five?
- EKEddie Kim
Yeah. I w- I would say everybody was kind of a product manager. We would build features, and we would go in that perma-Zoom and sort of share it with each other, and we'd just have a discussion, like, "Does this make sense to have or not?" If it is, then, like, it would get code reviewed right then and there. And if not, like, we would just delete it.
- CVClaire Vo
[laughs]
- EKEddie Kim
And normally that would be really, really hard to do, 'cause, like, it takes so long to build something, but these days with Claude Code, we literally, like, write some- a feature, we submit... We open a pull request, and this is not a draft pull request. This is actually a pull request, um, that is ready for a, a, a human code review, and we discuss it. We discuss if that's the thing that we want to have, a functionality that we want to have, um, and we're okay with deleting that pull request if, if the answer is no, right? You have a perfectly good pull request that was written-
- CVClaire Vo
[laughs]
- EKEddie Kim
... that's, like, ready for human review. It's not slo- You actually, like, spent time to, like, you know, make sure this code works and, and is written really well, and then you just close it sometimes. That was, like, the... That was, like, how we figured out what, decided what goes in and what, what doesn't go into this feature.
- 14:38 – 17:15
The “trash can” method
- EKEddie Kim
Like, the, the cost to write code is now so low that you can actually, uh, build, uh, products in, in this way and whereas I think you couldn't do that, you know, six months ago.
- CVClaire Vo
Yeah. I call this the trash-can method of software engineering right now, where you build code and you're l- like, actually literally okay with throwing it in the trash.
- EKEddie Kim
Yeah.
- CVClaire Vo
And I, I see two models of this. One is exactly what you say, like a PR and maybe a preview vanch- branch to even validate, is this a thing we wanna build? And if the answer is no, you just close the PR. The other version of this that I do quite frequently is, let's say we ship this V1 in 10 weeks. Customers start to use it, and then we actually have a sense of what the product shape and architecture should be. Like, it's very cheap to just build again from zero. You don't even have to build on top of what you've built. You can actually trash all the code, start, like, a /V2 branch, and rebuild it from scratch, and it's totally reasonable to do because of the co- the cost of the code just is, is so low.
- EKEddie Kim
Yeah. I have a funny story about that because, um, this prototype that I brought to the team, um, I was, you know, I was pretty, pretty happy with it. Like, and when we decided in that, um, that whiteboarding session to, like, actually, like, go ahead and build this, like, my assumption was that we're [laughs] gonna continue to build on my prototype. And so someone, one of the engineers brought up, "Hey, what do you think about, like, uh, using, uh, building this in TypeScript and using a Cloudflare Worker and kinda like making the actual agent, like, sort of a stateless thing that sits in its own repo?" And I was like... I really didn't wanna do it. I feel like, I felt like this is my code, like, it was good code, and here they were suggesting to start, start from scratch. And ultimately, like, I, I, you know, I trusted them, so I, we agreed to it. We deleted my code, and then we started from, from scratch on that day. Um, in hindsight, that was, like, absolutely the best decision, and now mo- But, but I think back then, I, I had a lot of discomfort with that because, like, I had invested, you know, um, that was my code. I, like, I don't like, you don't like to delete perfectly good code.
- CVClaire Vo
[laughs]
- EKEddie Kim
Like throwing something, some good food in the trash. Uh, but now, like, I'm totally used to it, right? It's, it's, it's... There's no, like, sense of loss when that happens anymore.
- CVClaire Vo
Yeah. It's, it's totally... I- it is just totally wild to me how, how frequently I find myself writing lines and lines of code that ultimately n- are, are great and never make it, either because they don't hit my product bar or they just aren't technically how we wanna implement, um, and then how often I'm just, like, tau- like, major red diffs,
- 17:15 – 19:10
The stack architecture
- CVClaire Vo
uh, all the time-
- EKEddie Kim
Yeah. Totally
- CVClaire Vo
... to just re-architect stuff. I do wanna ask you a quick question about architecture. Tell us a little bit about, um, Cofounder and kinda some of the primitives behind the scene. I heard you say Cloudflare Workers. People are actually pretty interested on how to technically build agentic products, and so I'm curious kinda what stack you all landed on and, and why and how you, how you chose that architecture.
- EKEddie Kim
Our stack is surprisingly simple. We, uh, build on... We use Cloudflare Worker for the actual agent loop, um, and Vercel, um, AI SDK. Uh, that's it. Uh, we don't have any other harness on top of that. Everything else, uh, was built in-house. You know, in the past I would've thought about how to use, you know, some third-party tool for memory or planning or things like that, and It's really just, you know, memory to us is a tool that writes to a database column called [laughs] memory, and that simple, right? Everything is just, like, all the harnesses and, or... and things that we used to build, like to, as complex, like AI, uh, agent loop stack, I, I think is no longer needed. It, it was literally just, um, um, Cloud- of Cloud- Cloudflare Worker and, uh, and Vercel.
- CVClaire Vo
Ah, I love it. That's, uh, very, very similar to my stack at, at ChatPRD, so it's, it's good to hear that. You know, people get really intimidated by the idea of building an agent, and I'm like, literally, it's an agent SDK running somewhere in the cloud, and if you use AI SDK-
- EKEddie Kim
Yeah
- CVClaire Vo
... you could switch your, switch, switch your model. That's it. Like this-
- EKEddie Kim
Right
- CVClaire Vo
... it, it can, it can look up files. It can have tools. It's really not that scary-
- EKEddie Kim
Yeah
- CVClaire Vo
... and complicated. Um-
- EKEddie Kim
Yeah. There's not even... I was, like, blown away, 'cause it was my first time using it, that there's not even a, a, a loop. There's not a while loop somewhere, right? [laughs] You just, like, it's called stream, and it, it takes care of the loop for you. It's crazy.
- 19:10 – 22:03
Shipping to production from day one
- CVClaire Vo
Yeah. Well, I have another question technically on how you, how you ran this, because PR as, like, the PRD is almost, almost what I'm hearing, which is PR is the proposal of what to build, how it gets built, the solution. You look at it in code, and so you've almost compressed that, that loop. Were you merging those into your production app and putting them behind a feature flag, and just... Is that how you were technically managing this development process?
- EKEddie Kim
Yeah, exactly. So, I mean, that, that is one of the benefits of, like, kind of a zero to one type thing. You may not be able to do that in all instances. Um, but we had essentially a, a hidden page in our web app, and we would land stuff into that hidden page. It would be on production, and then we would sort of, like, chip away at it. Like, I think the analogy we use a lot was, like, we started with a block of marble, and we're just sl- slowly kinda, like, chipping at this thing and forming it into, like, a piece of art over time, and we're doing that in production in place. So one of the really cool things that we did, uh, which I would highly recommend, is Katie, our designer, she actually shipped, started shipping to production, like a, a faked experience essentially. So it had, like, the UI, the k- the thing that we white boarded, but if you go in and, like, you know, hit, put in some text into the text field and hit submit, it would just give you the same response, like, uh, every single time, right? It's not actually going to any kind of agent loop. It's not hitting any kind of database. It's a pure front end. It's kinda like what, what you would maybe build as a first pass on Lovable or, or, or something like that. And that actually got shipped to production behind this feature flag, and then s- p- in parallel, the engineers would start to build out the data models. Uh, they'd build the d- the agent loop, and they would start to connect this to the faked front-end experience. And the front end would stay the same, but the canned, like, responses would get slowly, and in place, not even better, like they would actually be, like, real, right? And so you would see this thing kinda like morph from, like, um, a, a literal prototype that you would normally have thrown away because, like, it's just for demonstration purpose, but it would actually turn... We would, like, like literally breathe life into this thing over time, and that's kinda how we, how we built this. Um, at the same time we would have engineers, like, build features, and they would, you know, have to do some front-end stuff. They would, they would ship the design for this, right? And the functionality on the back end would work really well, but then, you know, the front end probably could use some improvement there. And we would ship that, too, right? And then, and then Katie, the designer, would then go in and sort of, like, you know, make, make the experience a lot better on the front end. And so that was a- another example of, like, just shipping something into production and then, like, continuing to chip, chip away at it to make it better over time. So if you looked at it at any given time, there was always something wrong with it, like, in production. But then ev- gra- over time, like, it
- 22:03 – 29:05
How a designer became a top engineer
- EKEddie Kim
turned into, like, this really nice thing.
- CVClaire Vo
And tell me a little bit more about Katie. We might have her on, on the podcast. But Katie, the designer, is shipping stuff into production. Her code is the skeleton on which a lot of this functionality is, is being built. Tell me how... You know, was she, was she technical? Is she technical? Was she a software engineer? How did she come to shipping code? Like, what, what blew your mind about her role in this team?
- EKEddie Kim
W- what blew my mind was that she w- turned into this incredible engineer, and I was just looking at our, our, our, our PR stats, which we use this, we use a tool called DX for it. She, across our entire R&D org, she is ni- in the 94th percentile of, uh, true throughput, which is a measure of, like, how many PRs you're landing into production, and that includes every single engineer, like ch- classically trained software engineer in the company, right? She's, out of 20, she's, she's the top, right? Uh, which is, which is kind of insane, and it's really good code. Like, I asked her, like, how, how, "What is special about you, and how do we get more of [laughs] this, like, across, you know, design and, and product management?" And her answer was basically twofold. One is that she, she's not an engineer, uh, she's not a software developer, but sh- she feels like she was a little bit more, like, technically curious than, than most designers, so she just kinda has a little bit of that more technical bent. And then most importantly is that she had a team of, like, three or four engineers, particularly on this team, that was willing to actually, you know, review her code, like give her feedback, um, show her, like, how to prompt Claude a little bit better and, like, also how to judge, um, that taste of, like, what is actually good code that it's producing and what is not. We took the time to kinda, like, you know, uh, pair, pair with her, right? Whereas I think a lot of engineers, what I hear them say is, like, "Well, it just slows us down, and, like, designers should just focus on, uh, producing Figma so that we can, like, really focus on turning that into real products." And yeah, that's true in the short term, but, like, now I think once you make that investment, you have a support- ... a ven- a software developer, uh, around her, um, or any designer, I think the divid- dividends pay off really, really quickly.
- CVClaire Vo
This makes my heart grow 10 sizes. As someone who folks don't know, I did not get a software engineering degree, and yet I, I believe I can cook. Um, I have [laughs] and I've been coding for over-
- EKEddie Kim
Yeah
- CVClaire Vo
... 20 years. I've run very large engineering organizations, and a lot of that was early in my career, folks, shout out to, like, Dave and Neyland and Jeremy, like, were willing to sit with me and pair with me and answer questions, and tolerate where my ambition outstripped my technical ability. Now, you know, even with these AI tools, you sort of have that very patient pair programmer next to you. But I do think culturally it's very, very important for software engineering teams to extend that mentorship and guidance and feedback loop to their non-engineering partners. And this is a stress test I give to a lot of teams, because I hear a lot of teams being really overwhelmed by code review and being w- really overwhelmed by, like, what may- maybe they'll call, like, slop PRs from non-technical folks. And I just say, like, on average, is your engineering team's PRs getting faster review than your non-engineering team's PRs? And, like, across the board, people are like, "Yeah, of course they are." I'm like, that is an anti-pattern. You need to prioritize reviewing these non-engineering PRs just as high as you do your engineering ones because you can give feedback, you can create systems that improve code quality. Um, a lot of those PRs are actually really good ideas. Um-
- EKEddie Kim
Yeah
- CVClaire Vo
... and so I do think there's this cultural aspect to it that I'm really pleased to hear you've, you've unhooked, because I think it's gonna pay dividends over the long term.
- EKEddie Kim
Yeah, 100% agree. And, and our priority has, uh, always been, uh, PR reviews.
- CVClaire Vo
Mm-hmm.
- EKEddie Kim
Um, I think we did an analysis, and I think our median PR review time was nine minutes.
- CVClaire Vo
On this team?
- EKEddie Kim
On this team, yeah.
- CVClaire Vo
Ugh, I love it.
- EKEddie Kim
Not, definitely not in the, in the, in the R&D org, but definitely on their team. And, and the reason why is, like, there would always be someone on this perma-Zoom. And so-
- CVClaire Vo
Yep
- EKEddie Kim
... like, you just show up in this perma- perma-Zoom and say, "I have this PR ready. Can we talk about it?" And then someone, um, sometimes in a group setting, sometimes you just go in a breakout room with someone. We... You just kinda talk through it together and, and review it together.
- CVClaire Vo
This episode is brought to you by Jira Product Discovery. AI has made individual PMs incredibly productive, but multiplayer mode is where it still breaks, getting everyone aligned on what should actually get built. Decisions live in a markdown file from last week, the roadmap's a spreadsheet no one's looking at. Jira Product Discovery is where teams actually decide what to build, capture ideas, prioritize them as a team, and share a living roadmap everyone works from. It's powered by Atlassian's teamwork graph, so it can pull in customer feedback, what your team's shipped, plus your goals, and suggest what to build next. And when a decision is made, you can hand it off straight to Jira, so a developer or even an agent can pick it up and start building. Teams at Canva, Deliveroo, and Toast already use Jira Product Discovery. Join more than 25,000 teams at atlassian.com/howiai. Start building the right things together. Does this bring you back to, like, early founder days?
- EKEddie Kim
It did feel a lot like the, like startups. Actually, when we started-
- CVClaire Vo
Yeah
- EKEddie Kim
... um, ev- also everybody coded back then.
- CVClaire Vo
Yeah.
- EKEddie Kim
Like, we hired designers that, like, you know, um... I mean, it's a different type of code. They, they wrote a lot of, like, HTML and CSS and maybe some light JavaScript, but they coded, right? They, they-
- CVClaire Vo
Yeah
- EKEddie Kim
... actually, um, uh, opened pull requests and, and merged it.
- CVClaire Vo
Mm-hmm.
- EKEddie Kim
Um, over time, I, I think that kinda went away and we said, "Oh, like, everybody's gotta go into these, like, traditional swim lanes." Um, and this was, like, kind of almost a throwback to when we just started, right? Uh, we just had maybe, like, a few whiteboards and we kinda, like, discussed in real time what we were gonna build, and we built it. And, um, yeah, and, and honestly, I mean, it w- it was a lot of work. I, I, I will say that to ship something like this in 10 weeks did take a lot of, like, nights and, and weekend time. Um, but ev- I didn't ask anybody to do it. They just did it because people were so, um, passionate about what we were doing, and honestly-
- CVClaire Vo
Yep
- EKEddie Kim
... they were having a lot of fun.
- CVClaire Vo
Yep.
- 29:05 – 31:45
Demo: Cofounder over text and Slack
- CVClaire Vo
You've, you've painted this vision. People are gonna walk away, and unfortunately, their teams are gonna be like, "You can ship this huge product in 10 weeks. It'll only take five people. I want nine-minute pr- PR review, [laughs] review time." So you're setting the bar high. But let's, like, let's prove it. I mean, show, show us what you built, and then maybe we'd love to see how you personally use Claude Code or used Claude Code to contribute to this product.
- EKEddie Kim
Yeah, sounds great. Let me, um, just share my screen here. And I'll, I'll... For the folks on audio, I'll try to walk through what's on my screen. This is Gusto. This is the Gusto that everybody knows, right? This is kind of, uh, [laughs] ironically, we call it Classic now.
- CVClaire Vo
[laughs]
- EKEddie Kim
Uh, when you're a co-founder, we would never use... But if you're, if you're in the co-founder group, like, you get to call the traditional Gusto Gusto Classic.
- CVClaire Vo
[laughs]
- EKEddie Kim
This is Gusto, uh, Cofounder here. It does the things, you know, basic stuff. I don't think any of this stuff is particularly interesting. Um, it's kinda like the normal agent loop that's connected to the tools. Um, I would say the really interesting thing about this from a user perspective is that it comes out of the box with all of the things that Gusto is, uh, is already doing for you, right? It has all the information that Gusto already has about your business, like your employees, uh, your payrolls, your schedules, uh, your time off requests, and, and things like that. And one of the things that was really important to us was just being able to communicate it ... communicate with it, not just through the web, but actually we want people to primarily talk to it through SMS or, or Slack actually, right? So here I'm gonna say something like, "Do I have any time off requests that I need to approve?" And it would be the same exact thing as if I were to like ask this in the, in the web application. Um, it's calling the same tools, and it's gonna respond to me, um, in, through the same channels. By the way, for those listening in, I'm, I'm showing a screen of my phone, basically.
- CVClaire Vo
Right.
- EKEddie Kim
My, my, uh, messaging app on my, on my Android phone.
- CVClaire Vo
And what-
- EKEddie Kim
And I just typed in, "Do I have any time off requests that I need to approve?"
- CVClaire Vo
What I'd imagine is this sort of like multi-channel experience is really important for kind of like small business owners in particular, who are probably like running around, doing stuff, al- always operating on, on their phone. Um, and so I do think it's interesting, as somebody who has like built B2B-
- EKEddie Kim
Yep
- CVClaire Vo
... web apps for so long, to think now my surface area is texting. It's just a very interesting product design problem. Um, and then technical problem with, you know, how do you, how do you show streaming or latency or make sure people understand that you are working, um, you're working on it. So I, I think-
- EKEddie Kim
Yeah
- CVClaire Vo
... this whole surface
- 31:45 – 36:26
Demo: running a real payroll
- CVClaire Vo
area is very interesting.
- EKEddie Kim
Yeah, exactly. So we have right now today Slack and SMS.
- CVClaire Vo
Mm-hmm.
- EKEddie Kim
But, um, you know, I kinda wanna add like WhatsApp and Telegram.
- CVClaire Vo
Yeah.
- EKEddie Kim
I, I think that's kinda one of the things I learned from using OpenClaw of like the power-
- CVClaire Vo
Yeah
- EKEddie Kim
... of like the, these, uh, uh, messaging channels. Okay, so it responded, um, actually looked up that there is someone named Todd, uh, who, uh, has a time off request. And, um, I could just say yes, and it'll actually approve that time off request, so I don't have to do that in the web app anymore. So I'll just let that run so we can come back to it to, uh, see that it actually approved it. But I wanna show something that's a little bit more interesting and, and more, more complex. Uh, so this actually came from a real customer, and, uh, this cu- particular customer that we have is a massage spa in New York City, and what they do is they use Mindbody to track all of their work of, uh, of their massage therapists. And they basically have, you know, how many 60-minute massages did they do, how many 90-minute massages. They also get paid like a bonus if they do certain upsells, like hot stone or CBD oil, and they have like a rate for that. They also like decide how they split... They decided to split their tips, like, uh, as like they group their tips together and, and they split it. So what this owner has to do every week is they actually, you know, they export something from Mindbody, they put it into a Google spreadsheet like this, then they actually run these calculations of like how much to pay them in terms of bonus and commission and tips, and then and only then they actually go into Gusto and, you know, they, they go to the run payroll page, and then they, um, um, they actually input all that, all that in, right? That part is really fast, of course, but it's all this like what I call the work before the work that a business that is not using AI has to do to run their payroll every single week. And this is like week in and week out, right? And so in Gusto Cofounder, I have a set of connectors where I can... Gusto Cofounder can actually access third-party systems like QuickBooks, Google Sheets, um, Notion, and things like that. And what I can do is actually just literally say my process here. Uh, so I wrote here like, "Hey, Gusto Cofounder, I need you to run my payroll. Um, look at this spreadsheet that's called Export from Mindbody, and here's how I calculate it. You know, for every hot stone upsell, add $15 of bonus for that therapist. For every, every CBD oil, add $20 bonus for that therapist. We pool tips, so just take the group tips amount and divide it by how many therapists we have." And it just goes. And it's kinda like Claude Code where it'll, it's going, it's going to that spreadsheet, it's pulling in the data, it's running those calculations, it's updating the payroll as you see here, and then it's actually gonna get to a point where it'll stop and say, "Here are the amounts. Do you want me to actually submit this payroll?" And I'll say, uh, yes, and, and it'll, it'll actually submit and, and run that payroll. So basically you can see here that it's calculated all my payrolls, um, the hours, the bonuses, the total payroll amounts. And I'll just type in, "I'd like to submit my payroll," and it'll actually submit the payroll.
- CVClaire Vo
Amazing. So a- and all this came out of a vibe coded prototype because you had a layover. And this is real-
- EKEddie Kim
Exactly
- CVClaire Vo
... like this is real business, business data. And so, you know, when I'm talking to leaders at companies, they tell me, "Oh my gosh, Claire, I am so excited about our December AI launch." And I'm like, "December? It is June. Like, what are you talking about?"
- EKEddie Kim
Right.
- CVClaire Vo
"You need to do this today." And so I think, you know, one of the meta stories of this is like bringing forward your ambitious ideas and just executing on them quickly is really possible with not that much investment. You know, the other thing that I think about is five people for 10 weeks in an R&D organization of 1,000, let's say at the end of the day you ship something, you're like, "Eh, I just, customers don't want it," is actually not that expensive of an outlay. Like it, it-
- EKEddie Kim
Yeah. No
- CVClaire Vo
... feels like a lot maybe, but it's, it's a very small fraction of your overall R&D investment, and the payoff can be very huge. And so part of the advice I give people that I think you're encapsulating is you can be a lot more ambitious, um, and you can, you can afford a lot more risk in your product development process.
- EKEddie Kim
100%, yeah. Just imagine if you had maybe 10 of those going.
- CVClaire Vo
Yeah.
- EKEddie Kim
Which even if you multiply this by 10, that's not, even that's not a big investment-
- CVClaire Vo
Right
- EKEddie Kim
... across a company of 1,000 in, in R&D. You know, you're gonna have like two or three of those, I think-
- CVClaire Vo
That, that hit
- EKEddie Kim
... meaningfully change the trajectory of the business.
- 36:26 – 39:39
Live coding with evals in Claude Code
- CVClaire Vo
Yeah. I love it. Well, okay, and then let's prove, you said at the very beginning, "Well, I consider myself an engineer on the team." So tell me a little bit about how you're using Claude Code or maybe show, show a little bit of your setup that you find useful.
- EKEddie Kim
It's funny, I was looking at some user feedback, um, this morning. And I had a feature that, um, I wanted to build, and so I thought maybe we could just build it together right now.
- CVClaire Vo
Yeah, let's do it.
- EKEddie Kim
Um, just give a little overview of how, how I write code, how I Claude code. All right, so this came out of some user, um, feedback. We were talking to customers since we've launched, and I actually wrote this in a GitHub issue where, uh, we had this issue where if Gusto Cofounder says how to do something in Gusto Classic, um, it says, "Oh, go click on this link and that link," and that doesn't make any sense based on the page that the user is on because they're not in Gusto Classic, right? So we need to basically tell them, "Go to Cl- Gusto Classic first." Um, so I basically, like, copied a example, um, [lip smack] a user conversation that happened here where it caused some confusion. So it feels like cheating almost, is, um, I'm gonna start Claude Code here on my terminal. Always, uh, you know, use-
- CVClaire Vo
Obviously-
- EKEddie Kim
... stage
- CVClaire Vo
... dangerously skipping permissions.
- EKEddie Kim
And I'm gonna just say, uh, by the way, I use Wispr Flow a lot. I barely type these days. So I'm gonna just say, "There's a customer issue that is outlined in this GitHub issue," and I'm gonna paste in actually just a link to that. "Can you please read this issue and come up with a fix for the problem that's outlined here? I'd love for you to first write an eval that fails to show that you can reproduce this issue. Then come up with a solution, and then prove that the solution works by, uh, showing that the eval now passes." And that's it. Um, it's gonna actually just read the whole issue. It's gonna look at the conversation, uh, where this problem surfaced. It's going to write an eval that fails, and then get that eval to pass. It's interesting. I was never actually a, a true, like, test-driven developer. Like, I never was, like could really get behind, like, writing a failing unit test first-
- CVClaire Vo
Yeah
- EKEddie Kim
... and then writing the code and getting the pass. But when it comes to, like, eval stuff, like AI stuff, like, it's basically kind of the only way we work now when we're trying to fix a, a conversation, right? So always write a eval, a failing eval first, then write the code to fix it, prove that it works by seeing that the eval passes, and then seeing how the rest of the evals in your suite pass, and then open up a PR. So, like, at this point, like, I like go grab a cup of coffee or, or maybe I'll start a second or third, uh, work item in a, in a separate Claude, uh, Code terminal and, and then just wait for it to, um, finish. Uh, when it's finished, and this is honestly the part that is the most important, is actually, like, reviewing the code that it wrote, the eval. In, in this case, it's probably gonna make a prompt change somewhere, uh, making sure that it's concise. Um, there's, like, judgment on, like, what the prompt should look like. And, and then and only then asking it to open up a pull request. Then I go to the Zoom, perma-Zoom in and, you know, uh, get someone to review this.
- 39:39 – 43:17
Recap: prototype, small team, permission
- CVClaire Vo
I, I love it. So I just wanna recap for everybody, 'cause there's so many good nuggets on how to build something in this, in this new world. And so the first thing is, it's okay to prototype an idea to get internal buy-in that we should get excited about something new. And you know, you did that. I think you have a lot of permission as, as co-founder and leader in this organization. But I think you would extend that permission to anybody on your team, right? If you have a good idea, let's prototype it and look at it. It seems like you-
- EKEddie Kim
Yeah
- CVClaire Vo
... gathered a team around who was most excited to build on this. It's something that I sort of heard, is you were like, people were leaning in, and it's almost like-
- EKEddie Kim
Yes
- CVClaire Vo
... the gravity of who was interested formed some of, of the team, which I think is, is quite, quite fascinating. [lip smack] Um-
- EKEddie Kim
Right
- CVClaire Vo
... I heard you kept-
- EKEddie Kim
Yeah
- CVClaire Vo
... kept the team small.
- EKEddie Kim
Yep.
- CVClaire Vo
No docs-
- EKEddie Kim
Very small
- CVClaire Vo
... no, no nothing.
- EKEddie Kim
No docs.
- CVClaire Vo
Um. [laughs]
- EKEddie Kim
Um, yeah, I mean, there were people that wanted... They, like, they really liked what was going on and they wanted to, like, contribute, but we kinda, like, intentionally kept it as small as possible-
- CVClaire Vo
Yeah
- EKEddie Kim
... because, um, we just were able to move really, really fast with a team of five. Now, that's not gonna stay like that forever. We're starting to add more people, uh, to the team, and more people are starting to help out. Um, but I think it was critical to keep it small in the beginning.
- CVClaire Vo
No, no one likes when I say this, but I say the, my secret trick to getting things to move fast is kicking people out of projects. [laughs] So I-
- EKEddie Kim
Yeah
- CVClaire Vo
... I cosign. It is an effective-
- EKEddie Kim
It's-
- CVClaire Vo
... tactic.
- EKEddie Kim
It is harsh, but true. Um, yeah, and I, I, I do, like, I think, so I think there's one important, um, difference here that, like, applies to this particular project that may not apply to others, right? And it's-
- CVClaire Vo
Mm-hmm
- EKEddie Kim
... I think it is honestly the fact that I, as one of the company's co-founder, was, was part of this, right? So I had, like, kinda the permission to, you know, break all the rules that we created at Gusto, right? N- if any other, like, team said, "Oh, we're not gonna, we're gonna skip tech specs and Figmas," they actually might get a slap on the, on the wrist about it. Um, and so how do, how do... I've been thinking a lot about how do you scale this to other teams, and I think, um, unlike me, where the permission is sort of implied, like, I think you actually have to go to these teams and say, "We, we are, we want you to work in this way, like, where you don't do any docs, no Figmas, no tech specs. We just want you to have a perma-Zoom, and, like, we're giving you permission to do it in that way." And in fact, I would e- go even further and say, uh, "We're not giving you permission to do it in any other way. Like, if you actually produce a doc or Figma, like, you will get a slap on the wrist because we explicitly don't want you to do that," right? That's one important difference. I, I, I think when you don't have, like, a co-founder on this team, like, you actually have to be more explicit, 'cause I have talked to teams that want to do it in this way, but they, they just don't feel like they're allowed to.
- CVClaire Vo
Yeah. This, this reminds me of what my friend Chintan at Coinbase did, is he actually, he does these extreme experiments with his engineering team. One that's my favorite to reference is he's like, "Delete your IDE." Like, "You are not allowed to have an IDE." Delete it.
- EKEddie Kim
Yeah.
- CVClaire Vo
Write code. Um, and his other one that he does is he's like, "You don't touch the outputs of agent code, you only get to touch the inputs. You only get to re-prompt, you don't get to rewrite the code." It's like a very-
- EKEddie Kim
Totally
- 43:17 – 48:44
Lightning round
- CVClaire Vo
different way. Um, you know, that, that brings me to a lightning round. We'll do lightning round. We're almost out of time and I wanna get you back to Claude coding, which I think is the most important thing any of us could be doing. So my first question-
- EKEddie Kim
Yes
- CVClaire Vo
... is, you know, coming off this conversation, do you really think docs are dead? Like, is this the way?
- EKEddie Kim
I think for a subset of projects, like kinda more zero to one, I think docs are absolutely dead.
- CVClaire Vo
I, you know what? People don't know this about ChatPRD, but my actual intention with ChatPRD is to be the one in the product management world that legitimately kills PRDs. And, and so I'm like the anti-PRD PRD maker, so I am all about this. I think this is truly the model. And, you know, even in my experience working with, uh, this is kind of breaking news, working with the new Fable model, is there are docs written now that are none of my business. That's what, that's my new, my new f- frame of, of mind is agents can write docs and they are absolutely none of my business and I will never be reading them. And that's actually-
- EKEddie Kim
Yeah [laughs]
- CVClaire Vo
... a very interesting [laughs] , interesting model where maybe docs exist but they're for the agents, not, not for the humans. Um-
- EKEddie Kim
Yeah, that's awesome
- CVClaire Vo
... my, my second question is about this, like, co-founder, executive leader role in building teams. I hear so much, or I see on LinkedIn like, oh my God, my CEO is, like, sending over Claude slop, or, you know, all of a sudden my CTO thinks that he can, he can, um, commit PRs to, to main. And there's actually a lot of, I think, a combination of, like, anxiety about the shifting more hands-on role of leadership, and then sort of an uneasiness when leaders who have maybe in the past, depending on your culture, have been, like, at a little bit more at arm's length with hands-on product development now are sitting with a team. And, you know, most, most teams that have really healthy cultures don't actually grapple with this, and so it seems like you all have a, a healthy culture and it creates not so much anxiety. But for, for orgs where you can imagine that anxiety exists, what perspective or advice would you give from the leadership side of that equation, um, that can make teams more excited to build with their co-founders, their CEOs, their CTOs, their, their VPs?
- EKEddie Kim
I think my advice to leaders is, like, actually get hands-on in building, like, production code. Don't just... I think, I think it is an important first step to build a prototype and come to your team and be like, "Look," like, "this is actually feasible and possible," right? And then, like, you know, like, that, that still, that still has value, right? But I, I do think that, and I've made this mistake before in the company where I've, like, literally done just that, um, it can lead to a little bit of, like, um, underappreciation of, like, the, like, the actual, um, nuances of the work. Like how much it, more work it takes to actually get something into, into real live production quality, like, stuff, right? And so I think my advice is, like, don't just stop there if you're a leader, right? Actually, um, be hands-on in, like, merging real reviewed, like, high-quality code. Um, and in my case, I kind of took it to an extreme where I, like, went into almost IC mode for the past 10 weeks and I was, like, literally building... I'm, like, 95th percentile on DX for the past three months. Uh, I... and just part of that was I wanted to prove that, like, I'm not here to just show you, like, prototypes and, and, and, like, tell you that you could move faster, right? I'm gonna prove it by actually going it, taking it all the way through.
- CVClaire Vo
I just, I could not agree more. This is just the moment where everybody has to be hands-on, and I tell a lot of executives, like, "Sorry, bud, it's time for the hard skill to, to show up again-"
- EKEddie Kim
Yeah
- CVClaire Vo
... not leadership inspiration, alignment. It's like get your hands in a, in a document, get your hands on the code, write a campaign-
- EKEddie Kim
Right
- CVClaire Vo
... build something. I think for two reasons. One, you have to be in it with your team to really understand, um, how your team should be working, and two, I think it's very hard to build great AI products if you are not spending all your time using AI products right now. It's just like, it's very hard to understand the primitives, the user experience, where it can solve problems, where it can't. And so a leader trying to come up with an AI, AI product strategy without spending all their time practically using AI products, I think is really hamstrung.
- EKEddie Kim
Yeah. I, I think, so one thing, like, that I'll disclose is that the original, original idea for Gusto Cofounder came from me actually just setting up OpenClaw myself, right? I had heard about it and I was like, "Yeah, cool. That sounds, like, really neat that you can, like, run an agent, personal agent on, on your own computer." Um, but it really took me setting it up myself and actually texting with it over Telegram to, one, like understand, like, the power of that-
- CVClaire Vo
Yeah
- EKEddie Kim
... like viscerally experience it, and then also, like, you know, learn what's wrong with it, right? It's incredibly hard to set up.
- CVClaire Vo
[laughs]
- EKEddie Kim
Um, you have to buy a Mac Mini, which you can't even get today, and that was, like, one of the p- the hypothesis of Co- cofounder, right? Like, we want it to be safe, um, you can... it runs on the cloud, but then also that's how we made, like, SMS and Slack a, a first-class, um, communication channel with it, right? And that, I don't, I don't think I would've gotten that insight if I didn't actually, like, set up an OpenClaw at my home
- 48:44 – 51:49
Where to find Eddie and Cofounder
- EKEddie Kim
myself.
- CVClaire Vo
I, I love it. I mean, I think every leader needs to feel, feel the Claw, um, for, for that exact reason. I, when I started using OpenClaw, I remember I turned to my husband and like, "Oh my God, I'm having a ChatGPT moment." In terms of it just changed my mental model of what- ... product could be in a way that I just-
- EKEddie Kim
Yeah
- CVClaire Vo
... hadn't felt or experienced prior to, like, e- even since, um, ChatGPT first came out. Even Claude Code didn't, like, change my world in the same way-
- EKEddie Kim
Right
- CVClaire Vo
... that, that OpenClaw really did.
- EKEddie Kim
Right. And, and, and you've probably heard of other people talking about th- that, like how it's like such a crazy, like, innovation, right?
- CVClaire Vo
Yeah.
- EKEddie Kim
But then you don't really, you, um, that, that's a problem. Like, there's so much press out there and, like, so much hyperbole that, like, you kind of become numb to it. So-
- CVClaire Vo
Yeah
- EKEddie Kim
... you do kind of have to experience it yourself, I think.
- CVClaire Vo
Yep. Completely agree. Okay, last question and then we will get you out of here. You know, when, when Claude is not writing a great eval, when it's not listening, when you know you're about to have to trash a PR, what is your prompting strategy to get it back on track?
- EKEddie Kim
I'm naturally a very polite person. [laughs] Uh, not confrontational, but I... And so I, I'm, I'm pretty nice to my Claude. I kind of like, you know, ask it nicely, "Why did it do this way?" Or like, "Could you please consider this?" And actually I, I, for me, I, I don't know if this is true, but I think there's a actual, like, practical benefit of it. I find that AI is so deferential and it just kind of like defaults to doing what you want it to do. But I actually want mine to challenge me, right? And like give me different r- uh, ways of doing things that might be better, ways of building things that might be better. Um, so I some, for some reason I just feel like kind of being polite, leaving it open-ended. Uh, if you think this is a good idea, could you try this? Like, 'cause I, I kind of want it to invite a little bit more of, like, pushback.
- CVClaire Vo
Yep. Yep. Love it. I, you know, most people are, are very polite. I am o- I'm often very polite unless it's gone real off the track, and then what I use is a 15.0, "No." I don't, I'm wasting tokens.
- EKEddie Kim
Yeah.
- CVClaire Vo
You know, it costs a drop of water, but I do it anyway. All right. Well, Eddie, this has been so fun. Where can we find you and how can we be helpful to you and the team?
- EKEddie Kim
Yeah, you could find Gusto Cofounder at gusto.com/cofounder. Um, we have a wait list, so if you're interested in it, please sign up for it and we'll give you access probably within a few days. Um, and check it out. Give us feedback.
- CVClaire Vo
Great. I'm a, I'm a very happy Gusto customer, so I'm gonna ask you to, to feature flag me into, into the beta, and I will send you all the feedback, and hopefully some PRs will come out of it.
- EKEddie Kim
I would love it.
- CVClaire Vo
Great. Well, thanks for joining, Eddie.
- EKEddie Kim
Thanks, Claire.
- CVClaire Vo
[upbeat music] Thanks 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 howiai pod.com. See you next time.
Episode duration: 51:51
Install uListen for AI-powered chat & search across the full episode — Get Full Transcript
Transcript of episode 5FKBkUCaLa8
