How the engineer behind Claude Cowork actually uses Claude | Felix Rieseberg (Anthropic)

1. 0:00 – 2:40

   Introduction to Felix Rieseberg

   1. FRFelix Rieseberg0:00

      AI is used poorly if it just needs to move the mouse cursor for you. I want AI to do a bunch of annoying things in the background to free you up for your creative energy.

   2. CVClaire Vo0:09

      The biggest gap that I see, it's not the capabilities of the tools, it is literally people being able to understand that almost any problem can go into these tools.

   3. FRFelix Rieseberg0:19

      I have built this little thing, which is just like a teeny-tiny Claude on a little stick, and this stick has Wi-Fi, it has Bluetooth. I want my little Claude to live on this thing, and I want it to cheer me on every single time I do a good job, and also every single time I need to approve something that Claude is doing, I want it to be on this big button that is out here. Claude has built all of that in one shot. I've needed to correct absolutely nothing.

   4. CVClaire Vo0:40

      My nine-year-old is a daily active Claude user, but he's decided he's really into cybersecurity. We're like very hacker adjacent here. And so he's truly Claude on one thing, the terminal other. He's like, "Mom, do you know that your device ID is this?"

   5. FRFelix Rieseberg0:54

      A truly magical thing is happening with kids because they've never learned what not to ask for. And I think our generation, we're very used to things just not working. So we've been living in this mind prison for way too long.

   6. CVClaire Vo1:05

      [upbeat music] 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 we have Felix Rieseberg, who leads some of our favorite Claude products over at Anthropic. He's gonna walk us through how you can solve almost any problem with Claude and show us how, for just $20, you can build your own hardware Claude buddy that you can smash a button when you need to approve things. 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. 2:40 – 3:25

   Felix’s role at Anthropic

   1. CVClaire Vo2:40

      Felix, welcome to How I AI. Thanks for joining us.

   2. FRFelix Rieseberg2:43

      Hi, Claire. How are you?

   3. CVClaire Vo2:45

      I am great. We were joking before we got started that I have referred to 2026 as the Year of our Claude, 2026.

   4. FRFelix Rieseberg2:53

      Yeah.

   5. CVClaire Vo2:53

      That is, that is the era we are all living in. And you are in charge of a lot of the experience that, that we every day get to, get to play with and work with. So tell me, how much of Claude do you get to product?

   6. FRFelix Rieseberg3:10

      Normally when I introduce myself, I say I work on Claude Cowork, I work on Claude Code, and I work on, uh, Claude for Chrome, and I work on the Claude desktop applications for Mac OS and Windows, because obviously it's a team effort. But I'm currently the eng- engineering lead for those products.

   7. CVClaire Vo3:23

      For those products.

   8. FRFelix Rieseberg3:24

      Yeah.

   9. CVClaire Vo3:24

      And what's

3. 3:25 – 5:55

   The multiple tabs in Claude and why they exist

   1. CVClaire Vo3:25

      really funny is, I'm gonna, I'm gonna give you a little bit of a hard time.

   2. FRFelix Rieseberg3:28

      Yeah.

   3. CVClaire Vo3:28

      But every time I talk to someone about Claude and how they're using it, I say, "Which of the tabs is your favorite?"

   4. FRFelix Rieseberg3:35

      I know. I know. Yeah. Yeah. Which one is your favorite?

   5. CVClaire Vo3:39

      Uh, r- the one I use the most in the desktop app is Cowork.

   6. FRFelix Rieseberg3:43

      Mm-hmm.

   7. CVClaire Vo3:43

      I'm really trying my best to figure out Cowork because I work with a lot of folks who are just uncomfortable in the Claude Code, what is a terminal interface. Even that third tab stresses them out a little bit. So I've been spending a lot, I've been spending a lot of time banging my head against Cowork, Scheduled Tasks, um, Live Artifacts, all that stuff. So that's the one I'm living in.

   8. FRFelix Rieseberg4:05

      I think we live in this, like, super interesting time right now where I, I often explain it to my friends and also to, like, people who work here as the, um, time right before we all came up with, like, the glass pebble as the correct shape for a phone. I think we currently live in this, like, super interesting time where some people are like, "Should your phone be shaped like a taco or should it be shaped like a lipstick? Should it have the keyboard underneath the screen or, like, right next to the screen, or like no keyboard?" I think that's the time we currently live in, and I think you can see that in a lot of products. I think that's also why you probably see, like, more entry points into Claude because I, myself, as an individual, I, I, I think it's a super interesting year because we're playing with all of these different form factors and I've not yet gained the confidence to say, "Throw them all away. This is the one." I'm, like, perfectly happy if people sort of pick their favorites, but I, I, I do understand that simply giving people a choice, right, like the same way that a restaurant does, creates a little bit of, like, extra work that we put on the user and it's, it's true that if I fast-forward to, like, what is the end state for w- for this? I'm probably not gonna make people pick anymore, right? I'm just gonna, whatever you wanna do, here's the one place where you do that. But right now it helps us quite a bit to know, are you just showing up to get some quick answers? Are you showing up to, like, do deep, meaningful work, or are you showing up, showing up to do engineering work? Like, those are sort of the three buckets we put you in right now, and knowing that ahead of time makes it a lot easier for me to give you an experience that is really, really good depending on what, what you came for.

   9. CVClaire Vo5:34

      Yeah. I, I like that because a lot of what I tell folks is we are really pre-convergence on AI tooling just generally and AI experiences. And so my answer to, you know, how do you wanna, how do you wanna use it? It's like, why not all of them? Just depends on the day. Depends on the day if I want my phone to be a taco or a, or a glass, glass pebble, and it honestly depends

4. 5:55 – 9:52

   Using Claude Cowork to design a new house using floor plans

   1. CVClaire Vo5:55

      on what mindset I'm in. Well, we're gonna talk a lot about product at the end, but to start, this is How I AI, and we wanna know-How you Claude. And so we were talking before we got started, and I said, "You know, we've done a Claude Cowork 101 episode with JJ. We've done a lot of Claude Code in the terminal episodes, but we wanna know how, how you use it because you probably know the edges and secret features and, um, some workflows that maybe folks wouldn't think of." So I'd love for you to walk me through one of your favorite Claude maybe Cowork workflows that you're using these days.

   2. FRFelix Rieseberg6:32

      You- you'd think that I would be much better at using the tools than other people, right? Because, like, my entire job is to, like, build them, work on them. And an interesting thing is happening where whenever people show me something, like, super impressive in how they, how they use Claude, like any of the product services, it is pretty rare that I'm impressed by something the model is capable of. Like, I sort of know the model capabilities. We have a pretty good understanding of what the model is good at, what it's bad at. And usually what impresses me is, like, the creativity in structuring your work and coming up with an idea. That, that is usually what impresses me quite a bit. But, um, my favorite example sort of, like, change week over week, it kinda depends on, like, what I'm, what I'm, what I'm currently working on. Carrie, you and I, like, right before we started the interview-

   3. CVClaire Vo7:15

      Mm-hmm

   4. FRFelix Rieseberg7:15

      ... like, briefly talked about our kids and, like, how, how we both recently had kids and, like, if you'd asked me three months ago, I would've said, "Oh, like, just putting all my medical documents into a folder-"

   5. CVClaire Vo7:25

      Yeah

   6. FRFelix Rieseberg7:25

      ... and, like, constantly annoying Claude with all the questions I didn't have time for in the hospital is, like, an excellent use case. But one that I've, one that I've quite enjoyed recently was, um, I'm about to move. I'm about to move into a new place, and, uh, my realtor just gave me the, the little, like, marketing floor plan that you get from, from a real estate company, um, and it didn't have any units in it, like, whatsoever. And [chuckles] this is, like, the kinda thing where I turn to Cowork, and what I've done is I have a folder, and I, like, made, made a very similar-- Oh, sorry. I made, like, a similar fake folder that doesn't contain all the same, like, secret stuff, but it contains fake documents about, like, an artificial house, an artificial house I'm, like, picking. And I'm just gonna select this here. I'm gonna say always allow. Um, it's the demo folder. And the demo folder contains all the disclosure, disclosures you would get.

   7. CVClaire Vo8:17

      Mm-hmm.

   8. FRFelix Rieseberg8:17

      It's a floor plan. It contains, like, information about the mortgage, um, any kind of, like, records that I could find about the house. And, um, I remember saying something along the lines of, um, "In this folder, you can find a floor plan. Can you figure out what the units for that floor plan are, and maybe make me a new one with units?" Right? And you can fire this off. This doesn't actually need that smart of a model. I've actually... I actually did that with Sonnet, so you can, like, just fire that off, and it's gonna go off and do, do that work. This is a fake house, so it's not gonna do nearly as interesting of a job. But for me, what it did was, um, I'm gonna, I'm gonna move to Marin, broadly speaking, and it figured out that-- it figured out that it found a permit for the garage, and I was like, "Oh, now that I know how big the garage is from the permit, I can, like, do everything else for you." And, uh, maybe I'm gonna share my, my other screen in a second. But the, the next thing that happened was once this is done, I was like, "Cool, now that I have a floor plan with units, can you come up with, like, some examples for interior design?" Like, I just wanna, like, see some possible layouts. Where can the bed go? Where can the nursery go? What can we do here? And Claude wanted to know, "How, how do you want that? Like, do you want me to just, like, put the furniture in the floor plan?" And as I was writing the answer, I was like, "Never mind. I need an interactive planner. I wanna be able to, like, move the furniture around." And ever since that has happened, I've just been, like, obsessed with how Claude did it, so I'm just gonna show you how Claude did it. Let me just, like, make a new window real quick. Um-

   9. CVClaire Vo9:51

      Great. And,

5. 9:52 – 12:37

   When to use Opus versus Sonnet 4.6

   1. CVClaire Vo9:52

      and while you're doing that, I have to ask you a question because you very quickly said, "This is not a problem that needs the smartest model," and you switched from Opus to Sonnet.

   2. FRFelix Rieseberg10:02

      Yeah.

   3. CVClaire Vo10:02

      Give us your, like, quick when you need the, the beefy model and when you can go with good old reliable Sonnet 4.6. What, what's your heuristic there?

   4. FRFelix Rieseberg10:11

      I think people probably don't have to think about it as deeply as I do. Like, I think for most tasks, Sonnet 4.6 is actually very, very good. It is very, very good, and it's pretty rare for me that I bump into the ceiling of Sonnet 4.6. This might be in part because the kind of things that I do every single day, especially in my personal life, are just not that tricky, right? Like, going and finding, finding the right floor plan on, like, a, on, like, a public website and then making a new floor plan is not that hard. But I get what you're saying, right? Like, what, what does that mean, not that hard? Like, where's, where's the line for not that hard? My heuristic is usually, um, my tolerance for the model not having thought through very exactly what the actual problem is. Let me explain that a little bit more. Like, I think if you think of, if you think of, say, a lawyer or an attorney or an accountant or a doctor, a g- a big chunk of their work is that they not just give you the exact answer you're looking for, but they also, like, need to sort of reinterpret what you're actually asking. W-what are you really trying to figure out? That is, like, a pretty important job. Um, and any of the creatives who are listening in, right? Like, in creative work, that is the most important piece of your job is, like, figuring out what does the client actually want because usually what they come in, in the door with is not really what they want. And I reach for Opus over Sonnet if I have self-identified as someone who doesn't really know yet what they're asking for. Is that helpful?

   5. CVClaire Vo11:41

      Yeah. I mean, it, it seems more like your ability to scope the problem is how you, is how you choose versus, you know, biting off something... I, I mean, I guess if you were to bite off something incredibly technically complex, maybe you would reach for Opus.

   6. FRFelix Rieseberg11:55

      Yeah.

   7. CVClaire Vo11:55

      But it seems like more how it decomposes generally stated problems into more specifically stated problems it can solve. This is a very specifically stated problem, which is I have a floor plan. I need units for that floor plan. I need a new one. So that seems a well-scoped problem for 4.6. I will say II love 4.6. I use it a lot. It's been, um, via API, a very happy, uh, player in my open claws. So I, uh, I like the 4.6. Makes me happy.

   8. FRFelix Rieseberg12:25

      Yeah. It's like a, it's a-- it has a really good soul and structure that I quite appreciate.

   9. CVClaire Vo12:32

      Yeah. Yeah, it's wonderful.

   10. FRFelix Rieseberg12:32

       But, you know, it's a little bit like-- It's like a restaurant menu again. Like, no wrong, no wrong answer.

6. 12:37 – 14:30

   Building an interactive 3D furniture planner

   1. FRFelix Rieseberg12:37

      It's not really. Okay. So Claude came back with, like, this interactive planner, and this is the thing that I find so cool. This is why I've been obsessed with this, and I've been, like, telling people about it for a long time now. So in, in theory, this is a pretty normal furniture planner. You can just, like, go ahead and, like, move furniture around, right? Like, this is no big deal. But, but what Claude did is Claude used Python, and this is maybe a thing I should explain. Cowork gives Claude its own computer. So Claude and Cowork is its own little developer. It ha- it has its own computer, a virtual machine, where it can develop whatever software it needs to do to solve your problem really, really well. And in my case, it, like, analyzed the floor plan and then built a 3D model of the house where I can still move the furniture around in 3D, and I can, like, drop in and, like, walk around, like, and, like, sort of look at things myself. At no point did I tell Claude, um, "Hey, you, like, should do this." Like, at no point did I, like, go inside and say, "You should make me a 3D model." I have also no idea how you actually do that. I'm a, I'm a pretty good software engineer. I have no idea how you turn, like, a 2D floor plan, I think, to a reliable 3D plan. I peeked a little bit at the transcript, and it did some contrast analysis on the floor plan to figure out where are the walls, how thick are the walls. But I found that really impressive. And then a thing I often like to tell people is that Claude gets a lot more powerful for your personal life if you manage to get-- give it context, right? Context in the form of your emails, your calendar, the kinds of information that is important to you to get your task done. And in this instance, a task that was pretty important was figuring out what kind of furniture I have. And in the, in the olden days, I probably would've, like, looked up what furniture I have, looked up the dimensions, cut that out of paper. Um, but in this case, I just told Claude, "You have access to my emails. You find all the furniture that

7. 14:30 – 15:58

   Using your email as a source of truth for personal inventory

   1. FRFelix Rieseberg14:30

      I bought, and then please, like, add it in here so that I can move around the furniture I actually have."

   2. CVClaire Vo14:34

      I just wanna pause so people really reflect on that use case, because I think they, they could gloss over it if they don't hear it again, which is using your email as a source of truth for personal inventory, which is all of your purchases end up going through your email. Um, so you're buying furniture, you're purchasing rugs, you're getting receipts, even maybe moves that you've done in the pa- I was thinking about this. I've moved maybe twice in the last ten years, and I've had to do that inventory manually and email it to moving companies. And if you use your email, which I don't know, I'm sure your, your personal email is like my personal email, which is just sprawling and completely inconceivable to, like, manage through, and you use that as a source, connect it to Claude, and then inventory your stuff, then you have, like, a, a structured source of data out of your email. I'm gonna do this with my clothes, honestly. Like, you buy clothes, you're like, "What do I have? What do I have?" I can look in my closet, or I can look at my email, 'cause we're all shopping online. Are there other things that you found, like querying your email, querying your calendar, like, that have been interesting kind of slices of data you wouldn't have thought of?

   3. FRFelix Rieseberg15:45

      I think what you're saying, like, really resonates, right? Like, especially the clothing thing. This is an idea I didn't have yet, but, um, now that you mention it, you can, like, build yourself a virtual closet and then use Claude to, like, get advice about, like, what to extend and, like, what, what else to buy.

8. 15:58 – 23:14

   The anti-to-do list: going one abstraction layer up

   1. FRFelix Rieseberg15:58

      For me, and this is, like, honestly the trick, this is, like, something I have to remind myself of every single time I use AI is, um, there was a brief moment where I started entering, like, manual furniture, right? Like, the furniture planner had this little thing at the bottom where you could enter, like, my bed is, like, this wide and this deep. And, like, in the middle of it, I was like, "What am I doing? I'm just gonna tell Claude I have this piece of furniture." And then I went another step up. I was like, "Again, what am I doing? Why do I need to tell Claude what kind of furniture I have?" Just like, "You figure out what furniture I have." And, like, applying this, like, step up in abstraction of the task and doing that over and over and over again and then, like, spending all of my energy on the piece that is maybe, like, more fun and more creative, which is, like, steering Claude on what the, what the house planner should be like or, like, adding stupid little features, like I wanna walk-- be able to walk through the house myself in 3D like it's a video game. Those are the things that I spend my time on. I spend my time less on, like, figuring out what was my furniture, when did I buy it, who did I buy it from. Um, because I don't know for you, but for me, certainly, I did, I did have this problem that I look at my house, I'm like, "I have no idea where I bought all of this stuff."

   2. CVClaire Vo17:08

      Wait till, wait till your kid starts bringing more and more stuff into the, into the house. And I, I do a very similar thing. I've been spending a lot of time with executives trying to figure out how to scaffold their own operating system with AI. A lot of times with Claude Cowork at the center of it. And my rule, I call this, like, the anti-to-do list, which is anytime you're-

   3. FRFelix Rieseberg17:27

      Yeah

   4. CVClaire Vo17:27

      ... like, doing something that's tedious, I just-- I'm like, I smack their hands. I'm like, "Why are you doing-- You don't do that. Your hands are not allowed to touch this. You need to go ask again," go that abstraction layer up. How could Claude do this? And then how could I never do this again, I think is, is the next question, which is if you wanna keep this, this, um, furniture or household inventory going forever, the next abstraction would be like what's the system that in a year or two years if I have to ask this question again, it, it's already there and ready for me to go? And so that's the other piece that I think people kind of miss is going that next layer up, which is like how will I never have to do this again?

   5. FRFelix Rieseberg18:07

      Yeah. Yeah. This is, this is really good. This is really, really good. Like, what you're saying makes a lot of sense to me because, like, I also frequently-- I frequently thenTake the same step to what you're saying, of like how do I keep this going? How do I make sure I can continue using this and like the new data makes it in and like it continues to be helpful in my life on an ongoing basis, not just a point in time. And, um, like a thing that happened to me recently is, um, a lot more people have figured out that they can just like message me on Twitter to like solve their problem, which is nice. But it, it created this problem for me where now suddenly I have to keep track of my problems. And, um, I did briefly like-- Uh, sorry, not keep track of my problems, but keep track of my promises. The promises I make to people, right? Where I'm like, "Send me your logs. I'll look at them. I promise you I'm gonna figure out whatever went wrong." And that too is a problem I just gave Claude. I was like, "Dear Claude, you can read all my messages. I want you to keep track of all my promises. I also want you to figure out how you can do that without like rereading all the messages every single time I talk to them."

   6. CVClaire Vo19:08

      Yes.

   7. FRFelix Rieseberg19:09

      And all of these things Claude is like good at. I have never actually looked at like Claude's little database. I think it like created both a SQLite database as well as like a mountain of text files.

   8. CVClaire Vo19:20

      [laughs]

   9. FRFelix Rieseberg19:20

      Keeps track of all the promises I make to people. But it's quite good occasionally reminding me of like, "Hey, just so you know, two weeks ago you said you would do X. It is time to do X. Please go do X."

   10. CVClaire Vo19:30

       What I, what I like about what you're saying too is while you might be curious about how these things are built, you also aren't getting in your way being like, "How do I build the perfect 3D renderer of my house?" Or like, "Oh my god, I cannot believe this is text files. This is so ridiculous." Like as long as it solves the problem, you can sort of move on, move on with your life because these are, you know, little micro apps. They're just for you. They don't have to be architecturally, you know, perfect or the code that you would write necessarily, although they're probably pretty good. Um, and so you really get to like how to solve the problem versus-- or that the problem is solved versus how you've solved it being the most important thing.

   11. FRFelix Rieseberg20:07

       Yeah. Yeah, I think that's totally true. Like I, I increasingly started stepping away from, from actually like supervising Claude too closely and really only judging it on its impact. And it's like something that I think for, for people in the workforce, we, we often aspire to that we're really only being judged by like the, the actual output.

   12. CVClaire Vo20:26

       Yeah.

   13. FRFelix Rieseberg20:27

       And I think as a control freak who like, you know, for a long time really needed to like read every single line that Claude writes anywhere, it was a little difficult for me to give up that level of control. But I'm, I'm getting increasingly comfortable consulting Claude with things where maybe I'm not the ultimate authority myself, right? Like, um, there's a lot of things I'm good at. There's an even larger amount of things that I don't know and I'm not very good at. And I think a lot of us are making, making this experience for the first time with getting just a little bit more context on medical issues. This is like, this is like a thing that I think is very universal when I talk to my friends. Like when, when they have medical issues they don't fully understand, at least not completely, and they just have like some questions about the physician's advice, um, they ask it both to the physician as they should, but they all of them without fail will also like ask an AI model of their choice. "Hey, can you just explain this to me a little better? Like I have the following 10 questions about this," right? Like in, in a way their AI has replaced, you know, the usual like Google endpoint for I have the following question about life on the internet. And knowing, knowing that I'm quite comfortable with, with using these tools in a domain where maybe I'm not the ultimate authority has also made it easier for me to not double-checking every single thing it does. Because to your point, like if the answer is always good for-- Like I have no-- Like I am obsessed with software. I've not read a single line of this financial planner. It's just for-- I'm just gonna keep it for myself. It is really only for me and my wife to like design our house. It will get thrown away in a month. But in this moment it is very, very fun and I don't need to optimize it for like a million users.

   14. CVClaire Vo22:13

       This episode is brought to you by Guru, the AI layer of truth for your company's knowledge. Here's the problem: Your AI is only as good as the information you feed it. Most companies are getting confident but wrong answers from AI because their underlying knowledge is outdated, incomplete, or just plain incorrect. Bad information doesn't just slow you down. It costs you money and puts you at risk. Guru solves this by adding a verification layer between your company's knowledge and AI tools. Instead of just hoping your AI gets it right, Guru automatically scores content for accuracy, flags outdated information, and ensures your team gets trustworthy answers every time. It works with the tools you already use, so you don't have to change how you work. Thousands of companies trust Guru to keep their AI accurate and compliant. Ready to stop playing Russian roulette with your company's knowledge? Visit getguru.com to

9. 23:14 – 26:02

   Introduction to live artifacts

   1. CVClaire Vo23:14

      learn more. I wanna go back to something that you, you said, which is, you know, you built this promise tracker, which I think is really interesting. And that made me think about a new, a new feature in Claude that I've been using and playing with a little bit, which is Live Artifacts. And I think this idea-- Actually I'm not gonna, I'm not gonna pitch Live Artifacts on your behalf. I'm gonna let you explain what it is and then maybe you can give us an example of where Live Artifacts could be a helpful tool. It, 'cause because it reminds me a little bit of what you're building with your furniture builder. So just tell me a little bit about that in Claude.

   2. FRFelix Rieseberg23:46

      Yeah, yeah. Here, let me like share my screen again.

   3. CVClaire Vo23:48

      Yeah, yeah.

   4. FRFelix Rieseberg23:48

      Um, and I'll give a little bit of a quick spiel of like what are artifacts, what are live artifacts?

   5. CVClaire Vo23:53

      Mm-hmm. Yeah.

   6. FRFelix Rieseberg23:53

      Why do we have them? What's the point?

   7. CVClaire Vo23:55

      Mm-hmm.

   8. FRFelix Rieseberg23:55

      So, um, generally speaking, what do we call an artifact, right? Like I can say, "Dear Claude, please make me a beautifully formatted page with two poems on it. Format it nicely." Um...

   9. CVClaire Vo24:13

      Beautiful.

   10. FRFelix Rieseberg24:13

       [laughs]

   11. CVClaire Vo24:15

       I like, I like the, the letter form.

   12. FRFelix Rieseberg24:17

       Yeah. The lack of creativity here in the prompt is like, um, is like pretty rough. But, um-

   13. CVClaire Vo24:22

       It's beautiful and nice

   14. FRFelix Rieseberg24:23

       The-- What Claude is now gonna do, obviously, is Claude is gonna figure out, "Okay, Felix wants me to write some poems," and then, um, those should add, uh, those should end up on a page. And, um, this page is what we call an artifact. We, we-

   15. CVClaire Vo24:36

       Yeah

   16. FRFelix Rieseberg24:37

       ... within the Claude world, an artifact is, like, some kind of file output-

   17. CVClaire Vo24:40

       Mm-hmm

   18. FRFelix Rieseberg24:40

       ... from what you've been working on. The furniture planner I just showed you is a single file. That is an artifact. Any kind of PDF you will make is an artifact. Spreadsheet, presentation, all of those are artifacts. And here we go. There are my poems over here on the right. This is a classic artifact. And artifacts become really powerful if you, if you use them in a way that they help with your life, right? Like, the typical examples are reports, dashboards, presentations. And we've discovered that data is a really important piece in your work. Um, like a typical example maybe for the founders out there is, like, a pitch deck, right? Like, you need to go and pitch your startup to 60 different VCs. All of them have, like, slightly different information that they, they rely on. They, they have different reference points in terms of other companies they've invested in in the past. The data should be up to date in those sheets, right? Like, however many, many signups you had is probably different this month than it was last month. So as a founder, you spend a decent chunk of your time making these pitch decks, right? Like, every single week you sit down and you update your pitch deck. And if you, like, abstract away and generalize a little bit what the core problem here is, it's that you have this, like, core idea of something you want, but you want it updated, uh, maybe for the audience. You want it updated with the latest data. And we thought about the idea of can we make an artifact that, like, refreshes itself with the latest

10. 26:02 – 28:37

    Building a personal dashboard with live data

    1. FRFelix Rieseberg26:02

       data? And a good example many people have used in the past is, like, sort of a personal dashboard. So when we say live data, what we use is we use connectors. Connectors are a way for you to get all kinds of information into Claude about all kinds of things. Um, like, we launched the Spotify connector today. I haven't actually tried this yet. This could go terribly well or terribly bad.

    2. CVClaire Vo26:23

       How is... You're live, come on.

    3. FRFelix Rieseberg26:26

       Okay, we'll do it live. So we're just gonna connect Spotify real quick. There we go. I'm gonna have to configure this and, like, actually log, log in. Um, actually, this is good. This is good. Um-

    4. CVClaire Vo26:35

       Yeah

    5. FRFelix Rieseberg26:35

       ... it's not gonna show you my terrible music taste. I appreciate this quite a bit.

    6. CVClaire Vo26:38

       Well, I mean-

    7. FRFelix Rieseberg26:39

       Well-

    8. CVClaire Vo26:39

       ... if, if you are like any of the parents out there, and if, you know, I think this is, like, Bay Area insider baseball, if you're moving to Marin, you're going hard parenting. So if you're like any parent out there, though, your Spotify is going to be white noise-

    9. FRFelix Rieseberg26:52

       Yeah

    10. CVClaire Vo26:52

        ... and then Disney, and then Disney soundtracks. That's it.

    11. FRFelix Rieseberg26:55

        Yeah, one of those two.

    12. CVClaire Vo26:55

        That's it for the next six years of your life.

    13. FRFelix Rieseberg26:58

        That's really gonna be the thing, yeah. But here's what we can do. Um, we're just gonna go ahead now and I'm gonna say, "Hi. Please make me a personal daily dashboard including reports and information, um, from my various data sources, say Spotify, Gmail, Calendar, Notion, whatever else you find that's relevant to my life." [chuckles] Um, you can, you can see, you can see that I'm, like, getting increasingly comfortable just, like-

    14. CVClaire Vo27:32

        Just whatever. Whatever you find

    15. FRFelix Rieseberg27:33

        ... letting, letting Claude figure it out. Yeah, like usually my experience is that, like, whatever ideas I have, Claude will probably come with a better idea and will go a little deeper than me. We'll spend, like, just a little bit more time thinking about this. And then I'm also gonna say, "This is for a product demo. Please do not use any real data. Just make all the data up. Thanks." And then we should probably define some kind of design. That is always a good idea. Um, design-

    16. CVClaire Vo27:59

        Last time you said beautiful and nice. [chuckles]

    17. FRFelix Rieseberg28:02

        Hey, it was beautiful and nice.

    18. CVClaire Vo28:03

        Cool.

    19. FRFelix Rieseberg28:03

        But we can go with, like, something like a modern editorial design, something calming. Yeah, I think that's a good idea.

    20. CVClaire Vo28:12

        That's great.

    21. FRFelix Rieseberg28:12

        Right. Oh, also make this a live dash, a live artifact.

    22. CVClaire Vo28:17

        You know what I wanna show for people is there is this thing called Live Artifacts. I always say when you're prompting something, like, use the magic word, use the incantation, and in this case, the incantation is Live Artifact, um, just to make sure you're getting that, that style of auto, auto-refreshing, auto-updating

11. 28:37 – 30:28

    Being polite to Claude (and why it matters for your humanity)

    1. CVClaire Vo28:37

       artifact.

    2. FRFelix Rieseberg28:37

       Yeah.

    3. CVClaire Vo28:38

       I have to ask you a couple questions while this is loading.

    4. FRFelix Rieseberg28:40

       Please do.

    5. CVClaire Vo28:41

       Do we-- Do you always greet Claude so politely? I've seen a lot of "Dear Claudes" and a lot of, "Hello. Hi, friend." Do you always do that, or is this just a little demo magic trick?

    6. FRFelix Rieseberg28:53

       I always do that. I do think, I do think this might be, like, a thing about the people who work at Anthropic. We probably all have, like, a relationship with Claude that is a little bit more personal than, like, maybe people have outside the company. Yeah, I think I f- I enjoy being polite and nice to Claude.

    7. CVClaire Vo29:09

       Okay.

    8. FRFelix Rieseberg29:10

       I don't curse at Claude. I don't-

    9. CVClaire Vo29:11

       I appreciate that.

    10. FRFelix Rieseberg29:13

        Yeah. Yeah. I think... I, I understand that the-- ultimately the chips don't care, right? Like that's, that's the whole thing. Like we ultimately know that I'm in-interacting with a tool here. But for me, as like someone who cares about my mental health, it's like good for me in my own communication-

    11. CVClaire Vo29:29

        It's good

    12. FRFelix Rieseberg29:29

        ... with anything to, like, be polite and nice.

    13. CVClaire Vo29:31

        Yeah, I ask this question on every podcast, and so you will be the, on the very polite and nice camp. And I say it's not about Claude's humanity, it's about my humanity, is why-

    14. FRFelix Rieseberg29:42

        Right. Right, right

    15. CVClaire Vo29:42

        ... why I'm nice. Yeah.

    16. FRFelix Rieseberg29:43

        Yeah.

    17. CVClaire Vo29:43

        Which is I don't need to get in the habit of being rude in, in written language. I also have found myself, it's so ridiculous, but it makes me feel good, in any broadly scoped problem, [chuckles] I've been consistently ending with like, "I believe in you. I know you can do it and make good decisions." [chuckles]

    18. FRFelix Rieseberg30:02

        That is so important.

    19. CVClaire Vo30:03

        It's like my go-to.

    20. FRFelix Rieseberg30:05

        Do you feel like it makes a difference?

    21. CVClaire Vo30:07

        Yeah, I do. Because I f- I feel like it, it asks me less when I say that because a lot of times I just don't actually wanna be asked my opinion. I often just say, "Whatever you think." And so this is my, my method of saying like, "You make the decisions. I trust your judgment."And saying, "I believe that you can do it, and I trust you."

12. 30:28 – 32:33

    Claude interaction tips

    1. CVClaire Vo30:28

       Look at this. This is beautiful.

    2. FRFelix Rieseberg30:30

       Yeah, this is really nice. Sorry, but before we talk about my dashboard, I have, like, more things to say about, like, what you-

    3. CVClaire Vo30:34

       Go for it

    4. FRFelix Rieseberg30:35

       ... just told me about, like, telling Claude that you beli- you believe in it. Th-- I, I, I think on a very personal level, it is wonderful that you do that because I think it's, like, good for you as the human in the loop. It is good for you. However, however, I have an actual tip for, um-

    5. CVClaire Vo30:53

       Mm-hmm

    6. FRFelix Rieseberg30:53

       ... I have an actual tip for people, like, interacting with Claude. We have noticed quite a bit of difference internally because sometimes the experiments that we're doing here are, I wanna say, a little bit on the fringe of what is possible with operating systems. I'm at heart a desktop developer. Um, I wanna make full use of the computer, and that often means pushing the computer far beyond what, what maybe most people do with applications, um, and like just operating a little bit on the fringe. I'll give you an example of, like, something that we have not shipped, we will not ship. Um, but there's-- Your operating system has a layer in between your icons and your wallpaper-

    7. CVClaire Vo31:30

       Mm-hmm

    8. FRFelix Rieseberg31:31

       ... where you can draw pixels, which draw-- like, is useful mostly for art. The reason you don't have any applications to, like, draw stuff in between your wallpaper and your icons is because there's not much use to be found there. But as a concept, it's, like, fun that you can, like, put things there. And I have frequently found myself telling Claude, um, that something is possible and I know it's possible.

    9. CVClaire Vo31:54

       [chuckles]

    10. FRFelix Rieseberg31:54

        Yeah, sort of the idea of like, "I don't actually know how, but I know it's possible."

    11. CVClaire Vo31:57

        Yeah.

    12. FRFelix Rieseberg31:58

        "We'll figure out how. You can do it." And that does seem to give Claude, like, more confidence in actually going after the task at hand. It, it also, like, preempts a bunch of conversations that Claude and I might have about Claude being like, "Felix, your idea is dumb. You probably shouldn't do this." And I from the get-go can say, "I know I'm-"

    13. CVClaire Vo32:16

        [chuckles]

    14. FRFelix Rieseberg32:16

        "... engaging in art. Please go along with it anyway." Yeah.

    15. CVClaire Vo32:21

        I, I, I love that. So okay, I know it's possible. I say that's my I believe in you, I think.

    16. FRFelix Rieseberg32:26

        Yeah.

    17. CVClaire Vo32:26

        I think you're capable, knowing it's possible, um-

    18. FRFelix Rieseberg32:31

        Yeah

    19. CVClaire Vo32:32

        ... we'll discover the space.

13. 32:33 – 33:55

    Looking at the daily dashboard

    1. FRFelix Rieseberg32:33

       Yeah. Yeah. Exactly. But here we are. This is, this is now my little, like, personal dashboard. The design is, like, something that Claude just came up with on the spot. The widgets it came up with are on the spot. This is like com- this is like clay, right?

    2. CVClaire Vo32:48

       Yeah.

    3. FRFelix Rieseberg32:48

       This can be anything you want it to be. It is very open-ended, but therefore so powerful. People frequently use this to get a little report about what they wanna do in their day, right? Like, just prep me for my day. What are the meetings I need to, like, think about? But again, the thing that is maybe most powerful here is going one abstraction layer up. So I actually don't believe strongly in morning reports that just summarize what kind of meetings you have today. That is not all that impressive. I can just look at my calendar. What is really impressive is saying, "Look at all of my meetings I have for the day. Go figure out who I'm meeting with. Catch me up on, like, the recent conversations we've had. What were the themes there? What were the problems? If y- if it's a coworker, go and, like, figure out what kind of stuff they've been working on in the last week and what stuff they might wanna talk to you about today, and then what you need to know about that concept." You can just, like, keep playing this, like, graph bounds where you go and pull in more and more information to get you prepared even better for whatever your actual work is, and that's where these things get really powerful. And this is the kind of data you can

14. 33:55 – 35:02

    How live artifacts work with connectors

    1. FRFelix Rieseberg33:55

       pull in live and have Claude crunch on the go.

    2. CVClaire Vo33:57

       Well, and I wanna call out for folks a couple things that they might not notice that I think are really unique about, um, these Claude Live, Live Artifacts, which is, one, the killer feature here is this little refresh button up in the top-

    3. FRFelix Rieseberg34:08

       Yeah

    4. CVClaire Vo34:08

       ... which is you can constantly pull in and reload data.

    5. FRFelix Rieseberg34:13

       Yeah.

    6. CVClaire Vo34:13

       And so this isn't this is your day today. Every time you come to this, it's gonna refresh your data and pull the latest in. Then the second thing, and correct me if I'm wrong, is it just is reusing the auth from your connectors. And so-

    7. FRFelix Rieseberg34:27

       Yeah

    8. CVClaire Vo34:27

       ... there's, like, no magic. I have to put an API key in, and where am I gonna store it? It's if you go into settings and go into connectors and connect your stuff, you can use any of those kind of connectors to scaffold out one of these live artifacts. And, like, look at this list of stuff. There are so many things that you can just one click, add in, sign in through OAuth or whatever, and then you can build a live artifact in Claude-

    9. FRFelix Rieseberg34:52

       Yeah

    10. CVClaire Vo34:52

        ... without having to, like, ask for an API key.

    11. FRFelix Rieseberg34:56

        Exactly. And it can be-- You know, it's not just the ones we have in our, in our little, like, connector store. You can

15. 35:02 – 37:55

    Redesigning the dashboard

    1. FRFelix Rieseberg35:02

       also connect your own. It, it is quite powerful, and the thing that I enjoy about this the most, this is, like, probably fairly unique to myself, but the thing that I enjoy about this the most is the amount of creativity you can pull in and how you can really shape this in your image, right? Like, we could go in and say, "I want this to look like a, a software made in the early 2000s."

    2. CVClaire Vo35:24

       Oh, um-

    3. FRFelix Rieseberg35:25

       Um-

    4. CVClaire Vo35:25

       This is my-

    5. FRFelix Rieseberg35:25

       Oh, 2000s is maybe... 200 is too early.

    6. CVClaire Vo35:28

       No, let's see what it does. [laughs]

    7. FRFelix Rieseberg35:31

       I mean, honestly, this is Claude. Claude, Claude is probably smart enough to know that I meant the 2000s.

    8. CVClaire Vo35:36

       Well, this is-

    9. FRFelix Rieseberg35:37

       Um-

    10. CVClaire Vo35:37

        ... my go-to Claude Design use case, which is I, I did an episode on Claude Design earlier this month, and I redesigned Lenny's newsletter in, like, 1999 Geocities style. It is incredible. We'll put the link in the show notes. It did an impeccable job-

    11. FRFelix Rieseberg35:56

        Yeah

    12. CVClaire Vo35:56

        ... at this. And what I told people is it, it wasn't even the design that was really impressive to me, it was the copy, was so perfect.

    13. FRFelix Rieseberg36:05

        Oh, was it, like... Yeah, was it like Geocities era-

    14. CVClaire Vo36:08

        It was Geocities era copy

    15. FRFelix Rieseberg36:10

        ... loyal?

    16. CVClaire Vo36:11

        It was 11 out of 10 exceptional copy. Um-

    17. FRFelix Rieseberg36:16

        Beautiful.

    18. CVClaire Vo36:17

        I wanna see if it's gonna do 2000s or 200s. 200s would be way funnier.

    19. FRFelix Rieseberg36:22

        We can probably look at it already, see, like-

    20. CVClaire Vo36:24

        Oh, it did 2000s

    21. FRFelix Rieseberg36:26

        ... in wording, it's 2000s. Like-Claude is smart enough. It knows-

    22. CVClaire Vo36:29

        Knows it's too much

    23. FRFelix Rieseberg36:30

        ... knows too much. Knows too much. And also, I mean, this is obviously like a bit of a demo account.

    24. CVClaire Vo36:34

        Yeah.

    25. FRFelix Rieseberg36:34

        But if you-- if, if I showed you my real account, Claude is, like, quite used to the fact that I constantly misspell things and, like, talk to it in a slightly different style. I'm like, I'm, like, eager to see how this is gonna go. I'm, I'm, in general, quite excited about, um, the amount of creativity you express and especially the amount of creativity people can express who are not software developers, right? Like, this used to be this entire domain where, um, you were maybe a designer working at a software company and, like, maybe then software developers would execute your vision, or you, like, picked a medium where it's a little bit easier, you can, like, low-code things. But I think what is really exciting to me is that we can now pull in people from all these different, from all these different, like, expertise areas, and they can all build these artifacts, like, be that a presentation or be, like, a straight-up tool, sort of in, in the vision they have. A couple of weeks ago, I, I read somewhere that Margaret Atwood wrote about using Claude, and the im-the immediate thing that popped into my head was, "I wanna see software written by Margaret Atwood."

    26. CVClaire Vo37:38

        Yeah.

    27. FRFelix Rieseberg37:38

        Like, I wanna see what, like, tools look like that she has made for, like, writing her own books. Um, that would be, like, so interesting and exciting to me.

    28. CVClaire Vo37:46

        Okay. Margaret-

    29. FRFelix Rieseberg37:47

        Yeah

    30. CVClaire Vo37:47

        ... if you wanna come on How I AI, I would love, love to see, uh, your, your, your Claude setup.

16. 37:55 – 41:52

    The biggest gap: people don’t know what problems AI can solve

    1. FRFelix Rieseberg37:55

       Me too.

    2. CVClaire Vo37:55

       And out of curious, while this is-- We're gonna make this happen. While this is loading-

    3. FRFelix Rieseberg38:00

       Great

    4. CVClaire Vo38:00

       ... I do wanna call out because I do think there's a gap.

    5. FRFelix Rieseberg38:03

       Mm-hmm.

    6. CVClaire Vo38:03

       People listen to and watch How I AI along a, a broad spectrum of technical capabilities. So we have the most AI-pilled, float through the tokens, intense software engineering folks that are really pushing the edges of what these tools can do. And then we have very ver-very early users who are just coming to this in sort of a naive growth mindset way and saying, "I need to solve a problem." The biggest gap that I see, which we were, again, talking about before we started recording, is it's not the capabilities of the tools, it is literally people being able to understand that almost any problem can go into these tools and what, like, a workflow would be. And this is why we've done this podcast. And on, um, the, the ChatPRD website, we have I think it's now close to 200 AI workflows that we've listed from this podcast. That it's just like if you're trying to solve a personal problem with Claude Code, here are the 15 ideas that we've seen on the podcast. And I do still think there needs to be this education and muscle memory change of you can build yourself a daily dashboard, you can build yourself a newborn sleep tracker. Hey, you're moving? Why not throw it all into a folder and then make your life easier as you're trying to close on the, on the house? And I think people still-- The gap between technology and the use case is still pretty, pretty broad. And so, you know, my, my advice is, like, if you're fussing with something on your computer, ask Claude to do it. Any other, any other tips you've seen on how to, like, discover use cases?

    7. FRFelix Rieseberg39:33

       Y-Yes, but I think, I think before I even give you an answer, I just wanna, like, underline how correct I think you are. Many years ago, I spent a decent amount of my time, like, I, I spent five years at a company called Slack, which I think, I think now is, like, fairly well known as, like, this chat tool that a lot of people use. And people were sort of, like, using Slack for different reasons, but they were all more about the way they organized their work with other people rather than it was about the tool itself. So Slack by itself, if you used it the exact same way you would maybe communicate with emails in a silo, was not all that useful, right? Like, Slack becomes really powerful if you open it up to the idea of what if you communicate more transparently and people can see what's going on, and we, like, sort of instead of having email threads, we have a channel, and, like, the channel is open to anyone who wants to see what's going on, right? Like, it's this transformation of work and the transformation of how do you actually organize communication with other people. Um, and AI is, like, in a similar vein of it, it beco- it, like, opens up so many opportunities that to harness them all, you probably have to change a little bit how you work, like, if you really wanna harness them. And yeah, I think you're right that, like, one of the biggest problems we have as an industry overall is not even, like, training the models and making the models very smart and making them very powerful or giving them the tools that allow them to turn that intelligence into, like, output. The, the, the biggest hurdle we have is how do we design the, the human model interface? How do we make this very easy for humans to harness? And right now, I think the way it shows up is that humans are sharing these, like, tips on how to use this resource, right? I think the tip that you gave was a good one. It was like constantly, whenever you do something that you find annoying and you're not enjoying, and it doesn't feel creative, and it doesn't feel like something where, like, you're, you're, you know, it doesn't feel like the, the core of what you really wanna do right now, that is a good time to pause for a second and, like, wonder, "Is there a way I can, I can use AI to do this?" And then, of course, and this is probably not surprising, but of course, like, many people have a decent amount of success just, like, asking Claude, right? Just ask Claude, "How would you help me with this task?" And usually comes up with a pretty good idea.

    8. CVClaire Vo41:51

       I call this

17. 41:52 – 42:30

    The reverse interview

    1. CVClaire Vo41:52

       the, like, reverse interview, which is just going into Claude and being like, "I am a mom of three boys. I run too many businesses for my own good. And, uh, you know, my biggest challenges are X, Y, Z. How can you help? Interview me, and then tell me how you can help me." That can be a really good, um, exercise because, again, people want the guidance of, like, do you have problems with your calendar? You know, are your kids in any sports? A-any, any of those things. And so I do think this sort of, like, reverse interview where you can use Claude or whatever AI tool to sort of solicit out of you the ways it can help solve

18. 42:30 – 44:05

    Making latency delightful through asynchronous design

    1. CVClaire Vo42:30

       your problems is a really, a really good one. And then again, while we're sitting here, I have to ask you another question because I think the, um, Anthropic and the Claude products are so well known for this.But we are chit-chatting right now because we are waiting for Cowork to load, and one of the things that I think you all have solved is making loading delightful. So give me your thesis on how to make a product with built-in latency not so annoying to watch loading.

    2. FRFelix Rieseberg42:59

       Honestly, the most important piece is probably to just get comfortable. They help users get comfortable with the idea that things are asynchronous, and I think most humans are actually quite comfortable waiting for something if the quality that they get at the end is very, very good, right? Um, that, that is generally something we're, like, quite comfortable with. And, like, maybe in the example of Slack, like, this is a good example of Slack. Um, this w- this was a problem we had fairly early on. The first version of Slack that I worked on, when you hit send on a message, it would immediately succeed or fail. Immediately. Right away. And of course, the problem is the internet itself. The internet as an entity is not very stable. It's like this complex mesh, so, like, messages would frequently fail. And we fairly quickly replaced that with, with a version that, like, tries sending the message once, twice, three times, and only after, like, a good couple of seconds if it failed, it would be like, "Hey, by the way, something seems to be off here." And this is the same way that, like, iMessage works today, right? Like, if you send a text message, it's okay if you're currently in a tunnel. It's gonna, like, try again, um, like, about

19. 44:05 – 45:28

    The redesigned dashboard

    1. FRFelix Rieseberg44:05

       a second after. Okay, we can update this. Ah.

    2. CVClaire Vo44:08

       Ooh.

    3. FRFelix Rieseberg44:09

       I... This is beautiful. Here, let me make this big. To my heart-

    4. CVClaire Vo44:13

       This is good

    5. FRFelix Rieseberg44:14

       ... this is, this is, this is very good. Okay.

    6. CVClaire Vo44:17

       [laughs] I love How I AM moments where we're real delighted about the technology.

    7. FRFelix Rieseberg44:23

       Yeah. I'm like, I'm, like, such a nerd for this stuff. Um, I'm, like, mildly obsessed with, like, software in the early 2000s. But yeah, this is beautiful. I'm a big fan of this.

    8. CVClaire Vo44:34

       Mm-hmm.

    9. FRFelix Rieseberg44:34

       Um, this is quite good. I love, I love that it, like, brought in... I saw in the thinking notes that it was like, "Felix requested Spotify, but we're in the early 2000s. We should talk about Winamp."

    10. CVClaire Vo44:43

        Winamp. I know. I was gonna say you need to skin your Winamp module here. Um-

    11. FRFelix Rieseberg44:48

        This is beautiful. Yeah.

    12. CVClaire Vo44:49

        This is beautiful. Okay.

    13. FRFelix Rieseberg44:52

        Um-

    14. CVClaire Vo44:52

        So we're gonna wrap what we were talking about, which is loading screens. Get comfortable with latency. I think realize when tasks don't need to be synchronous, and build that concept into your product. And then look at that. We just chit-chatted for a while, and as we were talking about latency, Claude must have been listening and said, "I'm gonna show them."

    15. FRFelix Rieseberg45:11

        Yeah.

    16. CVClaire Vo45:12

        "I'm gonna, gonna bop this right open." And, and, and again, folks, not paying attention to the details, look in the top right. The clock is moving. It's ticking along in the seconds. You have this refresh. This is... I, I wanna, I wanna open up and look at this

20. 45:28 – 46:44

    AI should free up your creative energy

    1. CVClaire Vo45:28

       every day.

    2. FRFelix Rieseberg45:29

       These are pretty fun, and you can, like, envision, like, you can shape this in any form you want. But I'll finish. I'll give you one tip-

    3. CVClaire Vo45:35

       Yeah

    4. FRFelix Rieseberg45:35

       ... on, like, how to actually build these things that, like, where you gotta wait a little bit, and, like, people need to wait for them and get a little uncomfortable with waiting. I think for us as Anthropic or, like, maybe for me as a product builder, I will always trade off taking a little bit longer and giving you a better result. I think ultimately that's better for humans. And the thing I probably wanna teach people is that it's okay to, like, not watch Claude as it's actually working, because that is not super... That, that is not really the vision I have for AI, is that we humans just, like, sit around and do nothing and watch the AI do the thing that otherwise we could just do ourselves. Like, the thing I always say is that AI is used poorly if, if it just needs to move the mouse cursor for you. The thing I really wanna do is I want AI to, like, do a bunch of annoying things in the background to free you up for your creative energy, so you can come up with ideas as good as make a daily planner look like it was built in the 2000s. You will have better ideas than me. But I think, I think it's sort of like actually moving people from having to watch the thing into a position where they get more comfortable not watching it, and I think this has more to do with trust than it has to with patience.

    5. CVClaire Vo46:42

       I love it. Well,

21. 46:44 – 52:33

    Building a $20 hardware Claude buddy

    1. CVClaire Vo46:44

       we do have one last little demo that you're gonna show us basically on that topic-

    2. FRFelix Rieseberg46:48

       Oh, wow. Yeah

    3. CVClaire Vo46:49

       ... which is how you know when, when Claude's done, and this is actually the thing that I reached out to you about doing because I love it so much. Um, but-

    4. FRFelix Rieseberg46:58

       It's great to-

    5. CVClaire Vo46:59

       But, but talk to us about the little stick.

    6. FRFelix Rieseberg47:01

       Yeah. So, um, in the interest of, like, getting really creative and, like, being more comfortable with, like, areas you're not very good at, um, I have always been, like, mildly obsessed with, like, these, like, little hardware devices, and I'm just not, I'm not a hardware developer. I, I've never really, like, soldered anything together. I'm not a hardware developer in any, in any shape or form. But it occurred to me that I can just go on the internet and buy all of these components myself. I saw a tweet yesterday on Twitter from someone who said, "Hey, if you wanna build your own, like, if you wanna build your own e-book reader, the components are actually quite cheap and very available." Um, and it occurred to me that I can just connect this device to Claude, and we talked a lot about Cowork, but we also have Claude Code, right? So I have built this little thing, which is just, like, a teeny-tiny, teeny-tiny Claude, like, on a little stick, and this stick has Wi-Fi, it has Bluetooth. So let me tell you what this is. So the internet is a magical place, and on the internet, you can just exercise free will and buy whatever you want. Um, and what you can now buy is you can buy, like, these teeny-tiny hardware devices with a perfectly good L-LCD screen, LED screen. This thing has Wi-Fi, it has Bluetooth, it has a little bit of disk space, um, and you can program it. You do need to program it in a low-level language, but you don't... Right? We live in the future. You don't need to, you don't need... Who cares? So what you can do is you can just straight-up connect this. Like, this is a little stick right here, right? Like, you can just straight-up connect this to your computer and just plug this in. And then all I did was I told Claude Code, "Here's, here's my vision. Here's my grand creative vision. I want, like, my little Claude to live on this thing," and I want it to, um, cheer me on every single time I do a good job.And also every single time I need to approve something that Claude is doing, I want it to like be on this like big button that is out here. And Claude has built all of that in like one shot. I've needed to correct absolutely nothing. And I've since seen on the internet that a lot of other people have like built similar things because we-- I, I open source my code, so people can play, can play with it. But I've also since seen that this is just like the, the tip of the iceberg. There's like so more, so many more cool devices out there. This, by the way, so this thing is $19. It has Wi-Fi, it has Bluetooth. I've already mentioned this like many times, but I can't, I can't get over, I can't get over the idea... We've been talking a lot about like how we optimize our, our lives sort of as it happens on a computer, right? Like, because that's where we live. But I keep having this idea that I can just like underneath Claude onto like all these little hardware devices and also improve my-- And by improve, I mean just make like more delightful and make it a little cuter. Um-

    7. CVClaire Vo49:45

       I, I did a very similar thing in a recent episode. I bought-- It's like, um, it's preloaded with this proprietary software, but it's like a tiny retro computer, very Windows 2000.

    8. FRFelix Rieseberg49:56

       Yeah.

    9. CVClaire Vo49:56

       And I had to hack into that thing. I was like Bluetooth sniffing between the like iPhone app and the thing. I was like dumping all the logs in and being like, like backwards engineer the encoding of the, the, the files into this thing. And I finally got it and made myself a little CLI tool where I can type and it just [laughs]

    10. FRFelix Rieseberg50:17

        Yeah. But see, that is so cool. That is so cool that we can do that just now. Like I... This thing also communicates over Blu-Bluetooth. Um-

    11. CVClaire Vo50:24

        Yeah

    12. FRFelix Rieseberg50:24

        ... I learned a lot about the Bluetooth protocol as I was building this-

    13. CVClaire Vo50:28

        I did too

    14. FRFelix Rieseberg50:28

        ... just by osmosis. Um, do you wanna, do you wanna see it? Do you wanna see this thing?

    15. CVClaire Vo50:32

        Yeah, I do. I do wanna see it.

    16. FRFelix Rieseberg50:34

        Okay. So this is now also like partially live in actual Claude. So you can build something very similar if you'd like. Buy any IoT device of your choice. I'm not gonna make a recommendation, but anything that you find on the internet will probably work as long as it has Bluetooth. But you go into Help, Troubleshooting. You enable Developer Mode. Developer Mode allows access to developer tools and features. We give you that warning because it does require that you sort of know a little bit of what you're doing. It's gonna restart the application. Here we are. And then you have this new developer menu where we hide all of our developer features. This is for people who work with-

    17. CVClaire Vo51:09

        Yeah

    18. FRFelix Rieseberg51:09

        ... NPCs or also for people who wanna build their own little hardware devices. And, um, in here is now a new open hardware buddy, this thing. You will notice that it looks a lot like the one I've actually purchased, um, but it doesn't have to be the same one. I think I made that point here. Follow your heart. Be creative. Um, and you can hit Connect, and it's gonna like scan for this whole thing for like a few seconds to like find it on Bluetooth, and it's found it. There we go. So now it's connected. Uh, it gives me a passcode.

    19. CVClaire Vo51:42

        Okay.

    20. FRFelix Rieseberg51:44

        Cool. So we're now connected and, uh, Claire, you tell me if you can see anything. So maybe what we're gonna do is we're gonna, um, we're gonna ask for like anything that would require any kind of like permission. Um, I'm just gonna say, "Just make a hello world.txt and write it to disk." Um, and the point of this is to just fire something off that will require a permission. Okay, so you can now see-

    21. CVClaire Vo52:10

        I heard it.

    22. FRFelix Rieseberg52:11

        [laughs] Isn't that cute? Isn't that very cute?

    23. CVClaire Vo52:14

        Really cute.

    24. FRFelix Rieseberg52:14

        And if I approve this here-

    25. CVClaire Vo52:16

        [laughs]

    26. FRFelix Rieseberg52:17

        ... then it will be approved. That's how that works. And now Claude is off doing something.

    27. CVClaire Vo52:22

        I love it. We saved the best for last, people. If you have made it this long in our, in our episode, we have saved the best for last.

22. 52:33 – 54:30

    Why kids are magical AI users

    1. CVClaire Vo52:33

       Felix, man, I really like it. And I'm like you. I'm like, I am a perfectly serviceable software engineer, and I have no idea what I'm doing with the Bluetooth protocol and with hardware. And it's just been a thing that I've stayed so far away from. And you'll appreciate this, I think, more, is as my kids get older too, I don't want them interacting with like the full computer thing, but I would love to have little, little things for them to interact with. I think like being able to scope kind of like micro devices to, to a use case, just like we're getting this personalized software is gonna be really fun.

    2. FRFelix Rieseberg53:07

       Yeah. And like, um, one, one of the pieces that's been maybe most joyful about my job is that people frequently send me like little videos of the kinds of things their kids are doing with Claude.

    3. CVClaire Vo53:18

       Yep.

    4. FRFelix Rieseberg53:19

       And, um, the creativity they have is like beautiful, right? Like you can like just take a photo of like a little animal your kid has drawn, give it to Claude and be like, "I need a jump and run. I need a flappy bird, but instead of the bird, it needs to be this little drawn bird over there." Um, and then you put your kid in front of the computer and like truly, truly magical things happen because I think... I'm still wrapping my head around this, Claire. But a truly magical thing is happening with kids because they've never learned what not to ask for. To them, the computer is just like can do anything. And I think to like sort of our generation, we're very used to like things just not working, right? We're like used to like, "Oh, you can't do that." So like, so we've been like living in this mind prison for like 20 years.

    5. CVClaire Vo54:04

       This is very on brand, but my nine-year-old is a daily active Claude user, but he, he's decided he's really into cybersecurity. We're like very hacker adjacent here. And so he's like truly in like Claude in one thing, the terminal other. He's like, "Mom, do you know that your device ID is this?" I'm like, "Yeah, babe, I do, I do know that, but good job. [laughs] Good job." Um, but yeah, I, I think it's totally

23. 54:30 – 59:22

    Recap and final thoughts

    1. CVClaire Vo54:30

       fascinating. Well, Felix, I know we have just been having so much fun this episode. I think people are gonna get so much out of it. Just to reverse for folks, we talked about-Claude Cowork being able to build you artifacts, both sort of like standard crazy 3D printed or 3D, uh, renderings of your floor plan and other things that you can just stand up to solve little problems in your life, all the way to live artifacts that can pull from your live data and really give you a rich personal experience with your data. We touched on a lot of topics, including email as a source of truth data, what we're gonna do with all this latency, and how to pick the smart enough model, which is to say, you know, you know when you need Opus and you know when you need Sonnet, but we both think that Sonnet's pretty good at most things. And then you showed us how we can hack into hardware for the all-in price of 20 bucks, including shipping, and build little, little buddies for ourselves. I'm gonna get you out of here. One quick lightning round question. Again, we did this at the, at, at the midpoint, so maybe you can just answer really quickly. But when Claude is not listening, and we've, we talked about how to set it off on a good path, but when it's really just making mistakes, um, instead of making no mistakes, it's making all the mistakes. What is your prompting strategy? I can't imagine you yell. You don't seem like a yeller. Um, but what, what do you do?

    2. FRFelix Rieseberg55:52

       Yeah, I do not yell. I think, I think it is, it is useful for me to know when people curse at Claude. This is like an, this is like an interesting thing for me to know, um, as a product builder. But my strategy for when Claude doesn't, like, really, really understand what's going on or, like, Claude seems to have gone off the rails, um, I usually try to debug my workflow straight up by asking, "Okay, here's what I actually expected. Can you maybe walk me through at what point you expected something different or, like, how we can maybe prevent this in the future?" It doesn't always work. Claude is AI, and AI can make mistakes. However, however, that being said, I, I have frequently found ways to improve the data source or to improve the amount of noise that is in the data, um, or like with Claude to come up with mechanisms. Okay, how do we, how do we, like, do, do we set up some kind of dry run? Um, I usually end up at a place where the learning I take away is not, "Oh, Claude can't do this. I'm not gonna have Claude do it." Usually, the learning I take away is I can maybe change a little bit the harness, the prompt. I can change, um, something in, like, how we set this up at the beginning. And I think after, after the time we had together now, there's no surprise to you, but, like, usually my answer to that is, like, to also involve Claude and say, "Claude, what do you think we can do here?" Claude is a good friend, and if people need, if people need to vent and people need to, like, externalize their frustrations, Claude can take it. You can curse at Claude.

    3. CVClaire Vo57:21

       Claude can take it. You, you can even do it.

    4. FRFelix Rieseberg57:23

       Um, yeah.

    5. CVClaire Vo57:23

       Maybe smash the button, like have an angry button instead of saying the thing on our little hardware buddy. You can have, like, the mad button and the happy button. You just, "I'm not pleased, Claude," smash, smash, smash.

    6. FRFelix Rieseberg57:35

       Yeah, yeah, and like there, there is a I'm not pleased button that actually also ends up on my desk that I do want people to, like, use. So every single time Claude does make a mistake, we do have the little, like... In, in many of our product services, this is across Claude, you will find the little thumbs up, thumbs down buttons. Those are super useful to us. We use those in training. We use them in, like, improving, improving not just the model, but also the products. So maybe actually the thing I'm gonna say is, like, if Claude hasn't done the thing that you wanted it to, cursing at Claude will probably not fix it for the future, but, like, pressing the little, like, thumbs down button-

    7. CVClaire Vo58:07

       Thumbs down button

    8. FRFelix Rieseberg58:07

       ... um, helps us quite a bit because it does end up on my desk. We deal with it.

    9. CVClaire Vo58:11

       Perfect. Well, this has been super fun. Before we get you out of here, how can we find you? And other than hitting the thumbs up, thumbs down button, how can we be helpful?

    10. FRFelix Rieseberg58:20

        Um, it's really that. That's, like, the, the number one thing that, like, really helps us build a really good product is getting a good sense for what works for people. The option space is so big. We're still in this, like, fun smart phone time. We talked about it. Um, and I do wanna hear from people. I wanna hear from people what works for them, what doesn't work. I'm always grateful for all kinds of feedback. Um, you can find me on LinkedIn and X. Those are the two big places.

    11. CVClaire Vo58:44

        Great, and, and you make promises. You made a promise to me before this, before this call that we will get to after we end. Well, thank you so much for joining How AI. That's, this has been great.

    12. FRFelix Rieseberg58:54

        Thank you, Claire. Yeah, this was fun.

    13. CVClaire Vo58:57

        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

Episode duration: 59:25