Claire Vo

Things Claire Says on Podcasts

Founder of ChatPRD, an AI tool for product managers, who writes and speaks about product management, AI agents and coding workflows. Hosts How I AI, a podcast where guests demonstrate practical AI workflows. Publishes How I AI episodes and solo AI tool tests on Lenny's Newsletter, alongside her own Substack. Has appeared as a guest on AI & I, The Pragmatic Engineer and The Growth Podcast.

Where to Find Them

Claire Vo hosts and writes Lenny's Newsletter , hosts How I AI , hosts and writes Lenny's Podcast: Product | Career | Growth , writes The Growth Podcast , writes Product Growth and hosts How I AI . They have also been a guest on AI & I (2 times) , One Knight in Product and The Pragmatic Engineer . They also write for Claire’s Substack, Milk Money and SaaS Product Management on Substack.

Recently: “🎙️ How I AI: Fable 5.2 Review + How I fight token fraud as a solo founder + Building a Claude Code family OS” on Lenny's Newsletter (November 2026); “How I fight token fraud as a solo founder” on Lenny's Newsletter (November 2026); “How I fight token fraud as a solo founder” on How I AI (November 2026); “Claude Code + Obsidian: My family’s AI brain | Scott Farrar” on Lenny's Newsletter (November 2026); “Claude Code + Obsidian: My family’s AI brain | Scott Farrar” on How I AI (November 2026); “Claude Fable 5.2 review: fast, creative, and finally not annoying” on Lenny's Newsletter (November 2026).

What They Said

“You don't need to know Swift. It's none of your business. What you do have, that a lot of people haven't invested in their own skilling, is design and product language: the ability to describe what you want with specificity… The more rich your reference set is when it comes to design, the better. When people ask me how you develop taste, I say, describe websites. Use your words to describe what makes brand A versus brand B special.” — Claire Vo, Lenny's Newsletter

Claire Vo was reacting to her guest's opening prompt for his app, which spelled out a warm, minimalist, light-mode look in detail. She uses it to argue that what matters when building with AI is vocabulary for design and product, not programming-language syntax.

Lenny's Newsletter · 2026-11-09 Permalink → Listen →
Lenny's Newsletter
Claire Vo

Maybe that feels like autumn in Norway, right? It starts to get really dark.

William Imoh

So, yeah, I had to reframe it before that. I was like, first, this shouldn't be in dark mode. Not everything belongs in dark mode. It should be light mode. Use light, warm colors, explore gradients. And I'll use liquid glass as much as possible as well.

Claire Vo

So I want to pause really quickly because what I think is so interesting about what you just said in that prompt and our conversation so far is: look, you don't need to know Swift. Like, you just don't. It's none of your business. You don't need to know. You need to know that. Maybe that you should use Swift, although AI could figure that out. But what you do have that I feel like a lot of people haven't invested in their own skilling is design and product language. Like truly the ability to describe what you want with specificity. And when people talk about taste, do they talk about taste? All of like, what is taste? We need taste. And really what you need is design language and references in the world that you can point to. You need to know what liquid glass is. You need to know what minimalism is. You need to know what a gradient is. And I think the more rich your reference set is when it comes to design, the better. And then on the product side, the more you know how to articulate a user journey in a way that anybody can execute on, an engineer, human engineer, an AI engineer, the better that like workflow will be. And so, you know, when people ask me, like, how do you develop taste or how do you get good at…

William Imoh

Yeah, I agree. I look at, and as soon as I put this out there, I didn't intend to share it with anyone because I wanted to build this for myself to use just by myself. And then I put out a tweet that, hey, I made this thing. I think it's really cool. I'm not going to share it because I don't want…

Claire Vo

Can you show it to us real quick? We're going to put your Norwegian to the test.

William Imoh

Can you speak? English. Yeah, uh, please, please just speak English.

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“When people talk about taste, what you really need is design language and references in the world that you can point to. You need to know what liquid glass is, what minimalism is, what a gradient is. And when people ask me how you get good at this, I say: describe websites. Use your words to describe what makes brand A versus brand B special. The more you practice that, the better you can be at prompting agents to do a great job.” — Claire Vo, How I AI

Imoh had just read out his long first prompt for the app, asking for a light, minimalist autumn look. Claire Vo pauses to argue that what made it work was design vocabulary, not knowledge of Swift.

How I AI · 2026-11-09 Permalink → Listen →
How I AI Around 14:27 into the episode
Claire Vo

Maybe that feels like autumn in Norway, right? It starts to get really dark.

William Imoh

So, yeah, I had to reframe it before that. I was like, first, this shouldn't be in dark mode. Not everything belongs in dark mode. It should be light mode. Use light, warm colors, explore gradients. And I'll use liquid glass as much as possible as well.

Claire Vo

So I want to pause really quickly because what I think is so interesting about what you just said in that prompt and our conversation so far is: look, you don't need to know Swift. Like, you just don't. It's none of your business. You don't need to know. You need to know that. Maybe that you should use Swift, although AI could figure that out. But what you do have that I feel like a lot of people haven't invested in their own skilling is design and product language. Like truly the ability to describe what you want with specificity. And when people talk about taste, do they talk about taste? All of like, what is taste? We need taste. And really what you need is design language and references in the world that you can point to. You need to know what liquid glass is. You need to know what minimalism is. You need to know what a gradient is. And I think the more rich your reference set is when it comes to design, the better. And then on the product side, the more you know how to articulate a user journey in a way that anybody can execute on, an engineer, human engineer, an AI engineer, the better that like workflow will be. And so, you know, when people ask me, like, how do you develop taste or how do you get good at…

William Imoh

Yeah, I agree. I look at, and as soon as I put this out there, I didn't intend to share it with anyone because I wanted to build this for myself to use just by myself. And then I put out a tweet that, hey, I made this thing. I think it's really cool. I'm not going to share it because I don't want…

Claire Vo

Can you show it to us real quick? We're going to put your Norwegian to the test.

William Imoh

Can you speak? English. Yeah, uh, please, please just speak English.

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“I also think that a lot of times these chain of thought reasoning elements in the UI are there as a band-aid for latency, which is, it feels very frustrating as a user to sit and wonder, is my agent working on something and is it making progress or is it just stuck?” — Claire Vo, Lenny's Newsletter

Host Claire Vo is praising how Meta's Muse agent hides its reasoning unless you ask for it. Her argument is that much of the visible "thinking" in AI apps is there to distract from slowness, and that a fast model makes it unnecessary.

Lenny's Newsletter · 2026-10-12 Permalink → Listen →
Lenny's Newsletter
Claire Vo

…you have ideas, you know, you have these, you have your feed, like you've just chosen different aspects to elevate. Is that because you knew that this was going to be serving a different type of user with a different kind of like breadth of intention around what this agent could get done for them?

Alex Cornell

…really detailed in the core chat. And that's the kind of thing I think that like typically we would have just put that in there because that's like what you do these days in AI apps. But I think in this case, it was like, well, does it really need to be there for everybody? It's like, probably not.

Claire Vo

I'll give you one other compliment because again, I am a Muse girl now, but I also think that a lot of times these chain of thought reasoning user elements in the UI are there as a band-aid for latency, which is, it feels very frustrating as a user to sit and wonder, is my agent working on something and is it making progress or is it just stuck? And so I think a lot of designers have struggled with how much do we narrate along the way, what is happening so it's quite obvious to the user so that latency doesn't feel so painful versus how much do we kind of like do progressive disclosure. And what I what I think is nice about my experience in the Muse app is I do like that progressive disclosure and is one of the things I called out in our review that I thought was quite nice, but also it's just fast. Like it is just fast. The model is just fast. Like I do think for especially something that's going to try to catch the eye of consumers, that latency really matters. And it's a zippy little agent.

Alex Cornell

Yeah, it is. And it's really, you know, it's interesting actually because it's one of those things where sometimes it's so. Fast that you are tempted to think, like, is it like, did it actually go do a thing? Like, cause it's, it's so quick. And I think, like, the nice thing is there are times…

Claire Vo

Yeah. One other thing, just thinking about this status message, I want to talk about, which is this concept of generative UI. And I think a lot of people think, when they're thinking about generative UI, they think like every time I log into my dashboard, it's different, or every button I click is…

Alex Cornell

Right. Yeah. I think perhaps one day we'll get there, you know, but I think these days there's, it's definitely a little bit more on the rails in terms of like where we can apply it. The avatar is a great example. And I think people find a lot of delight. I have seen when they do make their own new…

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“I said it was like a terrible use of $1,000 or whatever I spent. ... My kids were like, make the jellyfish a hula dancer. ... And I was like, there's just dollars going out the doors, kid. It's eight times as fast, but as Sam said, six times as expensive.” — Claire Vo, How I AI

Claire Vo, live at OpenAI's DevDay, describes a 3D game she built while testing a very fast new model early. Typing a request changed the game world on the spot, and her kids kept asking for more.

How I AI · 2026-10-05 Permalink → Listen →
How I AI Around 21:39 into the episode
Claire Vo

…promise automation, but you're really stuck doing all the work by hand, chasing screenshots, validating controls, and playing catch up when audit season comes around again. Vanta works differently. Their Agentic Trust platform is built to scale with you, not slow you down. With over 1,400 automated

Kath Korevec

…day or living in tools like Quad or Cursor. Want proof? Over 16,000 fast-growing companies like Ramp, Ryder, and Harvey save time and resources while scaling fast with Vanta. My listeners can get $1,000 off by going to Vanta.com/slash how IAI. That's v-a-n-t-a.com/slash how IAI for $1,000 off.

Claire Vo

…to for you to be able to build 3D games, which is pretty good at. So you should try doing that, deploy them, which you have solved, but then integrate these like very speedy, very fast models. I mean, I said it was like a terrible use of $1,000 or whatever I spent. I was like, my kids were like, make the jellyfish a hula dancer. Give the jellyfish bell, like, like babies. Yeah. I want a chicken. And I was like, there's just dollars going out the doors, kid. It's eight times as fast, but as Sam said, six times as expensive.

Kath Korevec

Yeah.

Claire Vo

But I do think as these like models both get like more smart and faster, you can imagine how this like. You know, people are talking about generative UI in this like very kind of like boring SAS way where it's like your forms will like progress how you want or you'll have these like widgets. I…

Kath Korevec

pretty cool. It's

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

Collections They Appear In