Vibe Check: Claude Cowork Is Claude Code for the Rest of Us

Anthropic just dropped Claude Cowork—essentially Claude Code for everyone, not just engineers—and we got to chat about it with a product engineer at Anthropic who helped build it. In this live Vibe Check, Dan Shipper and Kieran Klaassen explore the new interface together, testing what works (and what doesn't) in real time. Anthropic’s Felix Rieseberg joins midway through to explain the philosophy behind Cowork's design: why it separates "Tasks" from "Chats," how the queue system lets you send messages while the agent is working, and what "agent-native" architecture means in practice. They also dig into Skills—Claude's prompt system that lets you customize how it works—and the Chrome connector for browser automation. This is a raw, unfiltered first look at what might be the future of how knowledge workers interact with AI: async workflows instead of turn-by-turn chat. If you found this episode interesting, please like, subscribe, comment, and share! Want even more? Check out Dan's guide to building agent-native applications: https://every.to/guides/agent-native To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper 00:01:00 - What is Claude Cowork 00:02:36 - First demo: competitor analysis 00:03:33 - Email drafting that sounds like me 00:06:18 - Calendar audit running for an hour 00:07:39 - Book taxonomy demo 00:08:42 - PostHog analytics via Chrome browsing 00:14:36 - Chat vs Code vs Cowork: when to use what 00:31:06 - Felix from Anthropic joins 00:36:39 - Why they built it in a week and a half 00:37:57 - Design decision: why a separate tab 00:43:57 - Skills as the primary hackable surface 00:49:36 - Agent-native architecture principles 00:56:57 - The origin story of skills at Anthropic 01:03:00 - Our final rating

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Dan Shipper?

  If you're a non-technical person, you are used to a world where you send a prompt and then you get a response within a couple of minutes. And once you send a prompt or a chat, you can't do anything else with that AI. This is built for working with your AIs in an async way. This new Claude cowork app is a really good example of agentative architectures, which means at the bottom of the app, instead of having a software that works by deterministic rules, you have an agent and the agent is wired up to the UI of the app.

• 0:28Speaker 01

  I've been at Anthropic for a little bit, but this is the product that my team has built here. We sprinted at this for the last week and a half. And what we're trying to do-

• 0:38Dan Shipper?

  The last week and a half? That's it? Come on. We've got a new Anthropic drop. So Anthropic just dropped Claude cowork, which is basically Claude code for non-technical people. We got access to it early at every, and so I'm going to give you a quick run through of what it is and how it works. We will have a full write-up on every in a few hours, probably. We're just, we're kind of figuring out how to do these things. So I'm going to add Kiran. Kiran is here. Hello, Kiran. How you doing?

• 1:16Speaker 02

  Hey, what's up?

• 1:18Dan Shipper?

  So I'm just telling everybody, if you're, if you just got here, we are about to do a vibe check of Anthropic's new Claude cowork feature, which is basically Claude code, but for non-technical folks. I'm going to just demo it for you right now in here. And, okay, so let me just share my screen. All right, so this is what it looks like. It's Claude cowork. So you'll see we've got the chat on over here to the left. You've still got regular chat. You've got code here and then we've got cowork. So it's, it's three, the three Cs. It starts with let's knock something off your list. I love the copyrighting here. You can tell from-

• 1:59Dan Shipper?

  way they did this, that the it's it's really designed to do deeper tasks on your computer than maybe chat is. So you know, create a file or crunch data or make a prototype, send a message, organize files. It's got over here progress, it's got artifacts, context. We've been, we've been playing around with this for a couple of hours now. I think it's cool. I think it's cool. I think there's, there's a lot of like really interesting questions from the UX perspective of chat versus code versus work. And I think you can, you can really think of homework as being, it's like chat that has access to your computer and runs for a long time. Which is essentially Claude code, but just less intimidating.

• 2:43Dan Shipper?

  So a couple of things that we did that I think are kind of interesting to look at. Okay, so here's an example of it working. I asked it to go to the every.to website and find five competitive companies that do the kind of consulting that we do. And then analyze our positioning and you'll see it like just went and used my computer. It's, it's running in a, in a long loop. So this is, this is a really interesting one where you can do this with regular Claude, like Claude can do this. But the number of iterations that it's going through, this is many, many, many minutes of iterations. So it looks a lot more like, actually can you make this markdown?

• 3:24Dan Shipper?

  So it looked a lot more like Claude code, but it's friendly enough for anyone to, anyone to use. Well, we'll look at the, another thing I had to do, I have a, I have an, I have a dinner that I have to go to tomorrow night that I had to, I had to prepare some remarks for. And I asked it to basically like go, go to my Gmail and prepare remarks. It has a, it has a connector to Gmail and to Google Calendar, but the connector wasn't working. I think because this is like very beta and it was not out when I was testing this. And let's see, and I asked it to draft a response and it drafted a response. And I think the response is actually pretty good. So this actually sounds like me.

• 4:06Dan Shipper?

  This is kind of crazy here and you've got to look at this because this is, that's an implication for Cora.

• 4:12Dan Shipper?

  So basically, the setup was I have a dinner tomorrow that I have to do remarks for. And I asked, and the whole thing organized the dinner was asking me,

• 4:22Dan Shipper?

  can you tell me like what you're gonna, what you want to talk about? And so I just said, like, read, find the email and draft a response based on what you think I would say. And this is something that I could, I think I actually could send with minimal edits, which is, it's pretty cool. Are you seeing this, Kieran?

• 4:41Speaker 02

  Yes, looks good.

• 4:43Dan Shipper?

  I think one of the, the things that's good about this is it's gone through many, many steps to both identify what I would say and how I would say it. And has all the context, which is like, yeah, it's pretty cool.

• 4:54Speaker 02

  Yeah.

• 4:55Dan Shipper?

  Yeah, go for it.

• 4:56Speaker 02

  Yeah. So how is CoWork different than Chad? Like CoWork is more made to, you can, you can share your screen, but like it's more made to like go longer, like really work on something. So it's more focused on, on getting you some work done. And this is what we know in Claude Code already, like when you trigger Ultra Think or your trigger planning mode, things like that. So it is similar in certain ways, but it also, it will unlock a lot of things that you use as a developer in Claude Code. That now suddenly work very well for non-developer tasks.

• 5:31Dan Shipper?

  Yeah, I can sort of see this being a thing that

• 5:38Dan Shipper?

  just really accelerates, you know, our growth team or, you know, our, our people who are in our consulting business, who want to do some of these tasks and maybe are using Claude Code, but maybe it's like a little bit less intuitive. It should be released now. I think that they're, they're maybe holding it back, but the blog post is live. So you can take a look at the blog post. It's CoWork Research Preview. I'll throw it in the, in the chat.

• 6:04Dan Shipper?

  And yeah, so I think it'll be, it'll be out soon. Let me, I'll, I'll like, I can check with my Anthropic people. But okay, let me go back to this. So I also asked it to do a calendar audit. This looks like it's actually still running on this, which is crazy ass. This is like an hour ago. Go through the past month of my calendar and do an audit. Tell me how this reflects my priorities and whether it's aligned with my goals. Just browse on Chrome.

• 6:30Speaker 02

  Can you share your screen again, please?

• 6:32Dan Shipper?

  Oh, shoot. Yeah.

• 6:34Speaker 02

  Thanks.

• 6:36Speaker 02

  Yep.

• 6:38Dan Shipper?

  Tell me how, go through the past month of my calendar and do an audit. Tell me how this relates to my goals. And it just, you know, it's been browsing on my computer for like hours and hours. One thing that's, or not hours and hours, but like for about an hour. One thing that's different about this, which I think is really interesting is in Claude, when you start a chat and it's responding, you have to stop it in order to send a new message. But this, uh, just, I can just add to the queue. So this is a little bit more like the,

• 7:11Dan Shipper?

  this is more like the Claude code experience. So I think this is, this is one of those situations where

• 7:18Dan Shipper?

  it's built for you to send stuff as it's working and it's not like a, like one message, one response, one message, one response. So it's really more built for long, long tasks.

• 7:29Speaker 02

  Yeah. And it has the to do, uh, task, uh, also built in on the right, which is nice. So you can see where it is and what it's doing.

• 7:37Dan Shipper?

  Yeah, exactly. Um, another thing I did is I fed it a, a book and I, this is a book that I, it's called the outsider that I've been reading for a, a book that I'm writing. And, um, I just asked it to like, basically read the book, read the entire book and construct a taxonomy of all the main characters and ideas. And it looks like it did this. And this is something that you could also do with, um, with the, uh,

• 8:05Dan Shipper?

  with regular Claude, but it would be, it would just be less detailed. This is really interesting. I wonder.

• 8:11Speaker 02

  So yeah, so if you wanna trigger those longer running tasks, uh, like you can just say, make a plan, do this. So I assume if you just push it to do that more, it will just run for longer. So if you say, take an hour to read through every single email, it won't give up as easily as before and it will just keep going. So please try those things.

• 8:34Dan Shipper?

  Yeah, it has a, it has a, uh, it does have a plan mode. It said, I have not used the plan mode yet, but that's pretty cool. I also asked it to go through our post hog analytics and do some data gathering. So we published this guide. If you haven't seen this guide, it's like, I keep talking about this. Everyone and everybody is like making fun of me because I, I can't stop talking about agent, agent of architectures. We published this guide last week and we have these.

• 8:58Dan Shipper?

  We have these buttons, Read with Claude, Read with ChatGPT, and I was curious, okay, how many people click these buttons? And that's the kind of thing where I would go ask Andre, who runs our platform, and be like, can you go look this up? But instead, I just said, can you go into Post? I just went to cowork and I said, can you go into Posthog and just find all this stuff? And it said, okay, total chat with Claude button cooks 4,000. That's actually freaking crazy. Oh, my God.

• 9:27Speaker 02

  We should get money. We should referral.

• 9:30Dan Shipper?

  Referral fees, baby. What about chat with ChatGPT? What about

• 9:38Dan Shipper?

  Coffee for Agent?

• 9:40Speaker 02

  So this is cool because we were in a rush since we started this morning and we didn't have any MCP set up. What we just did was we connected Chrome and Dan is logged in on Chrome in Posthog. So just browse to the thing, got the things. So that's very handy, like MVP, just make sure you connect Chrome. That's a very good one to add already. You can also do that with the normal, but it's very good at browsing and figuring things out, especially now it doesn't stop as quickly, which is really, really handy. So anything you can do in a browser, you can now use cowork for to like use longer running tasks and kickoff things. And it can use multiple tabs as well.

• 10:25Speaker 02

  So you can have five tabs being controlled by Claude and running, which is great.

• 10:32Dan Shipper?

  Totally, totally. And it sounds like this is down for people. So come, come hang out on the street.

• 10:39Speaker 02

  Yeah, it's down for me as well, but for Dan is working, so.

• 10:43Dan Shipper?

  I'm the only one that's open for it. So we've got a monopoly here on Anthropic cowork content. So if you're here and you have stuff you want me to try, just let me know. I'm happy to, happy to throw it in the chat and, and make sure, all right, I have, I have something fun to do. Make sure that you use every, you read every, because every is the only subscription that you need to stay at the edge of AI. Every.to, we've got these five checks. When new models come out, we get them beforehand. We had this several hours ago. We knew it was coming since last week and we always have all the up to the minute stuff that you might need. We also have. A bundle of apps that we make. We have an app like the one that Kieran makes called Cora,

• 11:27Dan Shipper?

  which is an assistant, an email assistant. We've got one called Sparkle that helps you organize your files. We've got Spire, which helps you write. And we've also got Monologue, which is a speech to text app, which I will show you shortly. And let's actually go back to,

• 11:43Dan Shipper?

  uh, let's actually go back to the Claude demo real quick. So, and Karen, if you see anyone asking questions, just.

• 11:53Speaker 02

  Yeah, well, yeah, there's one good question from Hunter. He says, how good is it at research? Like, one of the things I love Claude's normal for is the deep research. Like, does that exist? So maybe we can see if it can do deep research on something.

• 12:09Dan Shipper?

  Yeah, let me know. Let me know if you have a research query you want me to try, but like, I can show you, you know, uh, actually, you know what? I'm going to share a different screen. Hold on. Um, plus, share screen. Okay. I'm figuring out my live stream setup. This is the first time that we've really done a, uh, live stream for a vibe check. Okay. So, um, now you should be able to see my screen again. So for research, like, okay, it depends on what you mean by research, right? Because this is a research query. Can you connect to Posthog and tell me for the agent native guide that we posted last week, how many people clicked the chat? Like, that is research. And it does give me actually like a really good, um, answer,

• 12:54Dan Shipper?

  which this is so interesting. Okay. Um, but like another form of research that we talked about is, okay, analyze my competitors. Um, this is specifically analyze our competitors for, um, the every consulting business. And I'm going to say open and proof. Proof is the agent native markdown editor that I built over the weekend. Can you believe I just said that? Um, and so this is a, this is a research document that, um, Claude coworker put together, which, you know, it's not like, it's not the meatiest thing I've ever seen. Let's see. I think this is not bad. Um.

• 13:36Dan Shipper?

  I'm not noticing like a super significant difference between this and like what a normal Claude would would pull out. But I can see the research itself is more um is much more extensive than normal Claude would do. And let me just actually throw this into normal.

• 13:56Speaker 02

  You can see also, so if you do deep research, the the research agents in chats, that's pretty extensive normally, but here you can see more. Yeah. So, yeah, I don't know, maybe that is also available in in that version. We're still figuring out what everything is that is available, but it's very close to what you can do in Claude code. So the kind of a fusion of chats and Claude codes is is cowork.

• 14:25Dan Shipper?

  Yeah. Yeah, this is very like you can see that they're calling these tasks as opposed to chats. So it's it's supposed to be, I think here's here's a good way to think about it. A good way to think about it is if you're a non-technical person, you are used to a world where you send a prompt and then you get a response within a couple of minutes. And once you send a prompt or a chat, you can't do anything else with that AI. You have to like move on to something else. This is built for working with your AIs in an async way. So everything is set up like the the idea of a task, the idea of having a queue. This is all set up so that you can say, go do something and then not think about it for a while and then come back.

• 15:06Dan Shipper?

  Which is very different from Claude where the normal Claude app, you're you're kind of you're you're trying to. You're trying to get an answer pretty quick. And I think that's the best mental shift. I think the real question that I have is, is this deserving of its own tab? For one, one reason it might be is there's a difference between like how you might treat one of these versus one of these. Like, these are more throwaway. These are probably like bigger chunks of work. But honestly, it's like kind of confusing. I would rather just.

• 15:38Dan Shipper?

  I think that they, I would rather just have it all in one tab and then have it. Do different levels of research and thinking and, and async based on the task and maybe based on.

• 15:52Dan Shipper?

  You know, a setting like saying like really fucking think about this. I don't know. What do you think here? How would you solve?

• 15:57Speaker 02

  Yeah, yeah, like for me, it's also confusing. It's like, oh, great. There's another tab and I have to like first think where to go, but I do get it. Because I, I've seen this transition as engineers, as an engineer, like we, we had the like copy paste into chat GPT. Obviously, and then like that evolved into cursor like more agentic. Which evolved to like, I don't look at code anymore. And, and I think. There will be a similar transition for people that do research or cowork. Like. Maybe now people are used to go into Chrome and like seeing what's going on, what's happening.

• 16:37Speaker 02

  And to, towards more of like, I'm just going to let it rip and do its thing. And then after it gets back, I'm going to review whatever the output is rather than understanding every single step all the way. And, and then you're like clearly already there. That's how you're thinking, but I do understand if you're not there, if you're more like. In the chat thing where it's like, oh, do this now. Why don't you look at this? Like if you have that conversation. It's maybe more chat and cowork is more you hand off a task to your agent and your agent comes back and you review the work. And you can follow up, but you can give extra directions. But I do understand to introduce a new tab because there. You need to shift your mind to do that. And obviously we're doing that, but.

• 17:22Speaker 02

  I understand lots of people in the world, especially that are not coders. Still have to make that transition where you just hand off something and then let it do stuff for thirty minutes or an hour and then. Come back and review that. So I do understand why they want to separate it. Even though it's all the same technology, because chat, code and cowork, it's all.

• 17:45Speaker 02

  The same model and it's very similar like harnessing around it. It is philosophically or how you use it may be a little bit different. So I guess that's why they did that.

• 17:57Dan Shipper?

  Yeah, it's interesting too, because we, you know, when we did this, um, when we did this original vibe check, when we got it a couple of hours ago, we had it, we had me and Karen and a couple of other people on the phone from internally at every. And we were demoing it together and their initial reaction was like, I don't know how this is different. And is this like even that, that useful compared to regular Claude or Claude code? Cause a lot of them are just using Claude code directly. And I think that that's like, that was a really interesting thing for me where you're not going to actually realize how useful this is until you get your hands on it. And there's probably going to be a learning curve on, on it where if you're a non-technical user who is used to, who's not used to the idea that you can just like hand off your work and then come back.

• 18:40Dan Shipper?

  It's probably going to take a while to like actually figure that out and, and get used to this as a UX paradigm. So maybe there's some benefit then to like having it be a separate tab. So people can like basically realize, oh yeah, this is, this is different and I should treat this differently. It's a real adjustment.

• 18:57Speaker 02

  Yeah.

• 18:58Dan Shipper?

  Yeah.

• 18:58Speaker 02

  Yeah. And that's, so i- if you want to learn about that adjustment, like we're writing about that for coding, but you could really apply whatever is happening to coding probably for cowork as well. Like how, how that shift happens, how, how that goes, how that goes. Uh, so yeah, like we, we, we thought about, we wrote about some of these things and I created a plugin around this idea. So what I will do in the coming days as well is like, see if the pattern or the paradigm of compound engineering, if that applies to cowork. Can I get that working in cowork? Because I would be very curious to, to expand that uh, and see, see if it works inside here as well.

• 19:43Dan Shipper?

  Anthony, uh, I see that you're from Anthropic. Do you want to come on the stream? Um, I'm going to send you a link. Uh, I would love to hear what you have to say about this and anything that we should try or anything that's missing.

• 19:57Dan Shipper?

  Here, give me a sec. Let's see. All right. I sent you a stream. Like, if you want to come on, feel free. If you if you're, you know, if you're not feeling it, that's also totally fine.

• 20:08Speaker 02

  Yeah, he says it looks or is closer to Claude code than chat. And it feels like that because all the tools like the ask user question tool, stuff like that have a UI, which is nice. So you can ask it to say, hey, can you interview me? Ask me a few questions. And there's like a nice UI with multiple choice and stuff like that. So. Yeah, it's really cool that you like.

• 20:32Dan Shipper?

  It is really cool.

• 20:36Dan Shipper?

  Okay, so let's keep. Let's keep looking at this. It's it's still working. One of the things I noticed is when it was erroring. It had it gave an error from Claude code, like the internal error message is Claude code. So it's it seems like it really is just like a UI wrapper on Claude code. Rather than a different agent harness, or maybe like a Claude SDK. Anthony, if if we're wrong about that, or anybody else from Anthropic who's who's listening, I'd be very curious for your. For your thumbs up or thumbs down on that. But that's like interesting design choice, not to to use just like actual Claude code. I assume that's because it's already in the app. So it's like pretty easy. You don't need to use the SDK, but it's a really interesting thing to see. One thing to. One thing that I want to show people in case you have not been.

• 21:23Dan Shipper?

  Watching everything that we're doing at every. And if you haven't been, I don't know why you would not. I don't know. I don't know what's wrong with you. But. One thing that's really cool that we're that we're thinking a lot about is agent native architectures. And an agent native architecture, this is this app is a really good example. This this new this new Claude cowork app is a really good example of agent native architectures. Where we think about agent native architectures as sort of like Claude code in a trench coat. Which means at the bottom of the app, instead of having software, you have like software that works by deterministic rules. You have an agent and the agent is wired up to the UI of the app. And so when you click a button, it is actually just going to the agent with a prompt.

• 22:05Dan Shipper?

  And I think this is a this is a new this is a new way of building applications that we've been working on internally at every. If you're interested in that, I highly recommend that you look at this guide. We'll, we'll, we'll put a link in the chat. But this guide goes through how to use or how to build agent into architectures. It's like, it's pretty cool. And it's like, it makes you build stuff like I built this. This is a markdown editor that I built with.

• 22:31Dan Shipper?

  This is a markdown editor that I built with Claude code over the weekend. So in the last couple of days, I built this whole thing. It helps me track, we, we use it internally. It's called proof. It helps me track.

• 22:43Dan Shipper?

  When I get a plan from Claude, it helps me track. Okay, what things have I approved? So you can see I'm, I'm approving things here. So I can track what have I approved? What have I looked at? What's, what's done, what's not done?

• 22:55Dan Shipper?

  And yeah, there's a lot of, there's a lot of cool stuff here. I'm going to stop blabbing about agent native and go back to Claude. Karen, anything you want to add here?

• 23:03Speaker 02

  Really what I'm, I'm curious for is like, as a power user, can I load my own plugins and stuff like that? And there were questions about can we, can you do custom MCPs? I think all the MCPs you can do, and also this app has access to your machine. So can use Apple script to load things on your machine, which is really cool.

• 23:24Speaker 02

  Yeah. And, uh, yeah, I'm, I'm really curious for how, where, where does it go? Like clearly it's trying to get called codes to the normal user. But I think as a power user, I would use this as well because in the morning I start up Claude code to make a day be planning. Like, well, what am I going to work on for the day? But it feels, it's probably nicer to do in an app. And also if this translates to mobile, this is super powerful because you can do more powerful work on your phone. That's not necessarily code related. So yeah, we, we need to experiment, but there are lots of interesting thing. I'm, I'm very curious as a power user, even though it is the same technology.

• 24:08Speaker 02

  Maybe it's a new way to use it, which is interesting.

• 24:11Dan Shipper?

  Yeah. So this is my calendar audit that I asked it to do. So I asked it to automate my calendar and compare it to my goals.

• 24:18Dan Shipper?

  I reviewed your entire month of calendar activity. So this is something that like regular Claude probably would not do. I have a lot of meetings and stand ups. So that's an interesting one. I actually don't go to a lot of these, so that's probably not fair. And I also have a lot of one on ones. I have a lot of podcasts scheduled, which I'm starting to get rid of. So it did, it actually did a pretty good job.

• 24:39Dan Shipper?

  Content media, health, non-negotiable.

• 24:43Dan Shipper?

  Many days have 10 to 15 plus scheduled events. That sounds probably right.

• 24:50Dan Shipper?

  This is interesting. It said, what are your top priorities? I would expect Claude to know this. I wonder if it has access to all my memories yet? Because Claude definitely knows like what my priorities are. But anyway, this is pretty cool. I like this.

• 25:05Dan Shipper?

  See if it did. Oh, we got, we did. We got the taxonomy. It's, it feels like it's, it's like slowly lazy loading all the conversation history. So it doesn't. It's like, this isn't happening. This is already, this is already done. It just didn't load it. I feel like a lot of the affordances here. They haven't built the statuses yet. So it's easy to see like, you know, in, in the code tab, for example, like I could pretty easily see. Usually what I've merged and what's waiting for me and stuff, but this is like just. An unorganized list, I guess, by recency. Or it's not, there's no visual differentiation, which is interesting. Hello, Kate. Our editor in chief Kate is just off camera.

• 25:48Dan Shipper?

  Kate, things are going well. We have, we've got 2,300 people here. So looking, looking at Claude code together. Yep.

• 25:58Dan Shipper?

  Oh, you want, okay, let me just. Yeah, maybe I should try that. If anyone from Anthropic wants to come on the stream and talk to us, I can see you commenting in the chat. I'll send you a link. To StreamYard, just like, say, yes, I would like to come on the stream and chat. We're very, very friendly and I think a lot of people would love to hear from you if you're already here. And I will update the app. This is, yeah, this is actually, this is important. I have a beta build right now. So this is something that. Was not, I didn't, I haven't updated my app and I'm a little afraid to do it on a live stream. Kieran, do you have it in your app? I'm curious.

• 26:33Speaker 02

  I, I'm trying to get it working, but it was down for a while here, but it looks like some, it's, it's wake up again.

• 26:42Dan Shipper?

  Cool. Anybody have other questions or things they want me to try? I'm taking requests. So ask for, ask any interesting queries. Most interesting query, we'll put in every, when we do our vibe check.

• 26:57Dan Shipper?

  I wonder if I could use this to code. I'm kind of like, let's see. Oh, this, it did our, it did our audit of.

• 27:06Dan Shipper?

  Every, the every agent native guide.

• 27:09Speaker 02

  Can you see if it has artifacts as well?

• 27:12Dan Shipper?

  It does.

• 27:13Speaker 02

  Okay.

• 27:13Dan Shipper?

  It does have, well, it didn't do this one in an artifact, but we do have artifacts. In another place, let me just find it.

• 27:24Speaker 02

  I do the fact that that context is clearly spelled out on the right.

• 27:29Dan Shipper?

  Yeah. It is, that is nice. See, context is here. I saw the artifacts tab somewhere. Yeah, it's just like a friendlier, it's like a friendlier version of Claude code to me.

• 27:43Speaker 02

  Yeah, mine is working as well.

• 27:45Dan Shipper?

  Uh, can you find my every proof repo in Cascade Projects? Basically, I want you to do a summary of the new feature, the, the provenance, the new feature provenance tracking that I'm, I've been building in every proof and write it up in a nice like HTML file artifact that I can send to Kieran to, to explain to him.

• 28:12Dan Shipper?

  How the new provenance is going to work. I think it's, this is a combination of something that is kind of, it's Dev Work related, but it's probably not something I would ask Claude Code to do.

• 28:24Dan Shipper?

  I don't have access to your, your Mac's file system in this Linux VM environment. Interesting.

• 28:32Dan Shipper?

  So that's interesting because it definitely does have ask access. Let's see. One of the things that gets confusing about this, I guess, is when it's running on your computer versus when it's not. Like, I think it's, it's sort of unintuitive to the average person, probably, that when you're using it in chat, it is all online. And when you're using it in here, it's actually on your own computer. I'm very curious, like.

• 29:00Dan Shipper?

  How they thought about making that clear from a UX perspective? And if anyone is from Anthropic on this stream, why does it think that it can't access my Mac's file system? Oh, maybe I have to add that folder specifically. Oh, yeah, that's what it is. That's so interesting. I just want, I just wanted to YOLO, give it YOLO access my file system, to be honest with you.

• 29:25Dan Shipper?

  Look at all these projects, by the way, this is how you know, like, I have a problem. Like, these are all vibe-coded projects, basically.

• 29:33Dan Shipper?

  Let's see, every proof. You know what? It's this one. Okay, always allow. All right. And now I can, the nice thing about monologue, so monologue is one of our apps at every, is I can just, there's a shortcut for this, I can just click it and then repaste.

• 29:52Dan Shipper?

  And, cool. But yeah, what I really want, I just wanted to access my whole computer. It has that, that's interesting, it has that file cleaning prompt, I wonder how that works if it can't access.

• 30:06Speaker 02

  Yeah, I'm testing it now as well, I'm trying to see if I can use the

• 30:15Speaker 02

  skills I already have.

• 30:17Dan Shipper?

  Oh, interesting. So I said organize and tie it up my downloads, and then it seems like it figured out, this is so agent-native, it figured out how to select, it's as if I selected that folder in the

• 30:30Dan Shipper?

  in the UI, just because I specifically asked for it. That's cool, I think that's a really smart affordance, it's just like, I wish it had gotten activated here, too. Like, ideally, it, it knows that I'm trying to access a folder in Cascade Projects, and it is as if I clicked this.

• 30:52Dan Shipper?

  Are you sure?

• 30:55Dan Shipper?

  It's the natural.

• 30:59Dan Shipper?

  See if this is actually working.

• 31:03Dan Shipper?

  Felix, are you joining? Amazing.

• 31:08Dan Shipper?

  Let me just find you on the X app, X the everything app. And.

• 31:17Speaker 02

  Then if you can share my screen and I can show.

• 31:20Dan Shipper?

  I will do that. Yeah, let me share.

• 31:22Speaker 02

  While you do that.

• 31:23Dan Shipper?

  Actually, this is helpful. All right. Remove. There you go. You're off the race.

• 31:28Speaker 02

  Okay, so I was trying this out. Help me generate a VST plugin, ask me user questions. And I found a little bit.

• 31:39Speaker 02

  So I found some things. So basically, the ask user question I love because it's this UI. It like runs you through and you can hit 12345, which is very nice. The weird thing is I didn't answer it and it started automatically skipping this.

• 31:59Speaker 02

  Maybe it's fixed now, but in the other one, it started automatically. Oh, yeah, here skipping. There we go. See, so if your mouse is not on here, it just thinks, oh, this user is not here. So we're going to skip this altogether, which is very confusing. But also I love it because I'm a dangerously skip permissions person and I understand. But it's weird because if you're here, scroll all the way up, it will skip to the next. So just a little bit strange here. But the cool part is here, I can say three and it will go and continue. So there's like, I like that it keeps, keeps going and it's set to like, keep going and finish.

• 32:46Speaker 02

  The skip UI here is a little bit weird, but let's say multi type delay. And you can see it's working with my skill or skills, skills choose.

• 33:00Speaker 02

  Oh yeah, it is mine. Happy Sharp Hopper is just the local place where this is happening. Say this. So this is an interface that never existed before, which is cool.

• 33:14Speaker 02

  Yeah, there is a, it's, it's a little bit weird because it's inline here, but in reality you're answering. So I'm sure, let's see, sending requests. Yeah, so this skipping part is very confusing. I don't know why it's skipping now. But I do like, like, I would rather say, maybe when I start the session, what kind of session it is? Like if, if it's like YOLO, let's go session, or where it like pings me and like very clearly in the cowork tab says like, hey, you need to answer a question here. I need your attention. Because like there's something to be said to both and now it's kind of somewhere in the middle where it's not super clear.

• 33:59Speaker 02

  So I'd rather have it say, yell at me and say, yo, I need your, your, uh, I need your input on something. And I don't want to give input on like creating or using things, but like if it, if it will change the direction of uh, what this will be with the ask user question broadly, that, that is handy to have. So far, this.

• 34:22Dan Shipper?

  Interesting. I, I have a, since we have, uh, it seems like there are some Anthropic people on here. I do have a, a feeling about, um, ask user question. I'm, I'm curious what you think here. And I just, there's a limit to how many characters it displays. And then it just goes over and hides the rest of my answer and that just annoys the shit out of me. Do you know what I'm talking about?

• 34:43Speaker 02

  Yeah, I, I know. Yeah. It, it needs to be a little bit more flexible also. Like, I want like, why not 20 options? Like, why is five the maximum or something like, like sometimes you just have 20 that you need to like, I get it. But also, yeah, uh, stop questions, go builds. Uh, so that is nice. Just make it now. Okay. So it did not really, like it's still doing stuff there, but here like it's, I mean, it's a little bit wonky still, but I love, I love the ask user question flow. It's very useful.

• 35:22Speaker 02

  Okay, so it does it here and you see the to do right, which is here on the right.

• 35:26Dan Shipper?

  Wait, I was distracted. What plugin are you building here? Can you, can you back me up? I think about a thousand.

• 35:32Speaker 02

  Yeah. Okay, so I, I will, I have a skill called the juice skill, which knows everything about, uh, about VST development and I'm creating a, I asked you, can you help me brainstorm a VST plugin? And we're doing a delay. Oh, like it's, it's an audio effect. So digital sound processing that you use in your

• 35:54Dan Shipper?

  I see.

• 35:54Speaker 02

  music making.

• 35:55Dan Shipper?

  Yeah, yeah.

• 35:56Speaker 02

  And I'm making a, a delay now and it's building the delay and like normally, normally the building of the delay Claude Code is great for, but sometimes you want to brainstorm. You don't want to build. And that's why I like cowork because I just want to brainstorm a little bit. And the cool part is it has these skills.

• 36:15Dan Shipper?

  I see.

• 36:16Speaker 02

  So, yeah.

• 36:17Dan Shipper?

  Uh, I want to interrupt you really quick here and because we have

• 36:20Speaker 02

  Yes, hold on.

• 36:21Dan Shipper?

  A, uh, member of the team from Anthropic here on the stream. Felix, welcome.

• 36:26Speaker 01

  Hi friends.

• 36:27Speaker 02

  How are you?

• 36:27Speaker 01

  Hey.

• 36:28Dan Shipper?

  And how are you? Uh, we never remember. Tell me about you. What do you like? What do you do at Anthropic? Like, how are you involved in this?

• 36:35Speaker 01

  How am I involved in this? Um, I've been at Anthropic for a little bit, but, uh, this is the product that my team has built here. We sprinted at this for the last week and a half. Um, what we're trying

• 36:46Dan Shipper?

  Last week and a half?

• 36:48Speaker 02

  That's it? Come on.

• 36:50Speaker 01

  Like, to be clear, to be clear, I think many people have had the idea that something like Cloud Code for non-coding work would be helpful and useful to people. And fundamentally, what we want to do here is we would do want to help people out with their work. Like whether that's a personal thing or a corporate thing. And we've had a different number of prototypes, in particular before Christmas. But I think over the holidays, one thing we have seen, I'm sure many people have seen this, is that an increasing number of people is using Cloud Code for almost anything. Just like we are, right? We're sort of like automating our entire lives with Cloud Code. So we were thinking, what is a small, early thing that we can try out and ship to people? And iterate with them together to really figure out what is the right, what is the right user experience? What is the right thing we need to build?

• 37:35Speaker 01

  And this is it. This is the the sort of like research preview, very early alpha. A lot of like, a lot of like rough edges, as you've already seen, right? There's a lot of things about it that I think we're going to improve very quickly.

• 37:50Speaker 01

  But this is our attempt to like build in the open, work together with people out there.

• 37:54Dan Shipper?

  I love it. Tell us about like some of the design decisions you made, like an an early one, for example, is there's a third tab instead of maybe adding a cowork mode into the chat tab. Like, how did you think about? And what was the process to to to come to the the design that you have currently for how the product works?

• 38:13Speaker 01

  That's a great question. So I think, I think one belief I have is that the current user interface that you see across agentic applications, not just at Anthropic, but across the industry, is probably going to change pretty dramatically in about a year or two. Right now, we have these hyper-specialized individual input fields, and we have a lot of custom scaffolding around the specific tasks that you're going to do. But as we see the intelligence of models improve, and as we also like maybe holistically as an industry figure out a little bit of the generalization problem, I expect that we're actually going to see a smaller number of interfaces for a wider range of use cases. For now, what we're doing is, the reason we broke it out is because we want to be pretty transparent that this separate thing is a construction site.

• 38:58Speaker 01

  Right? That we're sort of letting you into our kitchen. We want to like work together with you. We want to ship almost every single day some new features, some bug fixes, try out some things. So this separate tab is fairly experimental. It's, you could say on the frontier or the bleeding edge, but it's just a little bit, a little bit less polished and a little faster pace. And that's one of the main reasons for in a separate tab. There are some technical reasons too. I could tell you, like, one of them is that currently this is running on your computers, so your chats are local. They're not shared with other devices. We're being being a little bit more aggressive in how many agentic abilities we give Claude.

• 39:34Speaker 01

  Those are the main reasons.

• 39:35Dan Shipper?

  How did you think about, because I feel like that's such a huge UX hurdle to get over. How did you think about? Letting people know, hey, this is actually running on your computer versus chat, which isn't the same application as not. Yeah, that seems so hard.

• 39:50Speaker 01

  Yeah, I think the dream that I have, and I'm sure many people have this dream, the dream that I have is that it doesn't really matter, right? Like where your code runs, it should be technical implementation detail. And it should matter to people as much as when you visit thenewyorktimes.com, like, is it using web sockets or not? And it's like, who cares? Yeah, I think for us right now, it's an opportunity to move a little bit faster. And to ship a little bit quicker and also like work a little bit closer with the people for whom we're building this. I have this strong belief that it's very hard to figure out a great product in isolation. I guess all right, you sort of like go up into a cave and you work on something for a year and eventually comes out. I think it's really hard to build a good product that way.

• 40:30Speaker 01

  And I often like to remind people that like even the first iPhone was missing a bunch of things that we sort of consider to be table stakes.

• 40:40Speaker 01

  So yeah, I think it's a pretty big hurdle, but we're okay with that for now because we do want people who are signing up for this, right, to like sign up for it fairly intentionally.

• 40:52Dan Shipper?

  Yeah, I think that's a really interesting pattern is like, let's ship really fast and we'll ship it as a new thing in the app that maybe fewer people will click on. So that we can get it out in the open and start iterating together rather than like try to make it perfect. Especially in this new world where it says, you said you were working on this for a week and a half, this version for a week and a half, which is kind of insane.

• 41:14Dan Shipper?

  Kieran, do you have any questions?

• 41:16Speaker 02

  Yeah, I'm curious.

• 41:20Speaker 02

  Like clearly this is the version that's out now, but like, what is the version like in your's heads? Like, what are the like, where, where, where do you want to go next? Or like, what are the things you're dreaming about you use the word dream? Like what are those things where you wanna wanna go? What is, because I'm sure everyone on the team had like wild ideas and then they were like, no, we need to ship Monday. So let's just like, what are, if you can share any of those, we'd love to hear those.

• 41:50Speaker 01

  I I love that question so much because I think I actually have the same question for the two of you, right? Which is where do you want this to go? What do you wanna do? Um, I've already heard you say you kind of wanna give it to an access to an entire computer. Um, the multiple choice thing where like, actually, can we like shift around a little bit and how we wanna wanna do this? I think right now, I am much more in a mode of, okay, let's see what people think and then try out a billion things. Some of them will probably be the wrong things, some of them will be the right thing. But I think it's much more interesting to me what people wanna do with this, rather than like what's my own personal dream or vision.

• 42:23Speaker 02

  That makes sense.

• 42:24Speaker 01

  In the things that I've sort of built in the past, this was always, this was always the thing that happened, right? You have like an idea of how people will use the thing that you build. They actually find a use for it in all these other ways. And then you lean into that. So I'm really hoping that. I'm really hoping that we can learn a lot about what do people want, what do people not want, what do they like, what do they dislike? I'm sure people will like dislike a few things about this and then we like adjust and like iterate on it.

• 42:49Dan Shipper?

  That's the really cool thing about a Go4K.

• 42:52Speaker 02

  Yeah, so Boris is very good in building Claude Code in a way. That people can figure out what they want. Like, is there a way, like, do you use that strategy in a, in a way as well, where we, where you give some building blocks or things? For us, like, for example, can I include my own plugins or skills or like, i- is there a way for people? To experiment inside cowork as well in the like, maybe the non, non coding way, or is it really like, this is the product, it's? That's what it is, like, how, because there's a cool balance between like how Claude Code works and people that use it.

• 43:32Speaker 02

  Because it's super hackable, like, is there a similar philosophy in cowork as well for non coders?

• 43:38Speaker 01

  Yeah, like very composable, right? Like, the, the, the first thing you said about like Boris being very good at steering Claude Code in this direction of shipping early. And then iterating on it and seeing how people use it. Um, it's really funny that you mentioned that because I think one of the reasons we've shipped today, maybe shipped a little earlier. Was because Boris pushed me and was like, hey, you should probably show this to people, see, see what they.

• 44:00Speaker 01

  And on the composable piece, I think the the thing that I found most impressive in my own work over the last couple of weeks and maybe sort of the last two months is that I'm really leaning into skills. So instead of like previously writing MCP tools or like this, like very specific harness that is like very tailored towards just Claude, I instead just write skills. Sometimes I still write a binary and then I describe in a skill how to do something, right? I'm like, that's a good example. Um, I'm working on like a marathon training plan for myself and I wrote a little binary that fetches all my athletic activities from various pages. But then I just write in markdown in a skill file, hey Claude, if you wanna, if you wanna make a training plan, like please follow the following guidelines.

• 44:43Speaker 01

  Um, we do automatically load any skill you have installed in Claude AI into CoWork. And I think that's probably going to be increasingly, especially as well as it's water and especially with Opus four, five, it is so good at following skills. So skills is probably the primary hackable surface that I'm exploiting right now.

• 45:02Dan Shipper?

  That's great. Um, one thing you said earlier in the conversation is you're, you think that there's going to be fewer like UI services. Does that, does that mean that like over time there'll be fewer UI, UI services? Does that mean, because there's a lot of debate over the last couple of years about is chat the final form factor for AI? And everyone was like, no, we need more UI. Are you, is that, are you putting your stake in the ground as um, natural language actually is here to stay? And we're going to have fewer UI services where you just talk to an agent, maybe an agent orchestrator that goes and talks to a bunch of other agents. And um, that's the kind of form factor you're, you're pushing towards. So it looks a little bit like how Claude Code does today.

• 45:41Speaker 01

  Yeah, I think this is still very heavily debated and there's certainly no anthropic viewpoint. I, I'm not even sure that there's a viewpoint that my fairly small team would like holistically agree with, right? I think people have very different visions about how will people interact with AI and models in the future. If you ask me very personally, I think I believe two things. One is that the chat input and its various forms, not just for models, but in general, right? Like the idea of this text box and you put into the text box where you want. Um. If you generalize it enough to say even google.com or the address bar in Chrome is like a I want something input box. I think that is going to stick around for much longer than we all think. That's first thing I think. I think this

• 46:25Speaker 01

  we will continue to have something that looks like a search I want something box. The second question is like, how many separate boxes do you have, right? Like, do you have one box for code? Do you have another box for maybe like a personal attainment? Do you have another box for healthcare related concerns? I'm not sure we're gonna have too many boxes of those. And there too, maybe I would go back to Google. Um. I think I sort of remember the early two thousands where you did different search boxes for every single Google subproduct. And increasingly, you just type what you wanted to your Chrome search bar.

• 46:57Dan Shipper?

  Yeah.

• 46:57Speaker 01

  We don't, you no longer actually like go to subpage of something like I'm in the mode right now of looking specifically for shopping things. So I go to Google shopping. Um.

• 47:06Dan Shipper?

  Yeah.

• 47:07Speaker 01

  I would be surprised if we don't see a similar generalization that is smarter about figuring out what you want to do in the future. We might still have different interfaces where it's sort of like splits out, right? And on the same

• 47:17Dan Shipper?

  Yeah.

• 47:18Speaker 01

  then that you're trying to do X, therefore I'm going to show you UI for X, but the entrance point.

• 47:24Dan Shipper?

  I think the, yeah. The interesting counterpoint to that is something like Microsoft Excel, which I think it also has some similarities to the way that um um, you know, just generally AI works is it's this general purpose product. It's super simple to get started. You can make things real like endlessly complex with Excel. And then Excel sort of spawned this, the B two B SaaS wave, like you probably don't get B two B SaaS without Excel. So there's, I think there's also the other argument that you have these sort of general really general tools and then people find power workflows within them that then get split out.

• 47:59Speaker 01

  Yeah, yeah, I think I think Excel is like such a beautiful example of so many things because it's like for many developers, something that sort of exists a little bit on the periphery. Right? Um, I've often heard the analogies between like how many daily daily active users Excel has versus like how many developers even exist on the planet. Um, it's an interesting number. And I think, I think the thing that I find interesting about Excel and the, you know, the commitment it has from its power users is that those power users are not too interested in marginal productivity gains or marginal UI or UX gains over deep familiarity with the product.

• 48:40Speaker 01

  And I think that's interesting. Um, I think there's a lesson there in some shape or form. And I think I've I've actually seen that across like braids of the surfaces where you as a developer, sometimes look at someone's workflow and you say, oh, I can make this workflow like slightly better for you. If I make you a specific use case tool over here on the side, and then people sort of fail to adopt that thing. Because they're actually more comfortable doing specific things within their product. Um, as an example, I think that's a lesson that I have learned. I was previously at Slack for many years. And there's a lesson that I've learned there over and over again, is that you can make these separate services that you think might serve people's use cases much better, but they will continue to just do it in chat.

• 49:20Dan Shipper?

  Hmm. That's a really, really good lesson. I love that. Um, speaking of, speaking of that, I think there's, there's, today is for the non-developers, but I feel like there's a lot of developers who are watching this right now. And you're someone who's, if you, if you, you built this, so like you're, you're deep into how to build like agentated applications. And this is something that we've been thinking about and talking about a lot at every, um, we just published a guide called Agent Native Architectures. And we've been thinking about like, what are the core principles of agent native apps? And I'm really curious if these resonate with you, if you think they're wrong, or if there are things that you would add that are part of how you guys at Anthropic think about building agents. So.

• 50:03Dan Shipper?

  An example is parity. So one of the things that we think about when we build agents internally at Every is whatever the user can do through the UI, the agent should be able to do.

• 50:13Dan Shipper?

  And I see that a little bit. That's basically how Claude Code works, but I see that a little bit in what you built with CoWork, where, for example, if you didn't pick the file picker, it'll automatically determine that you are asking it to pick a particular folder and it will do that for you without you having to touch the UI. So that would be an example of parity. Another one is granularity, which is basically tools should be mostly at a lower level than features and the feature should live in the prompt or the skill. So that you can combine tools in new ways that you didn't predict previously.

• 50:50Dan Shipper?

  And then that allows for the third one, which is composability, which is you can combine, you can combine those in new ways and you get the fourth one, which is emergent capabilities. So people are just doing it for stuff that you didn't expect. And you met, you see the latent demand and then you like build for that. And this is essentially, I think, like a lot of my summary of how Claude Code works. I'm curious of like how this sounds to you and if you think that we're missing anything or are there any things that you've learned from doing this in production at a huge scale? That could make it, make people better at building these kinds of applications.

• 51:26Speaker 01

  I think this really resonates with me, right? And like, I think one thing that's hidden in emerging capabilities is the inability, I think, especially individuals and silo teams have to predict how an agent actually ends up being super useful if you give it fairly primitive tools. I think pushing down tools into like a general space is very powerful. Like the more composable they become, the more generalizable, the more generalizable the tool is, the more you will benefit from improvements on model intelligence. And I think for, for. Many developers that I've been talking to in the past, it seems like the rate at which model intelligence and models' ability to call tools effectively improves is actually much faster

• 52:09Speaker 01

  than your ability to like maybe churn out additional tools and like educate users on them. And I think if you if you sort of take a step back and you think of how can I build a very generalizable tool? You have a much better chance to build something that can adapt to new use cases. So I think that resonates with me quite a bit.

• 52:26Dan Shipper?

  Mm hmm.

• 52:26Speaker 01

  Really does.

• 52:27Dan Shipper?

  What about the like trade offs? Like I've been talking to Kieran about the trade offs in tools. Kieran, do you want to talk about the what you're kind of what you noticed in Cora and what you're thinking about?

• 52:37Speaker 02

  Yeah, so I I think putting things in a prompt

• 52:43Speaker 02

  is great and then having the tools, but there's like we need to now suddenly create tools that then read skills or something like that. So like we have to invent this meta layer like skills is like just in time prompt injection, but like we we need to create that thing. And now everyone that's building stuff unless you use Claude code or the Claude SDK, it's all built. But like it's this thing like now there's like this struggle of like, oh, but like tools are that you can describe stuff in the tool or you create a tool that then wraps around it and then calls something else. So there's like this eh this friction there and

• 53:23Speaker 02

  like it is great to make things composable, like if originally you create, for example, like five tool calls, one a search email, like read email, this and this and this. But you can also say, no, we do just do like an execute tool call and we create skills that can do those things or an MCP or some abstraction there. So um there's like this change happening and obviously this is like the Claude code is like and the Claude SDK is a very good

• 53:53Speaker 02

  push for that. But I feel friction there. I'm sure you felt that friction too. So maybe you have some best practices for people that are stuck in the old fashioned AI world and need to go to the more Asian native things that you learned or that you've noticed because you've implemented on top of, I I assume Claude SDK maybe or some variant like there is eh eh so you use that and you implement things on top. So I'm very curious if you learned anything there.

• 54:24Speaker 01

  I'm not sure that I have any like wisdom from the mountain that is going to be more valuable than yours. But I think, I think what you're saying, I think what you're saying that resonates with me is that you sort of need to make a call, right? Like which part of the outputs do you want to be non deterministic? And where are you comfortable, where you're comfortable relying on model intelligence? And every single time you do rely on model intelligence, if you take a cheaper model or like a dumber model, then those parts also go down in quality. And I, I like to break up my workflows into like the non deterministic and the repeatable parts. I think the more repeatable something is, and the more, more easily I can say this will never change. And if you get smarter, I'm not going to benefit here at all.

• 55:08Speaker 01

  Um, I think that's a place where, where it might make sense to like write a tool. And in a sense, we're already doing that, right? Like we're not implementing. You, you could give Claude a very generalizable write assembly code tool. Right? You could be like, just call GCC and figure out whatever you want. But, but we don't, right? We give it.

• 55:28Speaker 02

  Yes.

• 55:31Speaker 01

  Right? Because.

• 55:31Speaker 02

  That's dense ideal.

• 55:33Dan Shipper?

  That's the most granular you can get. Yeah.

• 55:38Speaker 01

  But I will say, I will say that I think when I talk to developers out there, depending on, depending on how sci fi you are, I think even that assumption is a little bit, I wouldn't bet too much money on it. That assumption is certainly under attack, like the idea of like, should you give Claude any tool at all? Or should it just be like a Claude, here's memory, start writing ones and zeros, go wild. Um, it's, it's, it's an interesting area. It's like hard for me to know right now.

• 56:06Speaker 02

  No one knows, but, but you, you learn stuff. You created skills for exactly this reason. Because you needed more than just a slash command and a sub agent that you're like, we, there, we, yeah. Like we need the Claude MD to be better, but like it's, it like, I guess that's why skills like were created and clearly that's working well. I resonate with you saying like, skills are amazing. This is also like, I'm creating skills every day and I love them. So, so clearly there is something there, but when, when do you like, when, when do you not have it be a skill? Or like I, I, it's, it's, it's very interesting to me.

• 56:47Speaker 01

  You know, I think this is, this is such a fun conversation. You, who, someone you should actually talk to at some point is Barry. Because Barry is the one who is

• 56:58Speaker 01

  at least inside the company, sort of like our skills person is the person who essentially came up with skills. And for us fundamentally skills for a little bit of a byproduct of the same tension that you're describing. So what we want to do is we wanted to make a very easy way for people inside the company to get dashboards. Right? And we have a, we use one of the popular data providers where we keep a lot of our data. And we were trying to figure out, okay, do we build really specific tools that fetch that data and then compress it down into like a specific format? And the first couple of dashboards cloud in the building looked a little, you know, this was before four point five, the dashboards were not ideal. Every third or fourth dashboard it generated was like a little leg cluster.

• 57:41Speaker 01

  And so we, we did think about, okay, do we like super parametize it and basically build like a fixed dashboard that you cloud then only plugs new data into. And but in that process, while building that, we sort of discovered, hey, if you just tell Claude how to effectively query this data source, that it can use SQL and that it please follows the following design guidelines for making dashboards. Suddenly you get something very, very good and you get it very good every single time. And then you also give people, and this is the emerging capabilities part. Then you also give people the opportunity to say, hey Claude, I understand that you're following these principles for dashboards, but I also want, I don't know, different chart type, or I want to combine it with other data. And that's then where things really open up, right?

• 58:25Dan Shipper?

  Hmm. That is really interesting. I feel like the one, one way to talk about why you might want to skill instead of just having it have GCC and just everything is just in time is it's like about sharing something repeatable with other people that you can talk about. Um, and there is something actually about not, not everything should be just in time because you want to do the same thing over time with a group of people. Um, and that's, that's kind of a skill, I guess.

• 58:51Speaker 01

  Yeah, yeah, that's sort of how we operate too as humans, right? Like when I join a company, someone tells me how to book a flight like.

• 58:57Dan Shipper?

  Yeah, yeah, yeah, yeah.

• 58:59Speaker 01

  Tool, how do you get a room? I think a lot of us sort of operate even as humans on a long list of markdown files. That's definitely.

• 59:07Dan Shipper?

  Felix, I want to give you an option. You've been very generous with your time. I want to give you an option to to hop off if you want. We would love to keep chatting. We have endless questions, but I'm sure you have a lot, a lot going on. Do you need to do you need to go or do you want to do you want to keep chatting?

• 59:21Speaker 01

  I think this is a good time for me to bounce, but I'm not going to go before both of you give me like one thing you would like us to change.

• 59:28Dan Shipper?

  I mean, my my easy one is just Yolo access to my whole computer.

• 59:31Speaker 01

  Okay, okay.

• 59:33Dan Shipper?

  And and make it easier for me to know whether it's working on my computer or working in the cloud on a chat. And make it easy for me to use it on mobile.

• 59:43Speaker 01

  Okay.

• 59:45Speaker 02

  Yeah, plus one on the mobile, but my favorite thing would be the ability to add my plugins. So just my I have a marketplace with plugins. I just want to hook it up to GitHub and.

• 59:56Speaker 01

  Fair enough. Yeah, yeah.

• 59:58Speaker 02

  Like, because now I'm like adding things in the app and then copying it there and like it's like I like it. Probably I can just copy it somewhere, but like just native support for a marketplace and then adding it and syncing it will be absolutely great.

• 1:00:13Speaker 01

  Thank you. I appreciate both of those quite a bit. We're going to take those back, going to tell the team about it. And for everyone else on the chat, like find us on the internet, send us what you think. We're quite interested in hearing from people and adjusting our roadmap.

• 1:00:26Dan Shipper?

  Thank you so much, Felix. Thanks for building this. Thanks for joining.

• 1:00:30Speaker 01

  Thank you.

• 1:00:31Dan Shipper?

  Have a good one. All right. That was awesome. So cool.

• 1:00:35Speaker 02

  Thank you. Yeah.

• 1:00:36Dan Shipper?

  And we have so many people on this stream. There's almost 10,000 people here. Oh, my God. If you're joining us for the first time, we just had Felix on. Felix is a member of the technical technical staff at Anthropic. And he was talking to us about Claude Co work. If you are you looking at this this stream, then you probably know what Claude Co work is, but I will share my screen and show you again in case you're.

• 1:01:02Dan Shipper?

  Case you're wondering, it is a new version of Claude that's sort of like Claude code for non-technical people. It looks a little bit like this. We've been testing it at every where the only subscription you need to stay at the edge of AI every dot to we get access to this stuff before it comes out and we do vibe checks like this. We do them live. We also write them on every dot to. So we had, we got this earlier today. So we were just testing it out. Um, here's an example of a task I gave it and you'll notice it looks a lot like normal Claude, like the normal Claude chat. The, the differences are a bit subtle, but I think that they, um, it does make a big difference. So instead of a chat, you have tasks. Um, when you, when you look at

• 1:01:46Dan Shipper?

  the, you know, this for this query, or maybe like, uh, let me find a better example of this.

• 1:01:54Dan Shipper?

  Like this query, for example, you'll see that Claude like a coworker ran for a really long time. If I asked the same query, I wanted to go to our every agent native guide and walk through it. Do you do UX review? Um, Claude would have stopped after a couple of turns and given me a pretty good answer, but this does a lot more research. So because it's working on your computer, it's going to be able to work for a long time. And I think that's, that's sort of the key thing that you can take away from when you might want to use coworker and how coworker might work differently than regular Claude, which is for the first time, if you're non- technical, you can ask your computer to do something and walk away for a while. Uh, and then you can, you can also ask it to do many things in parallel. So this is an experience that if you're using Claude code, you have a lot with programming, but I think most non-

• 1:02:39Dan Shipper?

  technical people are still in the kind of like turn by turn era of using, uh, using chat and just expecting a response almost immediately. And this is much more of an, uh, built to be an async experience for non-coding tasks, like, you know, data analysis or research or writing documents, like all that kind of stuff.

• 1:03:00Dan Shipper?

  Like Felix said, they built this in a week and a half. Um, which is crazy.

• 1:03:06Speaker 02

  Crazy, which is the new normal, by the way. So anyone who's like coming up with the PRD in two weeks. Nope, you ship the whole thing a week and a half.

• 1:03:16Dan Shipper?

  A hundred percent. So there are some rough edges here, um, but they're going to be improving them really quickly. I think it's, I think it's really cool. The, the pattern that I, he shared that I really think is interesting is I was kind of asking why even add a new tab? Um, uh, like a cowork tab and he said,

• 1:03:32Dan Shipper?

  we just needed, we essentially needed a playground to like mess around and do stuff that is a little bit less polished. And so it's nice to have, have this extra tab, which is an interesting pattern in AI where now you can build so quickly. I think we need more patterns for, for what to do with that.

• 1:03:47Dan Shipper?

  Kieran, any reflections from, from our conversation with him or anything you're thinking about right now?

• 1:03:51Speaker 02

  Yeah, I thi- I think it's like, why use cowork over chat or code? I think that is always my first question, and I think if you're a non-technical user, uh, just think of cowork as something that is chat. Just try cowork as the new version of chats, the better version or a different flavor. And just open it and do the same things you've been doing in chat, but you see that it is different and you can do things. Like one really, really important thing is in chat, if it is responding, you cannot send a new message. When it does something, you're like, oh, wait, wait, that's wrong. With cowork, you can queue a message and like while it's working, say something new.

• 1:04:33Speaker 02

  So like just those tiny things are very, very handy. So just try cowork instead of chats. It has skills like you can generate documents, Excel sheets, PowerPoint presentations, PDFs, like it can do all those things. So, um, if you are applying to jobs, like just upload everything and say, hey, can you rewrite my, uh, resume for this job? And, uh, like try it out, like things you would manually do normally. And also connect Chrome, uh, you can enable it. Maybe you can share, you can show that how to do that then in connections.

• 1:05:10Dan Shipper?

  Uh, yeah. So if you go into your settings and go into, I guess it's, is it connectors or is it?

• 1:05:16Speaker 02

  Yeah.

• 1:05:17Dan Shipper?

  It's in connectors. Here, control Chrome.

• 1:05:19Speaker 02

  Yeah.

• 1:05:20Dan Shipper?

  So you can, you can add that in there and then it'll just be able to basically use Chrome on your computer, which is really cool. I mean, one of the things I had it do. That is totally new and interesting is, do I have it? I had it go through my Twitter feed, my X feed. And I asked it to just like, tell me what was hot right now. What are people talking about? And that's really cool. Like, that's ordinarily something that you would have had to pay a lot of money for an API for. And this can just do that without really a problem, which I love. I love that.

• 1:05:55Speaker 02

  Yeah. And if you use Chrome and you're logged in on things in Chrome, it's already there. So you don't need to log in again. It just uses your Chrome itself.

• 1:06:05Dan Shipper?

  Yeah, exactly. And I use Atlas, so I had to log in all this stuff. But if you use Chrome, it's great. So like, look, it just read my Twitter feed. That's so cool. There's so many possibilities if you're a writer or marketer or anyone that does research, especially research on things that don't have APIs

• 1:06:27Dan Shipper?

  that you can now do without much trouble. And to your point earlier, Kiran, like when you're thinking about, okay, what would I even use this for? I think that one of the things that we try to embody at every is we try to be really curious and know that if you're trying new technology for the first time, the first five things you do probably aren't going to work. But there's like a really, there's something really fun about being curious right now. Because Felix, for example, the guy who made this doesn't even know how we're going to use it. He needs people like us, anyone who's watching this stream to like mess around with it and figure out all the new, interesting, emergent ways that it could be used so that he can make the product better. So it's the first time where

• 1:07:11Dan Shipper?

  the software developer is more like setting up a playground, but has no idea how the playground is going to be used. And the users are the ones that are being creative and figuring out things to do. And so if you've if you approach this with curiosity, it's like a huge opportunity over the next couple of weeks to like, figure out what this is for. I think another, another important thing is people tend to have this thing that I like to call capability blindness, which is I tried this once before, three months ago, it's never going to work with AI. And the really interesting thing about AI is like, it changes every couple of months. Like I freaking like Opus four, five, just totally changed everything. Stuff that had never worked before starts started working now.

• 1:07:56Dan Shipper?

  And so if there's something that you really want AI to do, like for me, that's, that has always been, I want it to do copy edits. Oh, we should see if it can do copy edits. I'm going to set that up. So I've always wanted to do copy edits. And every time something new comes out, I just try it because I know at some point in the next couple of months, it's going to start working. So I'm going to actually set that up. I think that'd be a really fun demo. Karen, do you want to, um, you want to talk about what, anything on your mind so that I can take a little bit of time and make the, make, get the copy edit setup?

• 1:08:29Speaker 02

  Yes, I'll share my, here, I'll just share a screen here. So yeah, if you share my screen.

• 1:08:39Dan Shipper?

  Oh, sorry. Yeah. Forgot that you were, uh, that I was your, could see my screen. Okay.

• 1:08:44Speaker 02

  We're professionals, everyone.

• 1:08:46Dan Shipper?

  Yes, obviously.

• 1:08:48Speaker 02

  We started live streaming last week, gave us some slack. Yeah.

• 1:08:53Speaker 02

  Cool. Yeah. So we talked about skills a lot. Uh, you might think like, what the hell is a skill? Isn't that just a prompt? Yeah, it's a prompt, but it's also more, uh, it's more like, uh, yeah. And what can you do with it? So, uh, this is the most hackable way for cowork. So if you want to personalize your cowork experience, this is the way Anthropic says. So I asked, what are all the skills I have and how can I use them? So for example, these are document creation skills. Uh, and it just learns how to create Excel sheets. And these are some of my own. Uh, I, I love Swiss design. So I have like a Swiss design, uh, scale, a Gemini, uh, image gen,

• 1:09:35Speaker 02

  where you can, uh, get nano banana images inside bold code.

• 1:09:41Speaker 02

  I have a DHH Ruby style, uh, to roast my coat. And yeah, all, all these things. So I just create skills for everything. So, uh, I have a 3D print skill where I needed to print some 3D things. And I was like, I'm sure Cold Code can do this. And so I created a skill. And these skills, normally what I do is I go to chat and like say,

• 1:10:11Speaker 02

  can you generate, can you deep research how Dan Shipper writes? So for example, if I like Dan's writing, I might do this and actually.

• 1:10:22Dan Shipper?

  I don't know, that guy's kind of a blowhard.

• 1:10:24Speaker 02

  I know. So normally what I do is I enable deep research here and go hard. And it run, deep research runs for like an hour sometimes, which is great. And then I say, can you create a skill for this? So I'll just fake do this, but then I create a skill for this. And there is this thing in Claude, in capabilities, that you can enable, which is really cool, the example skills. So you go to capabilities, example skills, and there's a skill creator from Anthropic. If you enable this, after you did the deep research or anything, you can say, create a skill out of this. Obviously, you can do that here as well.

• 1:11:09Speaker 02

  So you can do research in CoWork and create a skill out of this, and it will be loaded inside, inside here. So for example, now, can you design with Swiss design, a very beautiful chair for me and create a STL so that I can 3D print this miniature, four centimeters high. So let's see. So I do this and it shoot then, can you design?

• 1:11:38Speaker 02

  Okay, so hopefully it's, yeah, so it's loading the two skills here. You can see the context it pulled in the Swiss design scale and the 3D print scale.

• 1:11:49Speaker 02

  So I like that, that you can really clearly see this.

• 1:11:53Speaker 02

  And what it does, the skill will just inject a prompt where it says, just do these things. Make it look good, don't be, don't use enter or whatever. This is the aesthetics. So it's now doing things and there is also in skills, you can put like scripts, Python scripts, whatever script you want, binary scripts, anything you wanna run. And so if you want something programmatic, you can encapsulate that into a script and put it in a skill. So every time it runs, for example, if you wanna check if it's the shape or if it's following a certain like static

• 1:12:33Speaker 02

  or if it's actually linting well, you can encapsulate all that in a skill and trigger it as well. So it's now doing this, which is really cool. And the skill will create a STL file, which I can then 3D print. So we'll see, like a chair, obviously is maybe a little bit hard, but why not? So this, this is how you can create your version of cowork with skills. So you can capture and find the things you do and encapsulate your style and everything you do into a skill and then have it available here. What is cool here is on the right side, you can see the STLs out, the preview.

• 1:13:18Speaker 02

  There's a preview, let's look at the preview. Okay, so it's a little bit hacky still because, or here the sidebar, there we go. Okay, this is the chair, beautiful. So this SVG is not 3D, let's see, can we, can we look at this? No, we cannot look at this. But yeah, we have a STL, let's see if I can open this. Opening Ben's Studio. I'll see if this looks any good. And I'll share my other screen. Share screen and then we go to them. So here is my Swiss design chair.

• 1:14:00Dan Shipper?

  Amazing. We need the skill here and go, go.

• 1:14:04Speaker 02

  Uh, oh yeah, so the, the, actually the 3D skill is, is all my machine, but I'll, I'll share it. I'll push it to the, uh, to the interwebs. And that was actually my request to, uh, uh, yeah, to Felix is like, can I automatically, uh, like pull these things into my, uh, my, uh, coding experience or like in cowork that I, if I push them online. So yeah, I will share this, but, uh, it's, yeah, it's make your own things, uh, go wild. And it's kind of funny to, uh, then print this. I'll print it and take a picture later.

• 1:14:39Dan Shipper?

  I love it. Um, so I, uh, if, if you've just joined, one of the things that we're talking about with Claude cowork. I think that one of my bars for AGI is can it do copy edits in a Google Doc? Like it's surprisingly hard to get these things to do that. So, uh, what we have at every, obviously we publish every single day. We have a very, um, high bar for the copy that we publish. We want to make sure everything is like really, really clean and beautiful. And so we have a skill that's in Claude that is our every proofreader skill. And what I wanted, what I wanted to do is see can Claude cowork copy edit a Google Doc? So this is the Google Doc. This is an article that we published, um, last week, uh, by Katie Parrot, who's one of our writers, who's fantastic.

• 1:15:22Dan Shipper?

  She's going to be the one writing the vibe check on cowork for later today. So look out for that, um, on every, every dot TO. So I just said like, okay, I have an every proofreader file. I just downloaded the skill file and gave it, gave it to it in, in documents. Can you go to this Google Doc and make edits that suggest changes? Um, and then, uh, this is actually really interesting. So like, it's just hard for AIs to do this because they have to go through the, the, the copy editor and just look for every, for each rule in the copy editor. It has to go through every part of the document and find all the violations. And that's just like really hard to do. But you can see, I said, go do this. This is not something that I don't think that the regular cloud app could really do this. Maybe Claude, if, if you use it in Chrome could, but, um, other than that it could not do it.

• 1:16:07Dan Shipper?

  You can see it loaded the document. It's getting all the text, it's scrolled through the whole document. And it's now clicking on, it looks like it's clicking on suggesting. Let me see if I could actually find the Chrome tab that it has opened. Yep. So you can see that it's, uh, here's what it's doing. It is, it successfully got itself into suggesting mode. And now what it looks like is it's searching using find and replace for errors that it found. And we'll see, now I need to double click on editor in chief to select it and type the replacement. Let me triple click near it to select and manually make the edit. This is so interesting.

• 1:16:51Dan Shipper?

  I feel like watching this is like watching a video game. I'm like,

• 1:16:54Speaker 02

  Oh, yeah.

• 1:16:55Dan Shipper?

  Come on, Claude.

• 1:16:56Speaker 02

  Yeah. It's really entertaining. Yeah.

• 1:17:00Dan Shipper?

  Yeah. But Google Docs is like the final boss of stuff for AIs to use because it's just like so, it's ultimately such a simple application, but it's the way that they built it is so complicated. It's like not actually real HTML. It's like a whole, it's just, just really hard. So, um, yeah, it's just struggling. So if you're at Anthropic and you're watching this, if you could please improve your computer use to actually be able to use Google Docs. Well, that would like totally change my life and change the life of Kate, our editor in chief, and a bunch of other people here. So, um, yeah, please, please do that.

• 1:17:39Dan Shipper?

  And it says everything about AI is like a video game. Absolutely true. Karen, go for it.

• 1:17:43Speaker 02

  Yeah. So I'm thinking, so we have this skill, but is it like skills can be maybe optimized now to actually make use of sub agents and things like that, that maybe were never available. So it might be also time to rewrite our skills a little bit. If you created skills for Claude, maybe we can push it to use sub agents or you execute scripts more or like do some things in a programmatic way. So there might be an opportunity also to do more of that. Yeah.

• 1:18:17Dan Shipper?

  Katy Parrot, who wrote this article, says surely this is the cleanest copy that has ever copied. It's true. It's probably hasn't found many errors because Katy didn't make any. But we'll, we'll see. It's, it's still working on editor in chief with dashes.

• 1:18:31Speaker 02

  It's doing something.

• 1:18:33Dan Shipper?

  Thank God this is working. This is able to work async, because if I had to like, we were actually, you know, looking over the, over its shoulder for forever, it would, it would not be particularly.

• 1:18:43Speaker 02

  Yeah, we'll do a live stream, or Claude should do live streams of it doing work. Yeah.

• 1:18:48Dan Shipper?

  Yeah. Actually, that'd be really fun. Claude doing work.tv.

• 1:18:51Speaker 02

  And I see it mess up. Yeah.

• 1:18:54Dan Shipper?

  Here, I'm going to give it a hint. Hey buddy, you can just type in there and replace it. You don't have to use find and replace. Let's see if it, this is.

• 1:19:05Speaker 02

  So you still, yeah. Yeah, you still didn't do that.

• 1:19:08Dan Shipper?

  Yeah, this is another thing that like, that this does that is different from if you're using the chat, which is, you can see this button says queue, add to queue. And this is going to be a lot, the UX of this is a lot more like the UX in Claude code, where you can just send messages, even if it's working, and it'll deal with the messages. You don't have to wait for it to respond to your last one. And I think that's really, that's really, really good and important for

• 1:19:36Dan Shipper?

  async conversations. And we got our first compact. The, the bane of every Claude app user's existence is compact. So we'll see. Coming up after the break, we'll see Claude.

• 1:19:53Dan Shipper?

  Replace editor in chief with dashes.

• 1:19:56Speaker 02

  Or forgot what it was doing and does something completely different. We'll see. So one, one thing, it says queue, which is a little bit confusing, because queue in my head would mean like, do this after you finished the one before.

• 1:20:10Dan Shipper?

  Yeah.

• 1:20:10Speaker 02

  But it's actually a little bit smarter. If you say, yo, stop, stop, stop what you're doing. This is terrible. Like, it will actually look at the text and think like, hey, do I need to change anything what I'm doing right now? So it, it does like either pick it up immediately, or if it's like, after this, do this, it will actually queue it. So there is a little bit more flexible than just like injecting it. It will look at it whenever you add it, which is good to understand as well.

• 1:20:37Dan Shipper?

  I wonder if Claude is getting performance anxiety, because it knows that 13,000 people are watching it. Okay, dude.

• 1:20:44Speaker 02

  Oh, I thought it was thirteen people.

• 1:20:48Dan Shipper?

  Are watching this. Please just type. You're so close. Um, if you, if you want more, uh, extremely sight, uh, smart and insightful takes on AI, you should subscribe to Every. Every is the only subscription you need to stay at the edge of AI. It's every.to. Um, we, uh, we have a pretty cool business. We do, um, ideas, apps, and training at the edge of AI. So on the idea side, we have a daily newsletter. We get our hands on, um, we get our hands on stuff like, like Claude cowork early on the day that these things come out. We do, we do vibe checks, which tell you from our team, uh, as we're using these in our day to day life and work.

• 1:21:34Dan Shipper?

  Um, what is it good for? What is not, not good for? That, that, uh, happens for products. It happens for new models. So like when Opus four, five came out, we had a review on the day of. I can show you that. Uh, we also develop apps ourselves. So I'll, I'll, I'll talk about the apps in a second, but this is the article that we wrote on the day that Opus four, five came out. This is by Katie. Again, the Katie, this is Katie's article. It's by Kieran and by me. And, um, if you've been seeing all of the, um, like hype about Claude code and Opus four, five, we started talking about it November twenty-four, twenty twenty-five, the day it came out, and we said, it's the coded coding model we've been waiting for. It took people about a month to catch up to that.

• 1:22:15Dan Shipper?

  So if you really, really want to know, um, if you really want to know what's going on at the edge of AI, it's really good. I, I mean, I'm biased, but I think it's, I think this is a really good read and our vibe checks are really good. We also have apps. So, uh, we have four apps that we build as part of every, we have one called Cora, which, which, which Kieran builds, which is an AI email assistant, cora computer. Um, we have one called Monologue, which is a speech to text app. You can see Monologue right here. This is Monologue. I'm talking and it will type in here. Uh, I don't want to mess up our, our buddy Claude. Um, but it's sort of like Whisperflow, uh, or Super Whisper.

• 1:22:52Dan Shipper?

  And it copied it to the keyword. You see it. It just pasted my text in there. We've got a couple other ones. Spiral, which is a go an agentic ghostwriter and sparkle, which is a file manager, file cleaner, and it's all available for one subscription. So you pay one price and you get access to all the ideas. So everything that we write, all the apps. So for apps, AI apps at the edge of AI and training. So we have camps that you can go to. We're doing a cursor camp where the team from cursors joining us in a couple, in a couple of days and you get to learn directly from the cursor team. You saw we had Felix from Anthropic on earlier. We do these all the time. We

• 1:23:34Dan Shipper?

  basically teach you how we build. So everyone at every is a builder and writer. And as we're using these tools like Claude cowork and Claude code to build apps and do writing and do design and all that kind of stuff, we bring you along for the ride. You should subscribe every dot to. And we're still on this extremely scintillating view of Claude trying to make, make suggested changes in a Google Doc. And I think we can call, we can call this one just, we need a copy edit, Google Doc copy edit benchmark, and it has, it has failed. That benchmark is sat is not saturated. We're still not AGI folks. So stay tuned for hopefully the next model. Oh, Anthony, Anthony Morris from Anthropic,

• 1:24:19Dan Shipper?

  huge fan of Cora. I love to hear that. Karen, doesn't it make you feel good?

• 1:24:23Speaker 02

  Yes. Yeah, we have a few anthropic peeps using it. That's pretty great. Thank you.

• 1:24:28Dan Shipper?

  Yeah. Karen, what's on your mind?

• 1:24:32Speaker 02

  Um, I think on my mind is I want to try this out. This makes me very excited. Like this, this feels like something that was missing even as a coder, I want to use this. So like if you are using cloud codes, probably this is easier for you to use. And I really want to just see what it can do, how we can use it in our daily lives. I would love iOS integration, like it, like scheduling things, pushing things to my phone, like me chatting with it, like, and also one, one thing that looks like it's not super present now is like storage. So currently you can store or connect it to your local computer. But what if you're on your phone?

• 1:25:16Speaker 02

  Is there some persistence? Like, there are projects in the chat site, but there are no projects in the the cowork site. So like, I'm very curious how to use this, but what I love is it hooks into the skills and things I already have. So what I'm going to do is just whenever I would have started up a chat window, I'm now going to start up a cowork window. And just see how it behaves and goes and just, yeah, go from there.

• 1:25:43Dan Shipper?

  Yeah, I think that's a good, I think that's a good one. Okay, so we're gonna have to write the vibe check in a few and probably also do some other work.

• 1:25:52Dan Shipper?

  I am curious if you had to give this a rating. So when we do vibe checks, we have red, yellow, green, and then we have a gold medal for paradigm shifting. So when we, when we did Opus four five, I think you and I were both at the paradigm shift level for for comparison. I think for GBT five, I was a, I was a yellow, I was a yellow green and you were a yellow, I think, when it first launched, right? So where do you put this if you had to give it a red, yellow, green or a gold medal?

• 1:26:23Speaker 02

  I, I would rate it from just playing with it. You like the UI and like execution, I would say yellow because it's kind of janky. But, but it's very interesting, like it's like, like we can say what we want, but like it is kind of janky. But that's what they said. We, we made this to try out and like I see Anthropic is very, very good at listening to people. I'm sure like someone on the team here saw me click something or you do something, they're already pushing changes to this. Because that's how fast they go. But from an, like, from an idea, I would say green. Because I, I really think we should experiment more with the interface, what it is.

• 1:27:07Speaker 02

  And like giving this Claude code moment to more people, like having more people that do normal work. Also starts to feel a paradigm shift of like async work and really handing something to an agent. And I think this could be that, because I don't see any other company. Uh, do it like this. And obviously Claude is very, uh, yeah, it's like, it's a very good harness. So like, let's milk it. Let's make it better. But I would say ID, green. Uh, execution today, right now, yellow.

• 1:27:45Dan Shipper?

  Yeah, I, I think that's, I think that's spot on. And but like, to, to, to your point, Anthony Morris just said, I have a PR up already from something Dan said. So yes, lol.

• 1:27:55Speaker 02

  Exactly. Yeah. That's why we do these.

• 1:27:59Dan Shipper?

  Yeah. Uh, welcome to the Anthropic Product Meeting, happening live on X with your friendly neighborhood, uh, product testers. Um, and yeah, I, I think that, I think that's, that's totally right. They're moving super fast. I, I love how, I love that there's already going to be changes in the product from this. So for anyone who's watching or listening, you should give more feedback, do it in the chat, um, send it, send it to people on, on, on X. Um, they really actually are, do iterate pretty quick. And I think that it's fine that this is a yellow.

• 1:28:31Dan Shipper?

  And I, I, the, the, the way that I think about it is, obviously, there's a Claude code moment on X over the last couple of weeks. And like, that was the thing that they immediately just like shipped something. It's like, how many, how many founders were like building a Claude code for, um, Claude, we were calling it Claude code easy mode because it was an ideal, we were, we were batting around internally at every two. And, uh, and they just built it. They just went ahead and built it. And I think that's, that's so cool. And it shows they really have their finger on the pulse of what people want. That's the, that's the thing that I think is good about a lot of Anthropic stuff is you can tell they use it themselves. Um, yeah. And they're using it in a very AI native and agent native way.

• 1:29:09Speaker 02

  Absolutely. Yeah, they, they get it. And but they're also listening, like, they get it, but they also leave out things because they wanna listen as well. They're not like, this is the way. They're like,

• 1:29:20Dan Shipper?

  Yeah.

• 1:29:21Speaker 02

  This is a way and we're listening very carefully. And then they make iterations, which is great.

• 1:29:27Dan Shipper?

  Yeah. Speaking of which, this is a way that if you are a, if you want to build an AI, this is a way to think about doing it.

• 1:29:37Dan Shipper?

  We have a guide up on every about agent native architectures. So this is, if you're a developer, this is going to be really good for a developer. It's also totally good if you're a non-developer, you just click read with Claude or read with chat GPT. And it will tell you about what this is, but this basically boils down a lot of principles that we've kind of intuited from the way that Anthropic builds Claude code and now Claude for Claude cowork. And turns it into a really easy guide to think about, how do you build software in this era where agents are at the core of software? Instead of software being this sort of like deterministic thing that is, is built with deterministic code that are, that are rules that are laid out beforehand by a programmer. Instead,

• 1:30:18Dan Shipper?

  as the core of something like Claude code or Claude cowork is just an agent and features are really just prompts to that agent to get work done. And that opens up a whole new, new territory of software to build and it opens up who gets to build software. So if you're a non-technical person and you, you're feeling like, oh, I, I can't really build software. I promise you, you can. You should really try.

• 1:30:40Dan Shipper?

  Claude code, you should really try just a Claude app or now. It's worth trying. Claude cowork, I think that that it could be really good for vibe coding stuff. And if you're thinking about how to structure your apps, it's actually kind of not intuitive because it's a whole new world for, for the way that you do programming. And so a lot of the, a lot of program intuition, I think is outdated and a lot of, therefore a lot of AI intuition about how to build software is outdated. So you need guides like these to help push your AI to do the right thing and build, build the thing in the right way. I think we're, we're getting close to time. I'm going to need to hop off. We're both going to need to hop off and get some actual work done. This is fantastic. It's so fun. We're, we do vibe checks for every new thing that come out.

• 1:31:21Dan Shipper?

  We're doing this, these live streams as a new thing. Usually we just write them, but you should expect next time there's a new model drop or a new product release that we will have a live stream vibe check with our internal testing. Remember we get all this stuff before it comes out and we'll tell you what we like and what we don't like. Kieran, any final words before we head off the stream?

• 1:31:43Speaker 02

  No cheers. Thank you, everyone.

• 1:31:46Dan Shipper?

  Thank you all.

• 1:31:47Speaker 02

  Check it out.

• 1:31:48Dan Shipper?

  Check out every. Try Claude. See ya.

• 1:32:00Speaker 03

  Oh my gosh, folks. You absolutely, positively have to smash that like button and subscribe to AI and I. Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard. But instead of gold, it's filled with pure, unadulterated knowledge bombs about ChatGPT. Every episode is a roller coaster of emotions, insights, and laughter that will leave you on the edge of your seat, craving for more. It's not just a show. It's a journey into the future with Dan Shipper as the captain of the spaceship. So do yourself a favor. Hit like, smash subscribe, and strap in for the ride of your life. And now, without any further ado, let me just say, Dan, I'm absolutely, hopelessly in love with you.