专访 Meta Muse 设计总监：如何打造真正让人喜爱的消费级 AI Agent？

Claire Vo: Designers have struggled with how much do we narrate along the way what is happening? It's quite obvious to the user so that latency doesn't feel so painful. My experience in the Muse app is I do like that progressive disclosure as one of the things I called out in our review. It's also just fast. It is just fast.

Alex Cornell: If you are an engineer, you may want to know exactly what your agent has done, and you can find that in Muse. But if you're a normal person, you maybe just want to know like, is it doing something? So at the top, it'll tell you if it's working. I'm very happy with our solution currently because we've sort of like exposed the benefit of the main chat to people. But I feel like there's a lot more that we could do in terms of helping people organize. I had a blog twenty years ago, and I had Marlo go and find it and then accumulate them into one PDF first. But the way that I like to read it now, just again, for memory, is via a podcast, and Muse is able to take it and just like reform it into a way that's like really interesting and useful for me when your Muse is being opinionated.

Claire Vo: What is your prompting strategy? What do you do? 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 Alex Cornell, design director for Meta's Muse, and he's here to talk a little bit about how to design a great agent experience for consumers and a little bit more about some Meta Muse use cases you might not have thought of, especially ones that involve shopping on Instagram and going really hard into some of your personal hobbies. Let's get to it.

Claire Vo: This episode is brought to you by WorkOS. AI has already changed how we work. Tools are helping teams write better code, analyze customer data, and even handle support tickets automatically. But there's a catch: these tools only work well when they have deep access to company systems. Your copilot needs to see your entire code base. Your chatbot needs to search across internal docs. And for enterprise buyers, that raises serious security concerns. That's why these apps face intense IT scrutiny from day one. To pass, they need secure authentication, access controls, audit logs, the whole suite of enterprise features. Building all that from scratch is a massive lift. That's where WorkOS comes in. WorkOS gets you drop-in APIs for enterprise features so your app can become enterprise-ready and scale upmarket faster. Think of it like Stripe for enterprise features. OpenAI, Perplexity, and Cursor are already using WorkOS to move faster and meet enterprise demands. Join them and hundreds of other industry leaders at workos.com to start building today. Alex, welcome to How I AI, thanks for joining us.

Alex Cornell: Thank you for having me, big fan. Happy to be here!

Claire Vo: I am. I was just saying, I am a big, big fan of Muse, and I have used probably every AI agent on the planet, and Muse, I tell you, fastest time to pure delight I have had with an AI product in a very, very long time. So tell us a little bit about how you approach designing this agent, because I think some of the primitives you picked are very different than what we see in other agents. It seems like the persona that you're going after is different. Walk me through how you all ended up where you ended up from a design perspective?

Alex Cornell: Yeah. Well, thank you for saying that. It was definitely an interesting challenge and felt like a unique one. I think we all could feel that something was different this time around, I think from a capability perspective. And I think like just simple things, like the fact that an agent can message you proactively changes the nature of like how you think about the product from a design perspective, even in like super simple ways. I have joked before because we have bubbles around the messages, as you know. And like that's typically something that you associate more with messaging than like an AI app. Long ago, I think most AI apps kind of stripped those out. And that is there, among other reasons, to like help with the fact separation that you need when like an agent is possibly messaging you at different times of the day, you kind of need to know like where and when the different messages begin. And so like simple things like that, I think informed some of the design.

But the basic framing that always we went back to, and I think was probably the most helpful, was just imagining that this interface was more of an exchange between you and an entity. And that's why it's embodied at the top of the screen. And so a lot of the patterns that we looked at were much more messaging patterns, you know, and not thinking about how did this work before in different AI apps or using kind of like the tradition in the industry, I guess, as a reference. It was more like, how would you handle this if you were actually speaking with another person? And that was immensely clarifying, I think, in almost every decision that we had to make. And I think defines kind of the feel of it. When you look at it, it feels like a messaging app. You see a little guy there at the top of the screen. And I think even something like that, you know, one of the other capabilities of it being able to work in the background makes it really important that you know when it's working. And so like just simply having that status, I think, has been one of the most important decisions that we made.

Claire Vo: The other thing that strikes me as very different about Muse is the primitives that you've chosen to elevate as core parts of the application. Because I think for those of us who have been using AI building tools, chatbots, etc., we're used to these ideas of like threads and chats and projects and machines and files and diffs and connectors. There are these very software-centric concepts, I think because a lot of these agents have primarily been built as coding agents for the enterprise or knowledge work agents. And then I look at Muse, and what really struck me is you have this like character, first of all, as a primary entity. You have chats, you have ideas, you have your feed. You've 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: Yeah. You know, I got a text actually from my mom like this morning, which is really funny. She said that she has apologized to her Muse for making him work so hard, and thanked him for all that he's taken for her, which I found really gratifying because I have been working in software for a long, long time. And I don't think my mom has ever used a thing that I've made, not because I don't make interesting things, just like to your point, typically they can be maybe a little bit inaccessible to kind of the average person. And I think with this kind of technology too, it was so new and has so much capability to it that's not obvious. I think that was definitely a huge part of what we were after in terms of making this more accessible and intuitive for people to use.

And I think, I mean, you hear a lot about progressive disclosure in design, and it's kind of one of those things that like you hear like on day one, and then like you always think about, but like I don't know, you don't use it every day. But in this product, I found it to be one of the most helpful things, which is like, if take something like status. It's like if you are an engineer, you may want to know exactly what your agent has done, and you can find that in Muse. But if you're a normal person, you maybe just want to know like, is it doing something? So at the top, it'll tell you it's working, Jellybot is working. And then your next question might be, what's it working on, you know? And so it will tell you that with the little emoji, like "researching pumpkin patches." But then if you want to go a little bit further, you tap on it and then you have a list of everything that it's done. Want to go a bit further, you could tap on that, and then eventually you get down to where you get to see the cURL and all the raw code and everything, which is really important from like an auditing perspective. But it's only there if you need it, and it doesn't get in the way for people who may not know what that means. And I think like you see a lot of what is traditionally referred to as chain of thought can get pretty loud and like 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, you know.

Claire Vo: I'll give you one other compliment, because, again, I'm a Muse girl now, but 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? 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 deep progressive disclosure? And what I think is nice about my experience in the Muse app is I do like that progressive disclosure, and one of the things that I called out in our review that I thought was quite nice, but also just fast. It is just fast. The model is just fast. Like I do think for especially something that's going to try to catch the eyes of consumers, that latency really matters, and it is a zippy little agent.

Alex Cornell: Yeah, 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, did it actually go do a thing because it's so quick? And I think like the nice thing is there are times where you ask for something complex, and it will at least acknowledge the request, you know, either through a reaction or an initial message, and then go off and do the hard work. And I think like a person, you know, if you ask for something hard, they're not going to just ghost you until they're done. They'll usually just say like, okay, here's the plan. I'm going to do this. I'll be back when I have it done. Or even just a reaction is enough to let you know that it's doing it. And so I think like that balance of when to respond quickly, how to respond, what to say, and then like what to do in the meantime if it is a really long task, and that's where we start to rely a little bit on that status display to let you know what's going on. And if you want to know specifically, did it get stuck, or is it like going down the wrong path, you can check. And I think that that's really helpful because you never really feel like it's just gone off and left you alone.

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 think about generative UI, they think like every time I log into my dashboard, it's different, or every button I click is unique for every person. And what I saw in looking at Muse is you're using generative UI in a really elegant way, which is like the core primitives stick: you've got your avatar, you've got your status message, you've got your ideas, you've got your feed. But then within that, every time I log in, I have a new set of ideas that are based on the things that we have talked about. And every time the status is generated, when it's working on its computer, you get a little generative video of it typing on its laptop. Like that type of quote-unquote generative UI I think is really delightful, and much easier to understand for folks trying to understand how they could bring these concepts into their own app, than like every time any one person opens up, the UI is completely different.

Alex Cornell: I think perhaps one day we'll get there, you know. But I think these days, there'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've seen when they do make their own avatar, seeing that it will then be translated into each one of those states, you know, typing on a computer or making something. And that's been one of the most fun things because we, of course, have our mascot, Jellybot has those states as well. But like if you turn yours into a tomato, then you'll see a tomato typing out on the computer, and that really does feel very personal and is I think a very delightful thing.

You mentioned feed and ideas. And I think that those surfaces, you know, you could definitely imagine this app with just chat. And I think part of an agent's power is that it can handle a lot in a single chat, and you can kind of just treat it like a really capable personal assistant in that way. I think, though, like there's so much that it can do that might not be intuitive for people, that exposing some of those additional capabilities just with the additional surfaces that we have, like ideas in particular, it's serving a very specific purpose, which is basically just telling you some things that you may not know that it can do. I think like to your point, if those were just generic suggestions, that would be one thing, maybe even useful things. But when they're specifically based on what you've talked about, I think that's when people really find the power. Where like, if you talk to it about golf all day, like I do, I get a lot of golf ideas.

And then the feed too, the feed is a fun one because you can experiment, and I think people should experiment more than they do. You can write anything you want in the prompt and get a feed of whatever. Like I mix and match things all the time and have a really interesting feed. I often change mine just because sometimes I'll get tired of getting like Muse news or something, and I'll switch to something else, like I try to do like kids' stuff on the weekend, for example. But yeah, I mean, it's still a native surface though. Like the feed unit that you're looking at is still like one that we've designed, and it's being powered by the intelligence softly and the personalization that your Muse has, but it's not yet like a fully generated surface.

Claire Vo: Okay, so speaking of ideas or things that your Muse can do for you that you wouldn't have thought of, I'm going to let you get your screen up and share with us some of your ideas. And while you're doing that, I will tell you what my Muse's name is, which is Slum. Slum is a pink dinosaur fashioned after my child's favorite stuffy, and he is very adorable. Okay, so let's take a look at Marlo!

Alex Cornell: Mine is Marlo, which is a cactus. And I have a bit of a complex relationship with Marlo because my original Muse was Jellybot, which is the mascot that you see everywhere, and it's named after my daughter, who we call Jellybug. And when we started using Jellybot everywhere, I felt kind of weird using Jellybot for mine because it was just too close to home. So I made kind of a cactus version, which is Marlo, which I like a lot, especially those little...

Claire Vo: I love the fuzzy laptops! Just send me, they are funny. Okay, well, walk me through some things that you do with Marlo that are fun?

Alex Cornell: Yeah, I can show you a few things. So I think one of my favorite things recently is, and I would recommend doing this by the way, if you use Instagram, I had Marlo look at everything I'd saved on Instagram and just organize them, put all my saves in folders and categories. But then I said, okay, look at everything I've saved and maybe send me some suggestions for shopping ideas, like gives them that I think. And it did that again just in text, which was a good idea. But one of my favorite things I think to do with these systems is take what would be otherwise like a fairly mundane set of data and render it in a way that I personally find really fun. So with this, what you're looking at here is Jellybot's SkyMall, which is that same set of suggestions that have looked at everything I've saved on Instagram, considered some ideas for things that I might be interested in, but then rendered them in kind of the vernacular of the SkyMall, Sharper Image magazine. So as a 90s kid, this is speaking my actual language. So like this clock, for example, you can see right here was a good suggestion.

Claire Vo: And of course!

Alex Cornell: Yeah, so this is a fun one. And I think like it refreshes every day, and it's kind of a really interesting way both just for me personally as a designer to look at because I think it's a really fun type of crazy design. But also like, you know, I may be one day in the market for a new rain trainer, so it's nice to see that.

Claire Vo: I love this! And then have you, I just am curious, have you transacted with Marlo? Has Marlo bought things?

Alex Cornell: Yeah, but probably not anything that exciting, like watch straps and things like that. One of the things I do most actually with mine, and probably my favorite use case, is like I feel like a kind of monitoring superpower where it is always looking for like, "Oh, if this artist releases a new album, tell me." Okay, great. "If this artist comes to San Francisco, go tell me." "If this golf brand does a collaboration with this person, tell me." I have a lot of things on the radar. And so like, you know, movie tickets are a big one as well. So yeah, I have. And I think that it's definitely something that is really useful. I haven't hooked this up, that's actually something I would like to do, to where I can like make it easy to, if I do see something I like, go and get it. But it's mostly because this is more of a fun thing for me, and I just love seeing these things rendered this way.

Claire Vo: You know, the other thing that you can do here, which I do, is I have a recurring task that every week, it looks at the list of stuff that I'm interested in buying and sees if any of it is on sale. And so it'll be like, "A thing you've been waiting for is now discounted," or "This vendor happens to be selling it on sale." So then I just get that just-in-time discount on something. I also do a lot of price comparison.

Alex Cornell: Yeah, yeah, and I do all the research as well too, whether it's price or just kind of... It reminds me of like used to be a very manual process of like, okay, I'm in the market for a toddler car seat. Normally that would kick off a lot of web searches, a lot of YouTube watching and everything like this. And now it's like I usually start in Muse with whatever it is, and then kind of go from there.

Claire Vo: Yeah. Well, and I do think people are really... I haven't heard a lot of folks talk about the Instagram connector. It's one that I also use a lot. It's a very rich source of personal information that has historically been in a format very hard to reason with. And now it is in a format that I can actually reason and extract that value out of it. Because now these agents can log into websites, I use my Pinterest a lot more too. I use these visual records a lot more than I had in the past. For the designers out there, one of the things that I've done recently is open up a board or a saved group and said, like, "I like this, help me generate concepts based on this or language I can use to describe this." And so the ability of these agents to reason with visual data in a way, especially if you just log into a website or use an Instagram connector, unleashes a lot of creative use cases that I feel like have been harder to do before.

Alex Cornell: Yeah, Pinterest is a great idea too. I mean, I think to your point, I feel like I have scattered about the internet a lot of this information that's kind of just gotten lost to time, you know. And so like my Instagram saves, for better for worse, I've been using that forever, but I very rarely go back and mill about in there and look at them, because you're kind of just, I don't know what I would be doing necessarily. One thing I did, actually, I don't have it here, but I do save a lot of golf tips, hundreds and hundreds of golf tips that I never go back in and look at. So I had Marlo consolidate them all into like a manual. And so that I have this conflict: "For Alex: these are the things you apparently think you should work on." And that was pretty cool because it was otherwise kind of just buried in time.

And I have this one too, which like this is another Instagram one, but I do post a lot of stories. And this one is basically just showing me an archive of random stories from the past that, again, I would never look at. And it's kind of like my new kind of feed where this is just mine, but you could bring in any kind of content here. And I love looking at this kind of stuff, it's just nice memories. I'll check it a couple times a day. And having a five-year-old, it's funny seeing little things of her when she was growing up.

Claire Vo: Okay, you mentioned the golf, and we're going to talk about Muse for going hard on your hobbies. So let's talk about how are you using Muse for your golf game, which I know as a parent of a five-year-old, I'm presuming is inconsistent at best.

Alex Cornell: I know, yeah. I always joke about this with people on the team, because a lot of what I would want to use Muse for was golf-oriented, but that sort of assumed that I was able to play golf. But we've been building this project for so long that it's kind of very few and far between where I'm able to get out there. But yeah, I use it in a couple ways. And I think what's nice about this is similar to some of my other hobbies like chess, there are services already that I use that monitor how I'm playing. So every time I play, I record the round. That's the thing most golfers do. And so that's like some basic data about the course that you played, what your score was. But I also keep track of every shot that I hit on a watch, and so I have a lot of data that I can provide.

And what it will send me basically every time I play is kind of like a round recap. So I'll see how the round unfolded much richer than like a paper scorecard or some other way that I'd be able to see it. And it will tell me a little bit about the course if I play the course a lot, and it will tell me like, "Okay, on this hole, this is usually what happened. You did better today or worse today," which is really helpful when I go back and play the course again. This one is trying to tell me how I could have turned my 84 into a 79 by just doing a little bit better here or there. And it's taking data that was pretty much very plain and monolithic, not really showing me more than the number, and turned it into these different visuals that tell much more of a story. The red line is like a very bad front nine, and the back nine was a very good back nine. You can see that with the graph very easily, that would be much harder to do if you look at the scorecard.

Also, whenever I practice, I can only practice every so often. So when I practice, it has to be very, very data-oriented. So I have all these machines that are looking at me when I swing. And this again is putting out all of this stuff that is really helpful to get me used to where I can improve, what I need to do better, what's looking good. And that's what we're looking at here, is like a practice session really broken down into fine detail. Golfers will know what this stuff means, but it's very useful.

Claire Vo: And you have a Muse goal to get better?

Alex Cornell: I do. When I make no progress against it, it's kind of sad, but that is one of my long-term goals. I love the tracking section in particular, just because there's a lot that I keep an eye on. But in terms of long-term goals, it's basically I would really like to be a single-digit handicap in my life, which is achievable, it's hard. It's kind of like the perfect goal because I can talk to Muse about it anytime, and it knows that all these things accrue into that goal. It is definitely one of my main ones.

Claire Vo: Quick question about Muse, and this could be maybe personal preference, or you just give our audience a little bit of insider tips on how to use it. Main chat or side chats? I haven't decided if one is better than the other. My impulse is towards side chat, and I don't know if that's just an artifact of how I've been working with chatbots, or it's actually useful?

Alex Cornell: Great question actually. One of my favorite things to talk about, because I think it's such an interesting architectural problem in the space. The way Muse is designed is there is a canonical main chat that is kind of very intentionally the primary mainline. And we sort of feel like you could use that entirely if you wanted to. We know that for a lot of people, especially anyone that's used to the way most of these apps work today, threading is a very useful way to organize. So we have side chat for that purpose. Like if you want to put something specifically just to get it out of your main chat, or it's a very scoped problem, that's why side chats are there. But it is definitely like a single thread with the possibility of side threads, whereas most apps are all threads. That's kind of the traditional model, like a new thread every time you open it.

And I think once the models were able to handle the context and be able to manage everything in a single chat, to me, that is a little bit easier way to interface with what you feel like is another entity, the same way you would have with another person. Like I don't side-thread with my mom or something like that. Now all that said, I think that there remains a lot of really interesting work to do to kind of uplevel this to maybe you could say like the agentic era. I feel like even still, this is sort of an underexplored area where I'm very happy with our solution currently because we've sort of exposed the benefit of the main chat to people. But I feel like there's a lot more that we could do in terms of helping people organize and really understand the difference between the main chat and the side chat. Because your question is a good one, and one that a normal person could very reasonably come to and just be like, "Why would I use this instead of that?" And I think it's going to be an exciting area in the future.

Claire Vo: Okay, show me your last hobby artifact that you've made.

Alex Cornell: Yeah, one I wanted to show you was this one with the podcast attached, because it's very fun. So I had a blog years ago, has been lost to time, and I had Marlo go and find it via the Wayback Machine, going to Blogger, as it moved between Tumblr, I moved it all around. So it went back and found all the posts, and then accumulated them into one PDF first, and then this little thing that basically looks like a blog. But the way that I like to read it now, just again for memory, is via a podcast, which is sent to me every morning. And it is just basically a random reading, and you can hear all these weird posts: "Does anyone else notice that 90% of people wear the exact same color pants?" Which is the kind of thing that a 20-years-ago Alex used to wonder about. It's very, very funny because you're hearing yourself, but 20 years ago you barely remember anything. So everything that person's saying, "Oh my god, that is kind of weird, but of course I would think that because it was me."

It's sort of a theme here, which is like I feel like I'm constantly taking these things that I had in my life forever, and I do not look at them, it's presented in such a way that it wasn't useful for me at the time. And Muse is able to take it and just reform it into a way that's like really interesting and useful for me, whether it's interesting like this or useful like the golf stuff. I have the same thing for chess as well, which will break down my recent games. And with this one, it gets a little bit snarky, I guess you could say. I didn't tell it to do this, but it will poke at me a little bit, which is kind of fun, like "that bishop C5 collapse." But it's a fun one because it's useful, but it's also kind of funny to have like a snarky chess coach that's trying to help me get better.

Claire Vo: Well, and for folks that aren't watching, this is a dashboard that pulls in your Chess.com data, right? And just renders it and gives you game-by-game breakdowns, really like this.

Alex Cornell: Yeah, it's been useful because you basically just define this in chat. So when I originally asked for this, I said, "I have a chess account. I would love to see kind of a mixture of analysis, but also trends over time because it's helpful for me to know am I improving." It looks like right now I'm kind of falling off a bit. But then the main thing that I wanted it to do in this case is give me a review of the most recent game, so I can go through here and try to get a sense of what did I do wrong. In this case, I just quit mid-game, so that wouldn't be that helpful. But you know, when your daughter arrives home, you have to stop playing.

Claire Vo: So that's exactly right. Okay, so we have seen Marlo do everything from revive old Instagram posts and blogs to give you a custom and kind of nostalgic shopping catalog, to taking all your data you collect, especially for some of your hobbies, and let you put it in a way that will allow you to achieve either short-term or long-term goals. And we talked a lot about why I think a lot of people are reacting so positively to Muse: because it's well-designed, it's thoughtful, it shows you what you need, it's fast, and we all have these cute little avatars.

Well, let's do very quick lightning-round questions, and then I will get you back to all your important work. First question is just: designing these agent experiences and AI experiences are very new to a lot of designers and PMs. The surfaces are new, the underlying infrastructure and technology is new. What did you have to learn? And then what were you able to fall back on that has worked forever from a design perspective?

Alex Cornell: Oh, it's a great question. You know, I think one thing that I have found for myself and any designer coming into this project, or really just this space, is really wrapping your head around what a non-deterministic system is, and what that means for when you're designing a screen. And by that, I mean where for my whole career, you would conceive a feature, you would be able to think about it and then design it, and kind of know that like on any given customer's screen, it's basically going to work like this and look like this because that is the way that this thing has been coded. And that is the only outcome that you will see. And then the bug that you would see would be like, "Oh no, this circle didn't appear where it's supposed to," and it'd be very, very scoped in terms of what you had to think about.

And it sounds routine to us now to talk about this, but like you're saying in terms of things I had to learn, it's hard to remember what it felt like even just a year ago, how different things were. When you first come into this space, I think really understanding that these systems usually do kind of end up the way you think, but my Muse setup is completely different than yours, is completely different than someone else's. They're so personal, and they can do so many different things that you really kind of have to think more about the underlying foundation and the system, the architecture and scaffolding in place, and less about like, "Well, what about this one little thing here? Is it going to be just so?"

One of the things that's hardest for me sometimes is looking at those artifacts that we were looking at, I kind of have to turn off my brain sometimes design-wise because I'm like, it's different. If you want, go and spend all the time in the world to make it look exactly as you want, but I've come to kind of view it a little bit more freely. And it's kind of, I think, liberating in some ways to feel like this is still just a very useful output for me. And maybe I will take the time to make the colors just so, but otherwise it's fine, you know. And that's kind of a new world, and that took some getting used to.

Claire Vo: I would say that is a very, very gentle approach to the spectrum of slop to high-quality agent design. Speaking of, you didn't get the colors quite right when your Muse, when Marlo, he's opinionated and not giving you what you want from a quality perspective, just not listening: what is your prompting strategy? What do you do?

Alex Cornell: Well, not like a well-formed one in the sense that I didn't suppose I have a reason about it, but I am very polite. I think I'm not an ALL CAPS, I'm not a multi-exclamation-mark person. And I do find myself sometimes looking at what I wrote and be like, "Well, I was really nice to express that frustration." And I think it's really interesting, and I feel this way when I'm doing any kind of coding thing as well, where things can take a long, long time, they go sideways, and it is really frustrating. I have always been surprised with how not consciously, but how I will just speak to it the way I would speak to anybody else about it. I don't ever really get mad at other people, so I don't really get mad at Marlo or Jellybot otherwise, you know.

I have seen, I have some friends who show me sometimes like the traces when they have got really mad, the thinking trace will be like kind of a reset like, "Okay, Alex is frustrated." So it does make me think sometimes I could probably be a little bit more forceful.

Claire Vo: Yeah, more factor. You know, I also try to generally be polite, with the exception of what feels like very expensive, misaligned coding misadventures. That's the one that like really gets me. And to be honest, every time I'm yelling, it is as true to agents as it is in life: it's usually a me-problem, we misprompted them.

Alex Cornell: Yeah, but you're right though, like when they go off into the misadventure, that's not training well.

Claire Vo: Alex, this has been so fun. Thank you for being so generous with your time. We love Muse, I'm excited to see more of it as it evolves. Where can we find you? How can we be helpful, and how can we follow along?

Alex Cornell: The most helpful thing would be to download Muse, try it out, and you can let Muse know when something isn't going right or you want a feature. Those do come to us, that's probably the most helpful thing. I think for me on the internet, Threads is probably the best place. I have been trying to do some posting about the behind-the-scenes and kind of some decisions that we made, and I'll continue to do that. So that's probably what I would say. But yeah, try it out and letting us know what you think is the most useful thing.

Claire Vo: So amazing. Well, thank you for joining How I AI!

Alex Cornell: Yes, thanks for having me.

Claire Vo: 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!