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

0:04Today 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. Manivas 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 ClareVote.

0:37The mission of Clare'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 some day. Each episode is going to be about 30 minutes, often shorter. The guests 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.

1:15I couldn't imagine a more perfect host for this podcast than ClareVote. Clare is an engineer, a three -time cheap 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 Clare 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.

1:49And 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 howiapod .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.

2:25Now here is the first episode of Howi AI with Clare, but 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 shift features.

2:58It's also scary, I think, which is why I think so many people shy away from this stuff, is like there is a 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 the end of the day, I think it's sort of also job insecurity.

3:14Hey everyone, welcome to Howi AI, a podcast on how AI is transforming how we get things done. I'm Clare, 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, Sehil Lavingia, 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. Sehil has been at the bleeding edge using AI to transform how companies build products in right code, doing everything from open sourcing the entire Gumroad repo to paying his employees thousands of dollars if they can write more AI power code than he does.

3:55Today, he's going to show us exactly how he does it. Let's dive in. This episode is brought to you by EnterPrint. EnterPrint 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. EnterPrint unifies all customer conversations in real time. From GONG recordings to Zendes tickets to Twitter threads, it makes it available for your team for analysis. What makes EnterPrint 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.

4:39If 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 EnterPrint .com slash howiai. That's EN -T -E -R -P -R -E -T .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 Devon, 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?

5:28Do you think your way ahead of the curve? 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, by the end of next year, I would suspect that like every and hearing team and anything company is using cursor and Devon and V0 and all these tools to ship a multiple times faster. And the question is mostly like how my organization adapts such that those people can do so. Like the bottlenecks are shown up in other places.

6:06Like Togi just tweeted about 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 your 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.

6:39Awesome. 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 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 ordeal 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, not the retainer, all sorts of different types of people remote in person full time and let them choose their equity split, manage your cap table, all of that stuff and like the same product.

7:18And 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, engineering, 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, the designer will then do like tomorrow or the next day will then do one of 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 might have some questions that goes back to the desire. And by the time it shifts, you know, it makes it to production, even for something relatively trivial, you know, it's been two weeks or something, right?

7:51And 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 thus 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, there's like already a couple things that I noticed.

8:28Like aren't big enough to like really ask someone to do everyone's busy. They have their own stuff that they're working on. But there are like a few things that I noticed. Like for example, the day picker is kind of terrible. Yeah. Like it just uses like the, you know, the native day picker. It's not humanized, you know, you can't type in like next Monday or this Monday or have like a nice day picker, you know, if you go to like Shad Cn. And this is the beauty of open sources, you know, and the YAI is so good, there's a lot of open source. You get like a nice day picker like this, right? It's like nicely humanized and you could do all sorts of cool stuff.

8:59So that's like one thing I noticed that I think is like a really good candidate. For this, I would go straight to deb and I would, you know, it's, 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 the Shad Cn day picker. We might as well. I mean, the cool thing with Devon is you can like do that while you do other stuff. So there's, there's no risk really. So I can select the flexile repo and you know, say for this specific page, like update the date picker from the browser native. You know, input to Shad Cn import it for acquiring.

9:38I'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 gain, learn more. You know, basically, I think this should be really like a rich text like this. Like you can just type into it and you could type in like next Monday, I think recent 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 a .m. 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?

10:17This is kind of like what I think would be really cool. So I think this is also like I'm going to have Dev and do multiple versions and then we can take a look at how far I've gone 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 form. So you're you're putting into V0, you know, use this form using the very descriptive great requirements magical though. And then you're going to use V0 to get a prototype. Yeah. So generally my flow is V0 Dev and cursor is probably how I would say it. Like generally I V0 is my prototyping tool of choice.

11:03And once I have like a really good prototype that I'm happy with, then I go to Dev and if Dev and sort of fails to completely finish, then I open it up in cursor though. I think last week, Dev and launched this pairing mode where you can actually like jump in. And so I haven't really experimented with them 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 Dev and actually runs, you know, one of the most annoying things about being a developer is just getting set up. You know, just getting your admit, your your developer requirements set up, your and variables, local host.

11:40One 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 your it is for any new engineer to get started, whether or not AI. So you have V0 in theory going, there it goes. Yeah. Okay. So you have V0 going on building you a prototype. I have a question here, which is, you know, you mentioned Shad Sien as your component library. Was that driven by, you know, using these AI tools and, you know, those those component libraries being out of the box or was that something you were looking at before?

12:23Yeah, it was a huge reason to switch and try to adopt a lot of these tools both. I think it's 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. It's you know, basically it's faster for me to do it than to have AI do it. And I found that that's like a lot of it is just like AI is good at certain things. It's a really good at front ends, really good at react. It's really good at tailwind Shads and stuff. So if you're not using those sorts of tools, you're not going to get the value like trying to ship something like this with like rails in the back and end like outwire or whatnot in the front end.

13:00Like these just just doesn't exist. Like 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 government 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 like the majority of human engineering will be removing tech debt such that AI engineers can actually ship features.

13:43Basically like designers will be shipping 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 LinkedIn, the CI pipeline, the infrastructure, the dev setup, such that designers actually are more and more capable over time, like basically taking their idea. Like if you were a designer, you would like just design this part, you know, you'd design this, but you wouldn't design like all the little interactions in here. Right?

14:15Like you would just design like that because it would just take too long. Oh, you wouldn't even consider it because you didn't play, you know, you didn't, for example, like often you'll have design and they didn't consider a 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 tight. 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 isn't to Devon. So how does that transition work? What are you doing? You know, normally I would have a few back and forths here.

14:52You 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, I'd add a clear button or you know, when you had deleted it should actually delete. And this stuff will get only 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 it. It's thing having lots of fun. And I could start in you Devon and basically do that, right?

15:28So like on here, on this page, and you reuse the exact same prompt. It'll 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, yeah, I may just add here, you know, like all these are kind of like learnings 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?

16:08Sometimes I do. Like sometimes I'll take this and just use this command. And if I put this and I went into cursor, if I had cursor open on something, if I had to say I had an 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 reposite to the app. Shats the end, but it would basically like, you know, slot that file in and then I could reference the file and and you can also, I believe, just like, you know, you could, you could, you could share it. And you could literally like, just give the URL effectively, right?

16:45Like this. And you could just say, like, you know, mimic, mimic this, right? You know, you could say more things, you know, sorry, 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 in parallel to sees is kind of weird. But it below the input as a note. Yeah. I love putting I mean, what this does, but for some reason, 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, no, like I feel like a desire would get it.

17:30So, you know, this is kind of like what I would give to Devon 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 they basically, I think MVPs are no longer enough. Like you can actually spend like 10, 20, 30, 40 minutes here. If you know that Devon is going to be able to execute, like, sometimes you don't want to spend too much time here because it's just creates work for the engineer, right?

18:09You're like, oh, now I have to think about this and that and this and then all these like little bits that would make the customer feel really good. The user experience would go up and the developer experience would go down, right? But if you know an AI is going to be implementing all of that stuff and they're going to do it into like a very high level of conscientiousness, you might say, oh, by the way, we designed it to like have this or like, you know, different roles, for example, right? Like different roles have different amounts. They'll preview in the drop -down. You know, so one may be like 200 now or one may be like two paper projects, etc.

18:41You know, 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, yeah, I may just take your spec and actually do a benefit 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 jazz, host John Vercell, so they'll even give you like a preview branch, right? Where I mostly love doing front -end stuff with Devon.

19:19Actually, now with the Anthas pairing thing, I could actually go in and like, run Rails console and like check the backend stuff too. But you know, with the preview branches, like I love making changes to anti -work .com because I can test them almost immediately, right? I can be like, you know, let's say a new person joined the company, you know, 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. Like I didn't pick any of these icons. I would not have made myself a king, for example. I just said, like I basically just asked everyone in Slack, like tell me if you want it to link anywhere and what you're, what you want, you're, you know, you're, you're slogan to be.

20:02And then I asked Devon 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 V0 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 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, more features. And what I think, 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.

20:39And 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 be, I'll like go into the issue and be like, let's see if I have one here. Like I want it to improve the multiple periods for roll, as I mentioned, right? Like this is it. And I'll, you know, I'll be like, I'll just go in here and be like, you know, like this one I ended up, I was like doing something with gusto and I kind of liked it, you know, and I was like, it turned on this.

21:16And it's just free. People can ignore it if they want, but it's like free design research, you know, it's all of a sudden, I have an example of this. This episode is brought to you by Vanta, building a business, achieving ISO 42 .001 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 prebuilt for you, accelerating the process, helping you demonstrate trustworthy AI practices in scale your business.

21:57Start with Vanta's free ISO 42 .001 checklist, which gives you a breakdown of the compliance process in the road ahead. Download it at vanta .com slash how I AI. That's vantta .com slash how I AI 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?

22:42Yeah, I mean, first off, it's not easy. Change is uncomfortable, right? It requires work and energy and biologically, I feel like we're starting 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, you're annoying boss is telling you to do something. It's different than like leading from the front a little bit.

23:16I 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 isn't, you know, got a lot of views actually. Like I, I, yeah, that's how important I felt to us, 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.

23:48We also financially motivated people. So there's a couple times here. I'll find you an example of a Devon competition we did. So we did this competition where we did 30, 33 ,000 dollars split amongst whomever opens and merges more Devon PRs than me over the course of May. So, you know, it's 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. I opened 27 PRs with Devon. And then three people beat me. So it's, and I, you know, I do a lot of easy wins, you know, so like it props to all the engineers who, who, who did it.

24:30But yeah, I, this is all my, all my Devon PRs. A lot of people, like there's no way you use Devon. Like you're making it up. You're just trying to like go viral or whatever. I'm like, not really like I'm just trying to like help people be more productive. I didn't know that was controversial. But you know, there's like a lot of small things. I can remove this part of the homepage. There was 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 Devon, could you, you know, like, for example, these two things don't really need to be here because there's nothing under them, right?