We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
cover of episode Announcing a brand-new podcast: “How I AI” with Claire Vo 🔥

Announcing a brand-new podcast: “How I AI” with Claire Vo 🔥

2025/4/22
logo of podcast Lenny's Podcast: Product | Growth | Career

Lenny's Podcast: Product | Growth | Career

AI Deep Dive AI Chapters Transcript
People
C
Claire
L
Lenny
S
Sahil
Topics
@Lenny : 我很高兴推出新的播客 "How I AI",该播客将展示人们如何利用AI工具来改善工作效率和质量。这个播客将提供实用且可操作的技巧和工作流程,帮助听众立即应用。@Claire Vo 是这个播客的完美主持人,她不仅谈论AI,而且亲身实践并不断分享学习成果。 Claire: "How I AI" 播客旨在探讨AI如何改变我们的工作方式。本期节目邀请了 Gumroad 的 CEO 和创始人 @Sahil Lavigna,他将分享如何利用AI来改进产品构建和代码编写,包括使用v0进行原型设计,使用Devin和Cursor进行代码编写,以及如何激励团队使用AI工具。 Sahil: 我利用AI工具,特别是v0、Devin和Cursor,极大地提高了我的工作效率。AI可以将原本需要两周才能完成的任务缩短到两小时内完成,效率提升了40倍。我使用AI工具来改进产品中的细节问题,例如替换日期选择器。我通常使用 v0 进行原型设计,然后使用 Devin 和 Cursor 进行代码编写。选择合适的工具和技术对于 AI 工具的有效使用至关重要。未来大部分的人工工程工作将集中在消除技术债务上,以便 AI 工程师能够更有效地交付功能。在使用 AI 工具时,应该在原型设计阶段投入更多时间,以获得更好的结果。利用AI工具进行产品迭代,可以快速尝试不同的功能和设计,而不会浪费过多时间和精力。在团队层面有效使用 AI 工具需要相应的运营机制和企业文化来支持。有效使用AI工具需要激励员工,并让其参与其中。Gumroad 通过设立奖金等方式来激励员工学习和使用 AI 工具。AI 工具在各个部门都有应用潜力,例如营销、销售和客户支持。当 AI 工具足够强大时,资源的限制将不再是主要问题,团队需要思考更具有创造性的工作。即使在 AI 时代,人类仍然需要进行研究和探索,以发现新的机会和可能性。AI 正在提高内容创作的门槛,未来人们需要创造更优质的内容才能脱颖而出。使用大写字母和“等等”等技巧可以提高 AI 对指令的理解和执行效率。可以通过推特或私信与 Sahil 联系,并提供反馈。v0 是学习使用 AI 工具的最佳起点,因为它易于上手且能展示 AI 的可能性。

Deep Dive

Chapters
The podcast episode announces the launch of a new podcast called "How I AI" with Claire Vo, focusing on practical AI use cases in various fields. It promises 30-minute episodes with live demos and actionable tips.
  • Launch of "How I AI" podcast under Lenny's Podcast Network
  • Hosted by Claire Vo, engineer and three-time CPO
  • Focus on practical AI use cases, live demos, and actionable tips
  • 30-minute episode format

Shownotes Transcript

Translations:
中文

Today I've got something really special for you. You may not realize this, but we're living through one of the most extraordinary moments in history. How we live, how we work, and how we build is all changing with the rise of AI. It's both exciting, but it's also often overwhelming.

Many of us are wondering if we're falling behind, what we should be paying attention to and what we can safely ignore, and also just how to best use some of these new tools and technologies in our lives and in our work. That is why I am so unbelievably excited to announce the launch of a new podcast called How I AI with Claire Vo. The mission of Claire's new podcast is to show you how people from all walks of life have figured out how to use AI tools in their day-to-day life to improve both the quality and efficiency of their work.

What makes this podcast unique is that it's designed to give you highly practical and actionable tips and tricks and workflows that you can copy and start using immediately. No philosophical debates about the future of humanity or pontification on what might be possible someday. Each episode is going to be about 30 minutes, often shorter. The guest will share one or two specific use cases that they found useful in their work.

and they'll be live screen sharing to show you exactly how they do everything that they describe. I couldn't imagine a more perfect host for this podcast than Claire Vo. Claire is an engineer, a three-time chief product officer, a founder, and on the side has been building her own AI product that's now making six figures. What I love about Claire is that unlike a lot of people online, she doesn't just talk about using AI. She lives and breathes it and builds with it and is constantly sharing everything she's learning online.

I can't wait for you to learn from her and from her amazing guests. This is the first ever new podcast under the Lenny's Podcast Network. Depending on how this goes, we may add more podcasts down the road. And just to be clear, nothing changes with Lenny's Podcast. This is just more free content coming your way every Monday morning.

If you're building products, leading teams, starting a company, or just want to learn how to actually use AI in your life, this podcast is for you. What follows is the first episode of the podcast. If you like what you hear, head on over to howiaipod.com.

dot com to find future episodes. And a pro tip for the richest experience, since there's going to be a lot of screen sharing and live demos, you're going to want to watch the video version. So definitely check things out on YouTube or on Spotify, which includes video. Now, here is the first episode of How I AI with Claire Vogue.

Can you do something that used to take two weeks in two hours? And that's like a 40 times speed increase. So that's kind of like the number that I have in my head generally. Like what's the most optimistic case? If you kind of remove all the bottlenecks, something that would take 40 hours would take one hour. If you're suggesting to us that AI is going to raise the bar on what's possible to do, you are certainly setting the standard. The majority of human engineering will be removing tech debt.

such that AI engineers can actually ship features. It's also scary, I think, which is why I think so many people shy away from this stuff. It's like there is this part of why change is uncomfortable is that change can kill you. There's like a fear of change. It's like job security, right? But at the end of the day, I think it's sort of also job insecurity.

Hey everyone, welcome to How I AI, a podcast on how AI is transforming how we get things done. I'm Claire, product leader and AI obsessive here on a mission to help you build better with these new tools. Today I have an absolute powerhouse guest, Sahil Lavigna, CEO and founder of Gumroad. If you don't know Gumroad, it's the platform that has helped creators sell over a billion dollars of products directly to their audiences.

Sahil's been at the bleeding edge using AI to transform how companies build products and write code, doing everything from open sourcing the entire Gumroad repo to paying his employees thousands of dollars if they can write more AI-powered code than he does. Today, he's going to show us exactly how he does it. Let's dive in.

This episode is brought to you by Enterprit. Enterprit is a customer intelligence platform used by leading CX and product orgs like Canva, Notion, Strava, Hinge, and Linear to leverage the voice of the customer and build best-in-class products.

Enterpret unifies all customer conversations in real time. From Gong recordings to Zendesk tickets to Twitter threads, it makes it available for your team for analysis. What makes Enterpret unique is its ability to build and update a customer-specific knowledge graph that provides the most granular and accurate categorization of all customer feedback and connects that feedback to critical metrics like revenue and CSAT.

If modernizing your voice of the customer program to a generational upgrade is a 2025 priority, like customer-centric industry leaders Canva, Notion, and Linear, reach out to the team at interpret.com slash howiai. That's E-N-T-E-R-P-R-E-T dot com slash howiai.

Hey, so I'm super excited to have you here. And before we dive into the demos, I wanted to call out something that you said a couple days ago, which is Devin, the AI engineering agent, who I also love, is writing 41% of your PRs right now, and you expect it to go to 80% by the end of the year. So do you think that's the baseline that we should all be shooting for? Do

Where should we all be compared to that benchmark that you just said? I feel like I tell the team constantly, like we have a lead, you know, but the lead is getting shorter and shorter every day. Every week there's a new model coming out. So I would say like by the end of next year, I would suspect that like every engineering team in any company is, you know, using Cursor and Devon and V0 and all these tools to ship, you know,

multiple times faster. And the question is, is mostly like how the organization adapts such that those people can do so, right? Like the bottlenecks are show up in other places, like Togi just tweeted about, you know, his Shopify AI stuff today. And I think that becomes the question is like, how fast can you actually change your organization, your culture,

Especially when you're remote, it's harder to make these big changes across the org to get people to learn new stuff, to try and fail and cross share learnings, you know, all that, all that kind of stuff. Okay, so we're going to do it one at a time, which is you're going to show us how you actually redesign or build something using these tools. So we'll get your screen up and you can walk us through how you think about things.

Awesome. Yeah, I mean, so I think the coolest thing about all this AI stuff is that you get to spend more time doing what you really enjoy, which to me, and I think you as well, like, like solving customer problems. And for this product that we build is called Flexile.

And it's, you know, you can think of it like a like a store deal, but built specifically for the way that we run the business, which is like hiring a bunch of people, a lot of project based, a lot of hourly based monthly retainers, all sorts of different types of people remote in person full time, let them choose their equity split, manage your cap table, all of that stuff and like the same product.

And one of the reasons I love AI is that I can basically just use the product and instead of running into some issue and being like, hey, engineer, can you go solve this? And then spending all this time like writing up a spec, you know, then putting that into, you know,

sending that to a designer, that designer will then do like tomorrow or the next day, we'll then do a mock, there'll be some back and forth. And then it will go to like next week on Monday, it'll go to an engineer, they may have some questions that goes back to the designer. And by the time it ships, you know, it makes it to production, even for something relatively trivial. You know, it's been two weeks or something, right? And so like, can you do something that used to take two weeks in two hours?

And that's like a 40 times speed increase. So that's kind of like the number that I have in my head generally, like what's like the most optimistic case. If you kind of remove all the bottlenecks, something that would take 40 hours would take one hour. And that's pretty awesome. So even in this form, like pretty simple. And I built the software. So I'm like, you know, I'm not like saying, oh, it's so terrible, but there's always room to improve. And even on this one screen, which is the contractor invitation page, you

There's already a couple things that I noticed that aren't big enough to really ask someone to do. Everyone's busy. They have their own stuff that they're working on. But there are a few things that I noticed. For example, the date picker is kind of terrible. It just uses the native date picker. It's not humanized. You can't type in next Monday or this Monday or have a nice date picker if you go to chat.cn.

and this is the beauty of open sources you know and the why ai is so good is there's a lot of open source you get like a nice date picker like this right it's like nicely humanized and you can do all sorts of cool stuff so that's like one thing i noticed that i think is like a really good candidate for this i would go straight to devon i would you know it doesn't really really need that much scoping it's kind of just like replace date widget you know date picker in contractor invitation screen with uh chat cn day picker we might as well i mean the cool thing with devon is you can like

that do that while you do other stuff so there's there's no risk really so i can select the flex l repo and you know say for this specific page like update the date picker from the browser native you know input to shads yeah import if required i've never actually used this button but again this is a good example even somebody using this stuff like you have to constantly like

up your game to learn more. Basically, I think this should be really like a rich text like this. You can just type into it and you could type in like next Monday, I think resend at a cool demo like this where they have more like a natural language, something like this. And you could type in in one hour tomorrow at 9:00 AM, these sorts of things. Or Slack actually has something similar where if you go into a Canvas

You know, this is our roadmap. If you type in like Thursday, right, this is kind of like what I think would be really cool. So I think this is also like I'm going to have Devin do multiple versions and then we can take a look at how far it got on them. But this is kind of how I would generally work is I would just take these forms and say like, you know, build this.

this form. So you're putting into v0, you know, use this form using the very descriptive great requirements. Magical. And then you're going to use v0 to get a prototype? Yeah. So generally my flow is v0 devin cursor is probably how I would say it. Like generally v0 is my prototyping tool of choice.

And once I have a really good prototype that I'm happy with,

Then I go to Devon, and if Devon fails to completely finish, then I open it up in Cursor. Though I think last week Devon launched this pairing mode where you can actually jump in. And so I haven't really experimented with that yet. But that's presumably-- I would use something like that going forward where I could actually just jump in and fix the changes. The nice thing is Devon actually runs-- one of the most annoying things about being a developer is just getting set up.

You know, just getting your developer environment set up, your end variables, local host. One of the tips I have for engineering organizations that are large, which is if you can make your environment easy to set up for AI, it's probably a lot easier to set up for new hires. So it pays off to sort of use that as a testing ground for how easy it is for any new engineer to get started, whether or not AI. So you have vZero in

in theory going, there it goes. Okay, so you have v0 going on building you a prototype. I have a question here, which is, you know, you mentioned ShadCN as your component library. Was that driven by, you know, using these AI tools and, you know, those component libraries being out of the box? Or was that something you were looking at before? Yeah, it was a huge reason to switch and try to adopt a lot of these tools, both. And I think it's one reason that I think many people haven't really

It hasn't clicked, I guess, the AI stuff. They're like, oh, I tried it. It didn't really work. It's not that good. It makes a lot of mistakes. Basically, it's faster for me to do it than to have AI do it. And I find that a lot of it is just AI is good at certain things. It's really good at front end. It's really good at React. It's really good at JL and Chatsy and stuff. So if you're not using those sorts of tools, you're not going to get the value. Trying to ship something like this

with like rails in the background back end and like hot wire or whatnot in the front end like these just doesn't exist like you you would have to spend all your time just getting this to work you know some jquery calendar thing you think you know that's how gumroad was for a long time one of the things i wonder is if you know engineering leaders will decide on particular transitions or migrations to make just to power this stuff so that their teams can move

a little bit faster because they're just seeing themselves be left so far behind compared to those who are maybe using some of these libraries and technologies natively. I actually think that the majority of human engineering will be removing tech debt such that AI engineers can actually shift features. Basically, designers will be shifting features because if you think about it, what are they doing, right? They are thinking about what the features should do.

And then engineers are just basically setting up the groundwork, the framework, the defaults, the standards, the linting, the CI pipeline, the infrastructure, the dev setup, such that designers actually are more and more capable over time of like basically taking their idea, like, you know,

If you were a designer, you would just design this part. You'd design this, but you wouldn't design all the little interactions in here. You would just design that because it would just take too long or you wouldn't even consider it because you didn't play. For example, often you'll have a designer and they didn't consider mobile. Okay. So you got this design. Let's take a look at it. It looks pretty good.

It has the magical date creation, which is type. There you go. Type a magical date and it works. So it's not just the design, it's the functionality. And you said the next step for you from V0 was into Devon. So how does that transition work? What are you doing? You know, normally I would have a few back and forths here. You know, you could spend like three or four prompts, like 10, 20 minutes, like really nailing like the interaction, right? You may say like...

you know, add a clear button or, you know, when you hit delete, it should actually delete. And this stuff will get only faster and faster and faster. But once, you know, once you're happy with what you have, normally I would take like the final prompt and I would just paste that into Devon, you know, and I would basically do similar to what I was doing before. And I can see Devon doing its thing, having lots of fun. And I can start a new Devon and basically do that, right? So like on here,

on this page and you reuse the exact same prompt build this form yeah it's often i mean sometimes if i'm going back and forth and i learn stuff like i'm like for example this yep i may just add here you know like all these are kind of like learning where i could it's basically i'm like oh my spec could have been better like this these are things that human engineer also would have maybe not done you know like i basically just kind of go back and forth and like build basically i'm like

The v0 is kind of clarifying my spec in a way. Do you use any of the code from v0? Sometimes I do. Like sometimes I'll take this and just use this command. And if I put this and I went into cursor, or if I had cursor open on something, if I had to say I had it open on this, for example, I would just go to terminal and I would just paste this right in. And it would put in this component.

This is for a different repo, so it doesn't have shatcm, but it would basically slot that file in, and then I could reference the file. And you can also, I believe, just share it, and you could literally just give the URL effectively, like this. And you could just say, mimic this, right?

You know, you can say more things, you know, for example, I noticed that like in this thing, like I probably don't want the date to change in line. I like this parentheses is kind of weird. I'd probably add like a little note, you know, so I'd be like the putting the date and parentheses is kind of weird. Put it below the input as a note. Yeah. I love putting parentheses.

I don't know what this does, but for some reason, if I feel like I'm vibing with this person, like they know what I mean when I say note, I mean like slightly smaller font size, like gray, you know, like note, like I feel like a designer would get it. So, you know, this is kind of like what I would give to Devin and, and then it would, it would, you know, run off and do its thing. It'll wake up and,

It'll do all these things. All the stuff that I would basically do, right? Open cursor, get the thing, find the files that need to get changes. But I personally, one of the things I think is really, really important is spending more time in v0. Like I think many people just like, they do a first pass and basically I think MVPs are no longer enough. Like you can actually spend like,

10, 20, 30, 40 minutes here, if you know that Devin is going to be able to execute, like sometimes you don't want to spend too much time here because it just creates work for the engineer, right? You're like, oh, now I have to think about this and that and this and like all these like little bits that would make the customer feel really good.

the user experience would go up, but the developer experience would go down. But if you know an AI is going to be implementing all of that stuff and they're going to do it at a very high level of conscientiousness, you might say, oh, by the way, redesign it to have this. Or different roles, for example, different roles have different amounts. Go a preview in the dropdown. So one may be 200 an hour, one may be 2K per project, et cetera. One may be 250K a year.

Just for fun, I might say like one may even have multiple pay rates because I've been exploring this idea generally. And I think part of the beauty of not doing it yourself is to happy accidents. Like AI may just take your spec and actually do a better with it than you would have.

And so, yeah, that's kind of how I use it. And then I generally, if you're hosted, you know, depending on the projects, our newer projects are all Next.js hosted on Vercel. So they'll even give you like a preview branch, right? And I mostly love doing front end stuff with Dev. And actually now they have this pairing thing. I could actually go in and like run Rails console and like check the back end stuff too. But, you know, with preview branches, like I love making changes to antiwork.com. Yep.

Because I can test them almost immediately. I can be like, let's say a new person joined the company. I can just say, hey, add this person who joined the company. This is their motto. By the way, pick a fun icon that matches for them. I didn't pick any of these icons. I would not have made myself a king, for example. I basically just asked everyone in Slack, tell me if you want it to link anywhere.

and what you want your slogan to be.

And then I asked Devin to actually do it and pick an icon for each person. That brings me to something I was thinking about, which is when you were in vZero and you were asking it to add on features, I was playing the product manager in my brain. And I was thinking, oh, in past lives, people would say, no, that's scope creep. We're just focused on the date picker or we're just focused on updating this component. We can't.

kind of scope creep and add more and more features. And what I think is interesting, I'm curious your point of view, is you can really start to go to the edges of some great user experience. And it's less about how much time will this take or is it too complicated? It's more about what's actually going to work and be useful. Yeah, totally. And like I often like, I mean, maybe this annoys some people at the company, but like as I'm doing V0 stuff, like on other things, I'll like go into the issue and be like,

let's see if i have one here and like i wanted to improve the multiple pay rates per role as i mentioned right like this is it and i i'll you know i'll be like i'll just go in here and be like you know like this one i had i was like doing something with gusto and i kind of liked it you know and i was like did i turn on this and it's just free people can ignore it if they want but it's like free design research you know uh so all of a sudden they have an example of this

This episode is brought to you by Vanta. Building a business? Achieving ISO 42001 compliance shows your customers that you're taking the necessary steps to ensure responsible usage and development of AI. But the process can be time consuming, tedious, and very expensive. With Vanta, achieving compliance can be done in a fraction of the time and at a fraction of the cost.

95% of the required document templates are pre-built for you, accelerating the process, helping you demonstrate trustworthy AI practices and scale your business. Start with Vantage Free ISO 42001 checklist, which gives you a breakdown of the compliance process and the road ahead.

Download it at vanta.com slash howiai. That's v-a-n-t-a dot com slash howiai for the free compliance for AI checklist. You know, I see you as an individual being able to add this and fix that and update, you know, the homepage and all those things and use Devon sort of asynchronously. I'm curious how you've made this work.

at the team level? Like, what are the actual operational pieces that have to be in place for this to not degrade into chaos? And then what about just culture makes this work for you all? Yeah. I mean, first off, it's not easy. Change is uncomfortable, right? Uh,

it requires work and energy and biologically I feel like we're trying to save our energy all the time so you have to you know you have to motivate people you have to make it exciting you know there's a reason like colleges and classes are in person right like there's a

It's like fun to train together. You know, it's easier to go to the gym in a gym than like at home in your bedroom. Right. Part of it is doing it myself, too. You know, like if your manager, your annoying boss is telling you to do something, it's different than like leading from the front a little bit. I often do like screen shares. Actually, like I recorded these videos and I recorded this one with Josh Pigford on YouTube, which is like three hours long. And I basically did it because I wanted to. I was like, this is, you know, got a lot of views, actually. Yeah. Yeah.

that's how important I felt it was not just for me, but for everybody. But I was like, basically recorded it for the team. I had my team in mind as I was doing it, like check out how cool it is. Like imagine once we switched to tailwind, like how fast we can, you know, do this kind of thing and like how, you know, it sort of is part of that bringing the energy. We also financially motivated people. So there's a couple of times here, I'll find you example of a Devon competition we did. So we did this competition where we did 30, uh,

$33,000 split amongst whomever opens and merges more Devon PRs than me over the course of May. So, you know, it's a kind of a fun way to like motivate people to learn. It's time bound. And I actually did pretty well. Let's see the results. So I got I got fourth place.

I opened 27 PRs with Devon and then three people beat me. And I do a lot of easy wins, so props to all the engineers who did it. But yeah, this is all my Devon PRs. A lot of people are like, there's no way you use Devon. You're making it up. You're just trying to go viral or whatever. I'm like, not really. I'm just trying to help people be more productive. I didn't know that was so controversial.

But, you know, there's like a lot of small things like remove this part of the homepage. There's this like recap that we do in Slack that's generated by AI that recaps like everything that shipped last week. And so I said, hey, Devin, could you, you know, like, for example, these two things don't really need to be here because there's nothing under them. Right. So I just said, hey, Devin, like, could you like, you know, only show the products that actually have shipments and like hide the other ones? And also like some of these aren't really shipments.

Like this one is only the back end. The front end hasn't shipped yet. So like make sure, you know, the update, the AI prompt that we're using for this, which by the way, I've never seen. Like I just, I just know that there's an AI prompt that's, you know, involved and, you know, it'll, and that's actually what this, what this one is. Right. So.

It found the Slack weekly recap and it made these changes and it created this PR. So we can actually go in and see this PR and we can confirm my suspicion or not, which is, oh, turns out there is a prompt. Focus primarily on shipments, feature improvements, and bug fixes, right? Prioritize these categories. And then it also did something here.

which is, if we looked, it did this. It added a filter, so basically only the projects that have more than one. The thing that I would critique about myself is that ideally we would have a test, and maybe there is a test that I don't know about. So this is when the human would come in. I don't normally just hit merge on these things. I would normally send this to somebody else and be like, hey, I did my best shot at this, and you could see here for the Slack recap, don't include project names, etc.,

And then I pasted this, the link to the update. You know, I would normally like say, hey, can you make sure this looks good to you? And if there are any tests that need updating. And personally, I think this is way better that like someone has done most of the work for you. And basically, I think humans will start the process. I think of it like flying a plane, like humans will

take off, decide where to go and land typically, you know, do QA in the, in this context, but, you know, not actually build, write all this code, right? Like look up, like, for example, you know, like dot filter versus dot trim or dot clean, or, you know, like every language is different, right? But overall, I know rough amount of software architecture that like, this is

This is the right solution to this problem. You're just adding a simple filter that removes the things. And ideally, there would be a test. So I would have even higher confidence that this has done what it should. One thing I was going to call out on the code you just showed was I find that these AI engineering tools are pretty good engineering citizens and that their code is well-commented. Yeah.

They call out, you know, there's a little bit document doc strings and things like that that make it easier to parse some of those changes. Okay, so this is what we kicked off with. It's the native date picker replaced with the ShadCN one. Yeah, so the core problem I have here, which I guess is I need to make sure it works. Okay, so you're showing the time lapse of Devin here, which is basically...

A screen recording of every single step along the way. Right now you're in the terminal and the IDE. So you can actually replay step by step how Devin got all this code done. It looks like it has in here, you know, reasoning and thought and planning. Exactly. And then the part that I'm looking for, and hopefully it did it, is that it would run...

it would run the app locally and it often does this but sometimes if you have a complex app and we just open source this so that it may have like broken but it would actually run the browser in its little local box and then it would test it so let me ask it to do that around the browser and it's awake so it should pretty quickly start doing doing that and it's this is devon right here devin box mr devon

uh and also we can watch it on this one right it's uh it's doing its its little thing so because i used magical in quotes it presumed that i wanted to call it magical and you can see we actually open sourced it recently so it's always working on an old running which is my guess of why it's not working exactly right um so now there are two things i decided so you know replace

this input, the standard input with the type date with this new component, that's definitely correct. And then it created this component where it goes through and it replaces it. So the thing that looks wrong here is it doesn't look like there's any AI magic. So it's sort of

which maybe it doesn't need to. Maybe it's smart enough to know if I just type in today, tomorrow, or yesterday, but this probably wouldn't work if I said three Sundays from now, but maybe that's fine. Maybe that's not actually what anyone would really do. This maybe even is a good example of something that, to your point, I think AI has really good hygiene, engineer hygiene, where it is on a micro level, it's a better engineer than human engineer would be. So you have to

have to spend more time on like the architecture and like the planning aspect of it making sure your execution is correct like calling it magical date picker maybe it's not the correct approach i would probably call it natural language date picker or something like that because magical doesn't really give you any insight into what's magical about it uh but besides that my guess is like this code this natural language uh is actually like probably really really robust really good uh

Even this magical look, like check out the math on this guy, you know, like, whoa, pretty simple. But like, how long would it, you know, how many times would you have to tweak it to like, oh, I, you know, like, I got it wrong. This like fancy add days function, like it's pretty, pretty clever how it's doing how it's doing that. Find index, it's getting all you know, it's basically figuring out like when you type next Monday, it's like three days and you're adding the days to get to the right date.

right day in the calendar and it's parsing the database. And it's like, that's like, this would be like a, you know, two years ago, this would be like a, so impressive for like, this would be almost like an engineering challenge, you know? Like I would hire an engineer based on this, which is now they would just go to chat GPT and be like, and yeah, it would, it would, it would work. So what you could do is to go back to the V zero. If you really wanted to enhance this, you know, you could just sort of take this component and,

And they're actually working on a way to like embed, you know, bring a component back into V0. And then you can like iterate on it. And the UX, like a designer could even do that with V0. And then you could then pull it back in to the code base. So you could kind of like do a lot of this like customer focus iteration, you know, on the V0.

in a WYSIWYG way, basically, like Dreamweaver, you know, versus like, like in code, I mean, like this, you have to think so hard to understand like what, how do you improve the user experience looking at this, right? The amount of like brain power and it just hurts my head.

What I think about is imagine that an engineer took this and went a week away and came back and said, here, I built your magical natural language, you know, date picker. And you said, no, that's not really what I want.

it feels like such an expensive iteration to throw out that cone and do something new. Whereas you, you can iterate that on that, you know, in a couple of minutes or a couple hours over and over and not feel like you're wasting, you know, time and expense and people's honestly, people's like motivation and energy. I think about that a lot as well. Yeah. If you, if you spend two weeks on something and you're, you know, you're annoying CEOs, like, nope, that's not what I meant. It's like, Oh,

And then you got to go for a long walk and a coffee break before you're back to work. So it's so much better to really spend time here before. Yeah, I just leaned in. So we got a redesign from V0 on this new employee onboarding. And not only did it get new features, but you got a beautiful update on the date picker with some suggested common timeframes in there.

Yeah, this is super smart. Like, and all I did, by the way, I just said, build a really dope natural language day picker for an HR product onboarding form. So probably the critical piece is like HR, right? So it's like building it in the context of the problem you're trying to solve, which is, you know, if you're, if you're, if you're building like a, like a party planning tool, you'd probably have like Christmas or, you know, like whatever, whatever, you know, but in this case, uh,

Yeah, next Monday in two weeks. You know, probably it's going to be next Monday. That's my guess is that is the most common, you know. But you could say, actually, we're, you know, we're based in a, you know, a country in which, like, we work, we start on Sundays or Tuesdays. And, you know, and you could do all sorts of interesting things. Or we're in a, you know, a place in which our date, you know, we put the day before the month or whatever. And so, yeah, it just, it just...

Yeah, just a great opportunity to really push the envelope and just really spend more time. Even I love this. I put the first name and last name next to each other so you can read it out nicely. So we just watched you...

Ship in a new component, build a magical and now dope date picker for your employee onboarding tool. You've shown us how to get this done across your org, and you proved that you're at least in the top five people shipping PRs with Devin at the company. Oh, by the way, this is merged. We did it. We got it merged. So it looks like I made no mistakes. That's good.

So yeah, next week it'll be better. Like think about that would have been like, you know, at least 24 hours. So that's like a nice 10x speed increase. This is a lot about engineering at Gumroad. And you said, you know, 41% of your PRs are being written by Devon. You're writing code.

What org is AI coming for next? Where the 80% of the work you think is going to be started by agents? I mean, I think you could see, you know, if you think about what are the orgs that exist, you know, it's like design, product, engineering, customer support, sales, marketing. And I really, I don't know, I actually was probably more optimistic on like full automation. I don't think we're going to really get there for a long time. There's just always like a higher level abstraction that you get to operate at.

so you know there will be for example like i think there's a lot more marketing automation that could happen in terms of like suggested tweets like you know it could just watch what's happening in github it could like suggest hey this thing we you know we have a a content framework we should post about this feature right right now i noticed myself having to like you know say hey this thing shipped in github by the way only half of it shipped only the back end there's still all this nuance that i think you know marketing could get like a lot more efficient

sales too, I think. Like, for example, there are all these people who sign up, you know, they show up in our database basically, right? And they're just emailing

Right? You go to Flexile, you sign up. But there's, I think, a lot more automation. You know, if someone signs up to Flexile with like sawhillandnewerytimes.com, you know, you could sort of queue up an email to them. There's so much focus on customer support. We even built our own customer support product with AI, which is great. You know, you can talk to AI and it'll help you out. But this is all like reactive, you know? Well, what if I'm just browsing the page?

And, you know, it knows that I'm in New York for my IP, you know, and you can wave at me and, you know, it could be like, hey, what's up? I was in New York. It's kind of cold out there. It's kind of rainy. And you'd be like, oh, yeah, it is. It is rainy in New York. Why do you care? And you can have a conversation. And, you know, you're like, well, you know, it's kind of nice to be able to, like, talk about...

the problems customers are facing. So yeah, I mean, there's, there's, I think sales, like making it more, making support more about sales, making it more proactive. I think making design more about product, making engineering more about architecture. You know, I think there's always going to be more and more stuff to do. Maybe even like, like, like prioritization. I think I spend a lot of my time, like, you know, for example, like going through GitHub and saying, okay, we have all these tasks. We have like 27 things. Like what do we build first?

And right now it's like in my head, basically I've seen all these things go live or maybe even a better example, more people would relate to would be Gumroad. You know, we have this big roadmap and,

And, you know, I basically I think I'm pretty good at this. But the reason I'm good at this is because I've seen every single thing ship. And so I kind of can very quickly sort of be like, okay, this is this is, you know, going to generate like, you know, maybe 100 to $200,000 in value for creators, creator earnings, this will probably generate like,

300, 400 K, but then I have to also put on my engineering hat and say, okay, this is going to take like 40 hours of an engineer's time. This is going to take 300 hours of an, you know, and like do all this math, which you can go to business school, learn about bite and like all these things. And I could totally imagine like, you know, a button here that's like a magical rank. Right. And then it just like sort of goes through and maybe you should actually know that because you missed out this fact, it's actually much harder to ship or.

We don't yet use Shadzy until actually you're underestimating this and it could like reprioritize it. Right. And you could do all sorts of interesting things. That's like a huge, I mean, think about how many people at these large companies, especially like they're spending so much of their time on strategy, quote unquote, which is really just prioritization. Right. And what we do is we just email all creators and we just put together a list of things. And I just, we just sent this Google doc to like our top 200 creators in 2024 and

And we kind of like ranked this based on what they wanted from us, because it turns out like they're the ones paying our bills, right? And we started shipping it. And imagine AI could take all it in all that data. I mean, all their sales volume, we have access to right in our database. And you could somehow kind of like, get a good good sense of like, okay, what feedback should we be listening to? And, you know, you can imagine like, you just hit a button that says like, yeah, you know, assigned to Devin, you know?

And then boom, it's done. I mean, that's another weird thing, though, right? It's like, well, if AI gets so good, why do you need to do everything? What's the point of prioritization? Prioritization is a function of limited resources. So that's a whole thing. I would love to be in a place where I come into the office and I have no idea what's going to happen. I have no idea what we should even be building. And we spend time as a team...

like thinking about what should we build? Like we go, like there's nothing, there's no issues in GitHub. Yep. Because every issue is solved. So, you know, it's cleared. We're in box zero. And so it's like, okay, well, what do we do? And then we sit around and talk and pontificate and eat lunch. And, you know, we really have to think hard about like, oh, we should do something totally radical, like open source, the whole thing, you know, like things that like an AI probably wouldn't suggest that it wouldn't be in the

In the next token prediction or even in the reasoning models, we're like, okay, we should do really advanced content customization options. Okay, like, what is that? Okay, let's go design and V0, watch that and do a lot of research. You know, I think research is obviously going to get a lot better with AI, but still humans have to go talk to people, ask them questions, user research, design research, market research, research.

I think sales will always be important. I think marketing, like I think marketing will be one of those things where like the average marketing, like AI will get so good at marketing that like the level of what's interesting to a human, like kind of like the, you know, that meme of the Saratoga Springs guy drinking the water and whatever, obviously like putting banana on his face. Like to me, that's like a sign of how good AI is that like that level of content production is now necessary to go viral. Like it's insane. I can't imagine like how long it took to make. Yeah.

It's so funny. It's so thoughtful. And so many funny different little Easter eggs. And I think that's kind of what will need to happen. You have to up the game more and more and more. Right now, artists can post a painting on Instagram and people will be like, oh, amazing painting. But in five years, it's going to be like, you need to post the freaking movie. That's just what people will expect. Like, hey, we just want to see your 30-minute sci-fi movie that you did. And that's just for free, sorry. That's

That's what's happening to our dopamine system. Or we can spend a whole day talking about how do we get better at recommending products on Gumroad? Is there a totally different kind of recommendation experience that's much more AI-driven and much more natural language than just a marketplace of a feed of products where you can remember things about your tastes, your preferences. It can learn from you or

we're launching a community feature pretty excited about this next uh later this week which is pretty big but we you know there's just tons of yeah i mean who knows i mean it's exciting it's also scary i think which is why i think so many people shy away from this stuff it's like there is this like part of part of why change is uncomfortable is that like change can kill you you know like there's like a fear of change like you know it's it's like job security right but at the end of the day i think it's sort of also job insecurity like

We don't know if what we do will continue to be valuable. I can say for sure, if you're suggesting to us that AI is going to raise the bar on what's possible to do, you are certainly setting the standard. I think you're showing an entirely new way for teams to build. You're showing an entirely new way for a leader to show up and actually contribute to the work product of the company, which I think is really...

inspirational. And then I think you're also showing, look, you just have to go learn these things and try things and you're going to get in a loop. But over time, you can actually become one of these leaders that's on the leading edge as opposed to the lagging edge. So I think it's great. And I think you're setting the standard for how EPD orgs are going to operate in the future, if not companies. So we're going to wrap up with a quick lightning round. Two questions.

if you could encourage people to learn just one of all all your toys here you just showed just one that you think is the highest impact which one would it be v0 honestly i mean it's a bias i think because i spend so much time in product i think of our more of an engineer i think cursor's agent mode is pretty crazy i think if you're like a ceo of a company i think devon is like the most impressive like the fact that you can just be in slack and just talk to it and it will it will do this

It's crazy. So I think a lot of it depends on your role and what you value and what you think is the most important. But vZero, I think it's just the lowest hanging fruit. I think everyone is kind of familiar with Figma. And I think a lot of people think that, okay, now people... No one questions that AI can code, even though a year ago people were like, say, oh, it can't code or whatever. But now people are like, oh, it can't design. It doesn't have taste. And so it's just like really design a really...

nice onboarding wizard for a bank, you know, and like watch it do a better UI for a bank than any bank has, you know? So I think that this is like something anyone can do. Like a kid could like have fun with this. So I would say, man, I'd probably nominate vZero. And then, you know, the cool thing about vZero is it shows you what's possible. And so then if you want to execute on it, then you have to like learn all the other tools. The other nice thing about vZero is that it comes with a URL.

So you could build like a tic-tac-toe and send it to your friend and play tic-tac-toe, which is a kind of a nice, you know, a replate or bolt on you or lovable. Like they, there, there's just so many. We've talked a lot about how you are setting up incentives like bounties to get people to use AI or learn AI, but how do you get AI to do what you want? So I found that everybody has their own tactic. Like they're mean, they offer money. What is your strategy?

strategy for getting AI to listen to you when it's in a little bit of a loop? I mean, honestly, capital letters, not in like a mean way, hopefully. Hopefully it doesn't take it the wrong way. But I just think it's like, it is, you know, kind of like, it's kind of old school, I guess. You know, you have like literally like lowercase and uppercase and like

It's just a really easy way of saying, like, this part is really important. Like, please do not ignore this specific part. There's another hack that I love called Etcetera. So if you want a list of things, you can name, like, two of them and then just say Etcetera. And it will often, like, riff. It's really fun to just, like, be like...

It's kind of like a test, you know, it's like you've come up with two or three, but you need 10. It's kind of a nice way of letting it like be more, more, more creative. So, well, this has been incredible. And we have to wrap by showing you have not only redesigned your own product, but you've taken on the baking industry by generating a onboarding for a neobank apparently here.

in V0. I really appreciate you giving us a real look at how you're building with AI, both as an individual and as a team. I think you're definitely going to inspire tons of people to rethink how they show up at work. And I think a few folks are going to be looking over their shoulder thinking that you're about to lap them once or twice on some of this building. So thank you so much for the time. Where can people find you and how can

They'd be helpful to you. Yeah, you can find me on Twitter slash X. My handle is at SHL. And helpful, I don't know, just anytime you see something I've said that you disagree with or think of my thoughts could be improved upon, just reply, let me know, DM me. I'm always looking to get feedback and improve my thinking. So I just appreciate everyone tuning in and excited to see what everyone builds.

Thank you so much. Thank you. 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 HowIAIPod.com. See you next time.

We're sunsetting PodQuest on 2025-07-28. Thank you for your support!

Export Podcast Subscriptions