Claude Code's Creator Reveals "Claude Cowork"'s Setup

In this episode, I sit down with Boris, the creator of Claude Code and one of the key builders behind Claude Cowork, to unpack what Cowork actually unlocks and how people use it in the real world. He walks through a hands-on demo where Cowork organizes files, extracts receipt data, builds a clean spreadsheet, and even drives the browser to create and share a Google Sheet. We go deep on how “agentic” work feels different when the model takes actions across your computer, your browser, and your tools. Then I shift into Boris’s viral workflow for Claude Code: parallel sessions, plan-first execution, Claude.md as a compounding team memory, and verification loops that dramatically improve output quality. Timestamps: 00:00 – Intro 03:26 – Cowork Overview 05:51 – Demo: Folder Access + Renaming Receipts 08:23 – Demo: Turning Receipts Into A Spreadsheet 10:52 – Demo: Google Sheets + Chrome Control 15:52 – Demo: Emailing The Sheet + Parallel Tasking 22:07 – Best way to start/use with Cowork 24:22 – Where will AI and Agents Go Next 28:44 – Boris’s Claude Code Setup 41:12 – The “Claude” Pronunciation Discussion Key Points I use Cowork as a “doer,” not a chat: it touches files, browsers, and tools directly. I think about productivity as parallelism: multiple tasks running while I steer outcomes. I treat Claude.md as compounding memory: every mistake becomes a durable rule for the team. I run plan-first workflows: once the plan is solid, execution gets dramatically cleaner. I give Claude a way to verify output (browser/tests): verification drives quality. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND BORIS ON SOCIAL X/Twitter: https://x.com/bcherny

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

• 0:00Greg Isenberg?

  Claude Co-Work is here and if you understand how to use it, you're going to be able to outperform 99% of people on this planet. It is an easy way for you to use Claude Code. You might have heard of Claude Code, it's gone viral, but the problem is, it feels technical. You have to go into the terminal and it's not fun for a lot of beginners. So Claude has come up with Co-Work and it's a brand new product that harnesses the power of Claude Code in a UI that is simple, that anyone could use, that your dad can use, your mom could use, hey, even you can use. So in this episode, I brought on Boris, the maker of this product. I'm so excited that he shows you the best practices for how to use Claude Co-Work

• 0:43Greg Isenberg?

  and at the end, how he sets up his Claude Code to get the most out of it. You're gonna love this episode.

• 0:59Greg Isenberg?

  We are lucky, we've got Boris. He's the creator of Claude Code and I would say the co-creator of Claude Co-Work today. And today, what I want to get accomplished is, everyone's talking about Co-Work and I want to best understand what are the use cases? How can we get started? What are some non-obvious ways I can use it? So Boris, thank you so much for coming on the show. And I have one question for you. By the end of this episode, what are people going to get out of it?

• 1:29Speaker 01

  Ooh, I think people are gonna start to get some more ideas for how to use Co-Work. And hopefully, they're gonna tweet about it and maybe they'll even reach out to me so I could learn how they want to use Co-Work. It's funny, I feel like Claude Code, from the beginning, it was sort of built to be, it wasn't actually built to be a product at all. But when we first started thinking about it as a product, we thought that the thing people would use it for is coding. But we've learned very quickly that people didn't just use it for coding, they used it for like all sorts of stuff. So I kind of feel the journey of Claude Code has been very surprising. And I have been learning so much just watching how people use the product and how they abuse it and kind of like what they actually want to use it for. And even if it's not designed for that.

• 2:15Speaker 01

  So I kind of feel the same way about CoWork. You know, I have some ideas about what people are going to use it for. I kind of view these as hypotheses. And so, you know, happy to talk about it, happy to maybe I'll do a quick demo to to show you kind of some of the some of the things that we use it for. But I think that it's going to be pretty surprising and I hope that I will be surprised when we see how people actually use it in the wild.

• 2:37Greg Isenberg?

  Yeah, I think that's always the case with with platforms, especially if you think about it like when when the makers of the apps are created, the app store. You know, the the initial apps was like, you know, a beer drinking app and like a bunch of random apps like that. Did they know that, you know, Uber was going to come out of that DoorDash was going to come out of that TikTok was going to come out of that? Probably not. So I think that. What's really cool about the phase that we are in right now with Claude Code and also Claude CoWork is. We're all figuring it out at the same time. And none of us, including the creator, have all the answers, but I agree with you like what's. It's it's a good time to be sharing some, you know, sharing what's working, what's not working and, you know, if you're open to it, let's let's.

• 3:23Greg Isenberg?

  Screen share and get our hands dirty.

• 3:25Speaker 01

  Yeah, yeah, let's do it.

• 3:26Greg Isenberg?

  So what are we looking at right now, Boris?

• 3:29Speaker 01

  Yeah, so this is the this is the Claude desktop app. So you just download it. It CoWork is only available for macOS. You know, Windows coming soon. There's a few different tabs in the desktop app. So there's the chat, that's the default, there's CoWork, that's the new one, and there's code and that's just Claude code.

• 3:47Speaker 01

  CoWork under the hood, it's actually just Claude code. And so, you know, the agent that makes Claude code awesome, we call it the Claude agent. It's also available as the Claude agent SDK, so you can use it programmatically, you can, you know, all sorts of companies build. All sorts of cool things on top of it. We actually use that same exact SDK directly in CoWork. So it's like, you know, it's pretty cool. It's just kind of one layer across everything. We have the best agent, have the best agentic model, might as well use it.

• 4:17Speaker 01

  And so what I'll do is just to kind of show how to use this thing. And you know, like, when I think about agentic AI, this word agentic has sort of lost all meaning because it's just like used so much. So I feel like probably a lot of listeners have heard the word agent, but they don't actually know what it means. Or, you know, they think it's like some like cool AI or something. But it actually has like a very specific meaning in the AI world, which I think has kind of been lost because a lot of the products that people have released and called agentic in the past are not actually agentic. And so like, when you think about the AI products that everyone's used, you know, like obviously Quad Code, chat-based apps where, you know, you just chat with the app kind of back and forth, send some messages. The biggest difference with agents is it can take action.

• 5:02Speaker 01

  And, you know, it's not just text and it's not just like web searching, but it can actually use tools on your computer. It can, it can interact with the world. And so for Anthropic, from the very beginning, since before our models were good, like before, like, you know, like Quad 3 or whatever, this is a thing that we wanted to get really good at because we felt that it's very important. And so from the start, we wanted our models to be really great at coding and then really great at tool use and then really great at computer use. So it's kind of cool, like, you know, the last year, seeing how people have been hacking Quad Code. It's pretty obvious this is kind of the place that we should go. And so for people that have used Quad Code, you know, none of this will be, you know, like too surprising. These are actually things that you can do.

• 5:46Speaker 01

  So really what we're trying to do is make this something that everyone can use in a way that's safe. And so what I'm going to do is, you know, here on my desktop, I have this like receipts folder. I have a few receipts in it. So I'm just going to give cowork access to my desktop. And you have to pick like which specific folders I can see. By default, they can't see anything. So you have to kind of opt in to see, to let it access specific folders. And so I'm going to say, you know, I can say, I have a receipts folder.

• 6:21Speaker 01

  Can you rename the files to match the dates on the receipts?

• 6:29Greg Isenberg?

  So I think one interesting thing is when you're using cowork, it's really like it's operating with your files. Like that's, that's a big sort of mindset shift that people should have. It's almost like your operating system. Is that right?

• 6:44Speaker 01

  Yeah, exactly. It's like it has your files for the ones that you give it access to. But actually, the even cooler thing is it can use all sorts of tools.

• 6:53Speaker 01

  And so like files actually is like, you know, that's like, that's useful, but it's not, it's not like that cool. What's actually much more interesting is it can generate files for you. So, you know, it can make like presentations and things like this. It can interact with any tool over MCP and it has built in support for Chrome based browsers. So it can actually control your browser to do, to do stuff. And so I'll kind of show that a little bit. So this is kind of the first step. When you're first getting started with cowork, the thing I recommend is, you know, do exactly what I just did. You know, just mount the folder, give cowork access to it and just like play around with it. It's super useful for cleaning up files, organizing things like that. And so here it found these four receipts that I have.

• 7:35Speaker 01

  It's asking me if one of the receipts, I guess, is missing a date. So should it just rename the others? So I'll just say, um, you know, for one, it's, let's say it's like up to you.

• 7:50Speaker 01

  And then for two, I'll say, uh, don't rename it.

• 7:55Speaker 01

  And we actually call this like reverse solicitation in the AI world. So, so what this means is when the model is unsure about something, it's going to ask you for clarification. And we've sort of taught the model to be pretty good at this. So instead of assuming if it's unsure about something, it's just going to ask you.

• 8:13Speaker 01

  And so, yeah, in this case, so it renamed the receipts. So I'm just gonna open this up to double check. Yeah, cool. And so the receipts were named a little bit better organized.

• 8:24Speaker 01

  And so maybe what I can try next is, um, let's like put this in a spreadsheet.

• 8:30Greg Isenberg?

  So it takes control of your computer, basically, in that sense, right? If you allow it to take control.

• 8:37Speaker 01

  Yeah, yeah, that's right. And so we put like so much work into kind of safety and making sure that as this happens, you don't like accidentally shoot yourself in the foot and like delete files or whatever. So there's just like a huge amount of work that went into this. And it kind of starts at the model side where, you know, for Anthropic, from the very beginning, we were the AI safety lab and not the reason that we exist. And so there's a lot of work into like alignment and mechanistic interpretability and kind of all these ideas to make sure that the model does what you want in a way that's safe, kind of at the model layer. And this literally means like studying the neurons, kind of the same way that you would study neurons and, you know, like in the human.

• 9:18Speaker 01

  And so, you know, you can like identify structures and you can kind of study in a very scientific way as a black box also to make sure that it's safe. So this is called alignment.

• 9:28Speaker 01

  And then we do a whole bunch of other stuff. So there's actually a whole virtual machine running under the hood. And this is just to make sure that any actions taken are safe and don't affect your broader system. And then as of last week, there's also deletion protection. So if you accidentally delete something, then you're gonna get prompted first. So the model can kind of make sure that that's actually a thing that you want to do. Obviously, also, as we start interacting with the internet, something like prompt injection is quite scary. And so we built in a lot of protections against that. Obviously, you know, it's not perfect and it's something we're iterating on. But this is also part of the reason that we released this pretty early is we want to see how people use it. And a big part of making models safe isn't just studying them in a lab, but studying them in the wild to see how it's useful.

• 10:13Speaker 01

  And so this was like pretty cool, right? So we have this folder. First, it kind of renamed all my receipts. I asked it to make a sheet. It just made the spreadsheet, so it's already here. Um, maybe I don't want a spreadsheet. Maybe I want like a Google Sheet. So actually.

• 10:28Greg Isenberg?

  That's so interesting, right? Cause like, I think uh where people stumble with tools like cowork and Claude code is because you can do anything. Making it a, of course, that makes sense, making it a Google Sheet. But like, that's where it's so interesting that you can, you really can treat it like a teammate in that sense, right? Like, go and do this thing. The world is your oyster. Whoa, what is happening right now?

• 10:55Speaker 01

  Yeah. So it's like, it's opening the browser. Um, and so here it's gonna ask me for, for permission. Just for this demo, I'm gonna say always allow for the site. Um, but you can just say like, allow once or deny. And so Quad's taking the wheel. Um, it's making a spreadsheet for me. Um, this is gonna sort of take a while. And so this is one of the things that we're iterating on is like making this kind of computer use a lot faster. I, I remember like, man, this is like when I first joined Anthropic and this was maybe um, this like Sonnet 3.6 days or I forget what the, what we called it, like Sonnet 3.5 new. Um, and that was the first model that I think we really started to crack computers. And I remember I was like sitting with my team. And there was literally a researcher that ran into the room like in the movies and was like, oh my God, Quad knows how to use computers.

• 11:41Speaker 01

  And um, we just had it like order a pizza and it uh, it picked up pineapple pizza and then ordered it and it asked us for a credit card. And then we, we got that delivered to the office, but it was tedious. It took like an hour or something for it to click around. And since then, we've been improving the model's ability to use a computer. Um, and so you can kind of see that here. So here the, you know, Quad is typing and it's interacting with the spreadsheet. And it can see what's on the screen. It can interact with it. Anything that's in your browser, it can, it can just use.

• 12:11Greg Isenberg?

  And could it use like email? You know, let's say we wanted to send this to somebody, you know, finance team. Like can you, maybe we'll get into it later, but you know, things like connections and MCPs, um, is that possible?

• 12:28Speaker 01

  Yeah, yeah, totally. Okay. So let's like, let's make this like kind of a nice spreadsheet because we don't want to send like a badly formatted spreadsheet to our coworker.

• 12:36Speaker 01

  But let's make it nice and then uh, we can ask Quad to send it. And so here it's kind of cool. It's like, you know, it's, it's still early days. And so there's some like formatting mistakes. It didn't paste it exactly correctly. But it noticed it. So notice that, you know, it's not actually split correctly. And so now it's trying to format it.

• 12:53Speaker 01

  So kind of noticed this.

• 12:56Speaker 01

  And yeah, Greg, like to your point, it's funny, these like these use cases and the way that people are going to use these tools. Like I said at the start, it's going to be so surprising. I'm just so excited to see how people use it. And sort of the crazy thing about them is they're so general purpose. It's like, it's sort of like a computer itself, or like the internet or something like. Like you said, like when you first like had iPhone, like you would never have predicted that. You know, there would be an Uber app at some point, but you know, that's, that's what happened. And I sort of feel like we're at the beginning of that, but for, for agents.

• 13:27Greg Isenberg?

  Yeah, I think. It, it's, it sounds so obvious in hindsight, like, of course you have a phone with GPS. Of course, right? You're gonna, you're gonna have things like Uber and DoorDash and stuff like that. But. I feel like, yes, you're right. I think like what I'm trying to figure out in my mind, like I'm watching this and I'm like, this is really cool. But I'm thinking about like, okay. You know? How do I audit like my entire company? Like, what are all the tasks that the company is doing? How are they interacting with files? And how are they using the internet? And how are they sending things? And then what are opportunities I can use to like, make my team and also my life more productive? That's what's going through my head right now.

• 14:12Speaker 01

  Yeah, yeah, totally. That's a great way to think about it. And by the way, something that's kind of cool is, you know, as this is running, I'm just going to make a new task and do something else.

• 14:22Speaker 01

  So, you know, what are?

• 14:25Speaker 01

  Some cool episodes. Start up.

• 14:38Speaker 01

  Cool. And so while this one's running, we can like, we can let this one go too. And I often have a bunch of tasks running in parallel too.

• 14:46Speaker 01

  But yeah, that's exactly it. It's like you should just think about like, what's all like the tedious stuff that you do every day? And you can just throw all this stuff to cowork. And I feel like this happened for coding over the last year because of course, engineers and you know, programmers are the earliest adopters. So when the tooling first became able to do that kind of work, engineers adopted it first. But you know, now, now this is coming. Now this is possible for everyone else to use too. So that's like, that's super exciting. And when we talk to engineers about the way they like to use Quad Code, you know, they run a bunch of quads in parallel, they use it to automate the tedious stuff. And I don't know, man, like for me, this is just the most fun I've ever had as an engineer. Because I get to do

• 15:27Speaker 01

  the stuff that I enjoy, and I just feel so productive. Because Quad does all the, you know, the stuff that I didn't want to do.

• 15:35Speaker 01

  Okay, so now we have this like, we have the spreadsheet. This looks all right. It's not too bad. The data looks correct.

• 15:43Speaker 01

  You know, one thing that's missing though is,

• 15:48Speaker 01

  well, we can add maybe like the totals, but I think for the sake of the demo, what I'm gonna do is, I'm gonna see if it can email it.

• 15:56Greg Isenberg?

  So just reading for audio to listeners, can you open Gmail and send the sheet to Amy? And

• 16:04Greg Isenberg?

  wow.

• 16:05Speaker 01

  Yeah, so I'm gonna say always continue.

• 16:09Greg Isenberg?

  So how is it gonna know it's Amy, right? It's gonna pull up the contacts within Gmail?

• 16:16Speaker 01

  Yeah, yeah, exactly.

• 16:19Speaker 01

  Yeah, that's exactly it. It's gonna interact with it the same way that, you know, anyone else would interact with a computer. And it's the same thing. It can, it can like click stuff, it can read the screen.

• 16:31Greg Isenberg?

  Okay, so compose window open, let me type Amy. So you have like multiple, when you're, when you're like locked in, so to speak, you're kind of, you have multiple of these windows open at, or multiple, multiple virtual machines open at, at the same time?

• 16:45Speaker 01

  Yeah, yeah, I usually have a bunch of these, you know, like five or five or 10 or whatever. And so we can see the models, you know, trying to interact with this. And so it filled out Amy.

• 16:57Greg Isenberg?

  And you know, by the way, just because this is, you know, going on YouTube, you know, you're going to have some haters in the comments. So we're just going to address them right now. Someone in the comments is going to be like, but that's so slow. I can do it faster myself or something. What is your reaction?

• 17:12Speaker 01

  Of course you can. Yeah. I could definitely do this much faster. And it's actually the same thing for a lot of quad code, right? Like especially at the beginning, I could do it much faster. But, but I think sort of two things happen. One is that the model just gets better at doing it quickly. And this is just something you would, I would expect over time. But then the second thing is because you can do multiple things in parallel. It's actually a big time saver. And so usually my workflow is I'll kick off, you know, like a few different tasks in parallel. And I'll just kind of like go back and forth between them and kind of tend to my quads. Make sure they're in a good place, see if they have any questions or anything like that. So it's really a different kind of workflow.

• 17:51Speaker 01

  Like, I feel like now is the age of like, kind of multi, multi clotting of, of parallelism of like, not going super deep on stuff. But kind of being more of a generalist and more tending, tending to your quads. And so this was this other chat that we kicked off earlier. And in this case, it sort of did some research. So that's pretty cool. So it didn't just go to, you know, like startup ideas podcast website, but it searched the internet, checked a bunch of different places. Checked like someone's notes about it. Yeah. 10, 10 rules for, for quad code. Yeah. I'll find that interesting too.

• 18:29Speaker 01

  And let's see, so it seems like this is, the email is probably all drafted.

• 18:36Speaker 01

  The draft has been saved.

• 18:39Speaker 01

  Please send.

• 18:41Speaker 01

  And I also use this for Slack too, like a pretty common use case I've been doing maybe a couple of times a week. Is I have a spreadsheet where we track all the team's work for the month or for the week or whatever. And instead of having to bug everyone on the team to fill out the status. What I do is I ask cowork to look at the spreadsheet, any column that's not filled out, just message the engineer on Slack. And it does that really well. So, you know, I just ask it to do that. And then I go get a coffee and I don't have to do that anymore.

• 19:10Greg Isenberg?

  Do you think that cowork is going to be the gateway drug to Claude code? Cause for a lot of beginners, non-technical people, Claude code feels a bit overwhelming. But when I'm, when I'm watching you do this, this feels, you know, approachable.

• 19:25Speaker 01

  Yeah, I mean, I think it's like probably two kinds of users. And it's also, it's funny, Claude code is built originally in a terminal. And you know, nowadays it's available in the Claude mobile app, it's available on the website. In the IDE, on Slack, on GitHub. So, you know, nowadays it's available everywhere, but originally it's built in a terminal. And I never thought that most engineers would want to use a terminal. Cause you know, it's scary. It's like this thing that's sort of hidden away on the computer, like, you know, only the most hardcore engineers want to actually work in a terminal day in and day out. And so it's surprising to me that most engineers wanted to use it. What's even more surprising is a lot of non-engineers started to use it, and that was the craziest thing.

• 20:06Speaker 01

  And, you know, looking at like the sales team at Anthropic, like the GTM team, half of them use Claude code every week. And looking at other non-technical people at Anthropic, like designers, product managers, data scientists, pretty much all of them use Claude code every day. So that's been like pretty surprising. But my hypothesis is what they would prefer is actually something a little bit more like this. Where you don't have to deal with a terminal and all that kind of thing. You have a, you have a nice UI. Because you don't need access to Bash and all that kind of stuff, because the model will just do it for you.

• 20:39Greg Isenberg?

  Yeah, I think what I would love with something like this is. You know, automating some of these processes. It's like, instead of doing one offs, it's like anytime this happens, I want you to do this.

• 20:51Speaker 01

  Hmm.

• 20:52Greg Isenberg?

  That's my dream.

• 20:54Speaker 01

  Yeah, it's a cool idea. I'm excited to see like how it's tied into skills also. I think it's something where we're thinking about. We haven't quite figured out yet.

• 21:03Speaker 01

  Yeah, because like a skill, what is it? It's essentially kind of a repeatable way to do something. And so you saw that a little bit earlier up in this conversation. Where when Quad was generating this spreadsheet, I don't know if you saw, but it actually loaded the skill. And so we prepackaged the skill for Excel, and that's the way that Quad knows how to do it.

• 21:23Speaker 01

  And so if you have some like weird file format, I don't know if you work with like AutoCAD, or if you work with, you know, like Salesforce, whatever it is, the tool, the tool that you use, you just make a skill and then Quad can do it for you.

• 21:35Greg Isenberg?

  That's interesting. So if you have more skills, cowork, and you're asking it, you know, to do things related to those skills, cowork is more likely to use those skills. So you might be able to get a better outcome out of cowork if you, you know, do some upfront work to actually create some skills.

• 21:57Speaker 01

  I think so. Yeah.

• 22:00Greg Isenberg?

  Wow.

• 22:01Speaker 01

  Yeah, I think I think that's exactly right.

• 22:03Greg Isenberg?

  Yeah. Okay. Well, that's good to know. And, and, you know, what else do we need to know about cowork? Because I know there's, you know, there's, you know, extensions, there's, there's skills, like walk us through some of, is there anything else that, you know, we need to know in order to get the most out of, of the product?

• 22:23Speaker 01

  You know, we tried to build cowork just to be pretty simple. When we think about the different audiences we serve, for an audience like engineers, they don't actually like simple, like simple is good by default, but engineers love to hack their tools. They love to customize their tools.

• 22:38Speaker 01

  So that's actually really important. So Quad Code is just like the most customizable coding agent. It has just like so many extension points. There's like, there's skills, there's custom agents, there's hooks. There's an insane amount of configuration and settings that you can set, you know, there's a very sophisticated permission system. So there's all sorts of ways to customize it. And this is because we know every engineer works different and everyone has different preferences. Everyone uses a different tech stack. Everyone uses a different editor. Everyone uses a different OS. So we wanted to make sure it's really customizable. For some of my cowork, I think we're kind of starting in the opposite direction. And just keep it really simple at the start. And so if you use cowork, I would probably not customize too much.

• 23:19Speaker 01

  Like if you have cowork installed and you install the Chrome extension, that's pretty much all you need. And it'll do everything else for you. I think over time, as you find yourself using maybe software that cowork is not great at, like that's the point to think about writing skills. But that wouldn't be my starting point. Just start simple, like, you know, see how it works, see what's useful. And I think also the other thing, you know, it's just, it's so early. This feels to me a lot like Quad Code a year ago. Where, you know, we released it before it was early. It was not very good yet. It was like super buggy. It kind of barely worked. Like the model was not very good at coding a year ago. And it kind of feels like that to me.

• 24:00Speaker 01

  But I think cowork is actually a little bit better than Quad Code was when we first released it, because it's actually useful. And, you know, it's already a thing that I use every day. And yeah, I think in the first week, we've, we've seen so much more growth. It's, it's been like a multiple of the growth that we saw with Quad Code the first week. So that that's very exciting. It seems like this is something that people are already finding useful.

• 24:22Greg Isenberg?

  You know, we're recording this, what is it, January 2026? If we, if we come back here in 12 months, it's January 2027. How do you think people are going to be using cowork, you know? I know you don't have a crystal ball exactly, but what sort of use cases? And what is, what does the product look like? Like, describe the world in January 2027 with, with cowork.

• 24:47Speaker 01

  Oh geez, Greg, I, I plan in like a one week timeline. The model is just changing so fast. It's, it's so hard. And I just feel like, you know, like the model is, it's advancing exponentially. And just like my puny, human meat brain, like can't grapple with the exponential. It's like we think in linears. And so I think this kind of exponential is just very, very difficult to plan around.

• 25:10Speaker 01

  Okay, but if I had to speculate,

• 25:14Speaker 01

  a year ago, I made, and I think Dario also made this prediction, that by the end of the year, people wouldn't be writing code anymore. And I think that was like sometime mid, you know, last year or something. In, you know, I code every day. I ship, you know, 200, 300 PRs every month, something like that. And in the last two months, Quad Code has written 100% of my code. I haven't written a single line by hand. And this is something like, I also predicted this, you know, like way back middle of last year. It was sort of not intuitive. Because if you just think about kind of the experience at the time, and you trace it linearly, there's just no way that the model would be at that point. So you really have to kind of believe in exponential.

• 25:59Speaker 01

  And just literally like plot it out and kind of follow the way that the line, the line goes. That's the only way that you would have predicted this. And it was just, it was absolutely right. And so I think for coding, this is a work, this is something that we're going to start to see in more and more places for more and more kinds of code. That the model is able to just do all of it. And when we think about cowork, I think it's somewhat similar. I think it's a little bit earlier. And I think what we're going to see is for all this kind of tedious tasks, like, you know, like connecting app A and B, or kind of shuffling data back and forth, or whatever, the model is just going to be able to do it. And it's going to get increasingly good at it. This is, I think in some ways, it's a little scary. And in some ways, I think it's really exciting because you don't have to spend your time on this toilsome work anymore.

• 26:44Speaker 01

  You can just focus on the work that you enjoy. And also, everyone, I think, just becomes much, much more productive. Because you have an army of clods that can do this.

• 26:54Greg Isenberg?

  Okay, I like that feature. I like that feature a lot. It's a hard question. It's a hard question. When you, it's sort of like the genie is out of the bottle, and it's hard to predict like where the genie is going to go. So I believe that cowork is the gateway drug to Claude code. I think that people are going to start using it. And they're going to develop like vertical use cases, like for whatever it is their businesses, like you mentioned AutoCAD. Like you probably weren't thinking about AutoCAD when you were helping develop cowork. So I think there's going to be like these verticals. And I think

• 27:36Greg Isenberg?

  I think that cowork is going to be similar to like vertical job boards, where there's very specific roles that you can hire to people. And I do think that there's going to be this

• 27:47Greg Isenberg?

  combination between skills and these like digital teammates that you're gonna quote unquote, hire.

• 27:53Speaker 01

  Yeah, that's that's super interesting. Maybe we should make a bet and just see where it pans out in a year. You know, I have no idea. But it's definitely interesting to speculate because I just feel like the way this technology goes is so different than past technology waves. It's sort of similar to the internet. It's sort of similar to computers. You know, like maybe like telephones or something before that, but the speed is just so much faster. And because it's kind of piggybacking on all of this, like the internet could not exist without telephones, telephones and kind of like phone lines being everywhere. You couldn't have dial up without it. You know, mobile phones couldn't exist without the internet existing.

• 28:29Speaker 01

  So it's sort of like every layer of the stack, it just gets more and more powerful and it spreads more quickly. And so it's like on the back of all of this that AI can exist. And yeah, it's just gonna be very exciting to see to see where it goes.

• 28:42Greg Isenberg?

  I want to shift gears just for the last 10 minutes. Because we mentioned Claude Code. You had a you had a post that went absolutely viral. I think you know what post I'm going to talk about 99,000 bookmarks, which is crazy. And I'm going to share my screen. I want to go over it a little bit.

• 29:02Speaker 01

  This is me learning to use Twitter. I think I made an account like a decade ago and I haven't really used it, so.

• 29:09Greg Isenberg?

  It's funny.

• 29:09Speaker 01

  Yeah, it's been fun to learn.

• 29:11Greg Isenberg?

  You have like just a few tweets, but like this, you know, this one, you figured it out. You say, I'm Boris, I created Claude Code. Lots of people have asked for how I use Claude Code. So I want to show off my setup a bit. My setup might be surprisingly vanilla. Claude Code works great out of the box, so I personally don't customize it much. There's not no one correct. There's no one correct way to use Claude Code. We intentionally built it in a way that you can use it, customize it and hack it however you'd like. Each person on the Claude Code team use it very differently. So here it goes. Could you just talk about? Some of the, just expand on some of these and what you were saying, you know, what you were saying on here, because I thought it was really interesting.

• 29:53Speaker 01

  Yeah, I'd love to. So this first one, it's very similar to what I was showing in CoWork, where my job now isn't to go super deep on one task, it's to do a bunch of tasks in parallel. And so, you know, in the, when I'm working on Quad Code, I usually work in a terminal or on the mobile app. These are kind of the two services I use the most. But like I said, everyone on the team is different. Every user prefers something different. So we build all of these. And so usually what I do is I'll sort of task in kind of one tab. And once Quad is thinking about it and starting to work on a plan, I'll move on to the second tab and I'll ask it to make a plan for the second thing. Then I'll move on to the third one, ask it to make a plan. And then finally, like when, you know, I've run out of immediate tasks to do, I'll go back to the first tab. I'll see if the plan looks good.

• 30:38Speaker 01

  I might go back and forth a little bit. And then, once the plan looks good, I usually go into just auto-accept edits right away. Because I think with Opus 4.5, once the plan is good, the model can just execute it pretty much perfectly. This is definitely not the case with previous models. And so I think there was a lot of excitement about Opus 4.5 in, you know, over the last couple of months. And I think this is kind of one of the big reasons. It's just gotten very good at coding, but also excellent at planning. So once the plan is good, the code is good. And so, yeah, my work now is just jumping between tabs, kind of tending to the quads, make sure they're unblocked, answering their questions. With CoWork, I think, I think it's actually quite similar now.

• 31:17Greg Isenberg?

  I like that. I'm gonna, I'm gonna quote you on that. Once the plan is good, the code is good. Because that's so true, right? Because if you nail the plan, the code should, you know, the agents should do the work.

• 31:29Speaker 01

  Yeah, yeah, exactly. I think like sometime last year, there was all this buzz about spec-driven development.

• 31:35Greg Isenberg?

  Yeah.

• 31:35Speaker 01

  And, you know, it just feels like, it feels a little like too QT and like a little too rigid to me. But I think this is sort of a form of spec-driven development. It's like there, there is some kind of spec, you know, I think it's just like a plan. That's all it has to be. It's just a text file. It doesn't have to be in a particular format. Once you have that, you're good.

• 31:52Greg Isenberg?

  Number two, you say, "I also run five to 10 CLods in parallel with my local CLods. As I code in my terminal, I will often hand off local sessions to web using and/or manually kickoff sessions in Chrome, and sometimes I will teleport back and forth. I also start a few sessions from my phone, obviously, from Cloud iOS app, every morning and throughout the day, and check in on them later." What do you mean by that?

• 32:17Speaker 01

  This morning, I kicked off, I think, like, three CLods as soon as I woke up. I just had like some thought in the morning about, "Well, maybe I should like build this thing or fix this bug or whatever." I was like checking Twitter and someone had a bug report. So I just opened my phone and, you know, in the CLod app, on the left side, you click the little menu and there's a code tab. So you can just like access CLod code there. That's what I use for a lot of my code. And it's funny, I never would have guessed that this is the way that I code. If you asked me a year ago, I would never have predicted that the way I code now is like, probably half of it is just on my phone and it sort of just works.

• 32:53Speaker 01

  And then web is kind of the other part. So once I've run out of tabs, because it's just like, you know, it's kind of a pain to manage a bunch of different Git checkouts. Because in each tab in my terminal, I actually have a totally separate Git checkout. And I don't really use work trees or anything like that. I just keep it pretty simple.

• 33:09Speaker 01

  And in web, if I just ran out of terminal tabs, I'll just start like overflowing to web and starting tasks there.

• 33:15Greg Isenberg?

  Beautiful. So yeah, I also, so recommending, use iOS, use web, open multiple, like that's what, that's, you'll get the most out of it that way.

• 33:27Speaker 01

  Yeah, absolutely. Yeah. And we have an Android app now too. So yeah, just like use the mobile app and see how far that can take you. If it's not giving you good results, also make sure that you tune the environment setup and make sure that you invest in your CLod.md. That's super duper important. And I talk about that in number four also.

• 33:46Greg Isenberg?

  Number three, you say, "I use Opus 4.5 with Thinking for Everything. It's the best coding model I've ever used. And even though it's bigger and slower than Sonnet, since you have to steer it less and it's better at tool use, it's almost always faster than using a smaller model in the end."

• 34:03Speaker 01

  And cheaper. It's sort of counterintuitive and I had to explain this to people a few times. But because the model is smarter, it actually uses less tokens in the end. And it uses so many less tokens, it's often cheaper than using a smaller, less intelligent model, even though the per-token cost for that model is lower. So a little counterintuitive, but yeah, just use the smartest thing if you can.

• 34:29Greg Isenberg?

  Well, we appreciate that, you know? We appreciate that.

• 34:33Greg Isenberg?

  Number four, "Our team shares a single Claude MD for the Claude code repo. We check it in to Git. The whole team contributes multiple times a week. Anytime we see Claude do something incorrectly, we add it to the MD, so Claude knows not to do it next time. Other teams maintain their own Claude MDs. It is each team's job to keep theirs up to date."

• 34:55Speaker 01

  And the Claude MD is just a text file. So there's no special format. People ask this all the time. Is there some special format that it has to be in? No, it's just like, it's just a text file. So you can put whatever you want in it. This is a screenshot of our Claude MD. This is literally it. So just really simple. And you know, you could format this kind of however you want.

• 35:13Greg Isenberg?

  Love it. And then finally, I think, yeah, number five. Oh no, you have a, you've got a few more, so.

• 35:21Greg Isenberg?

  Number five, "During code review, I'll often tag @dotclaud on my coworkers' PRs to add something to the Claude MD as part of the PR. We use the Claude code GitHub action for this. It's our version of Dan Chipper's compounding engineering." What do you mean? What is compound engineering?

• 35:39Speaker 01

  Yeah, oh my God. So there's actually like two bugs in this tweet. I think, I think Dan actually calls it compound engineering, not compounding engineering. And then the @dotclaud, this is me wording how to use X. But it's actually @claud, there's, there's no dot. I just didn't, I think there's like an actual user or something whose name is Claude. I didn't want to tag them. But yeah, so what you do is in Claude code, you run this slash command slash install GitHub action. And what this does is it installs the Claude app in your GitHub repo. And what that lets you do is you can then at mention Claude whenever you want and just have it make changes. And it can just work on PR. So it'll push back to your branch and it'll push the changes right back. You can also tag it on issues. You can tag it kind of wherever.

• 36:23Speaker 01

  I do this multiple times a day. It's really, really useful. I think one of the most common use cases is just like little fixes. I think the other one is updating the quad MD to keep the knowledge base up to date. And you know, you should never have to comment about something twice. Back when I was at Meta, something that I did is, this is like in a previous life, in a previous job, something that I did is every code review that I did, I would keep a spreadsheet of all the issues that came up. And whenever the same kind of issue came up again, I would just like tally it up in the spreadsheet. And whenever something hit, I think like five or 10 tallies or something, I would write a lint rule. And what that is, is it's a way to automate that part of the code review. So I don't have to comment about

• 37:06Speaker 01

  it again. And that was back in the days before LMS and before the model was any good at coding. And so this is the equivalent nowadays. You just tag Claude and you have it update your quad MD, which is your team's knowledge base. So really simple. And what this means is you don't have to point anything out twice. I'm curious to see what this looks like for cowork. I don't think we figured that out yet. But definitely for Claude code, quad MD is kind of the, this is the one, the one thing that you should all be updating all the time.

• 37:34Greg Isenberg?

  Love it. Number six, most sessions start in plan mode. If my goal is to write a pull request, I will use plan mode, go back and forth with Claude until I like its plan. From there, I switch into auto accept edit edits mode and Claude can usually one shot it. A good plan is really important.

• 37:53Speaker 01

  Yeah, like I said, planning is just the most underused feature in Claude code. Actually, a lot of people use it, but I would say still underused. I use it for almost all my sessions.

• 38:04Greg Isenberg?

  Yeah, it's, it's a no brainer. So if you aren't already doing this, please do. Do we've got, you know, we're not going to have time to do all of them. What are the, I don't think, because you have a hard stop. Do you want to pick one or two to end with?

• 38:24Speaker 01

  Yeah, let's do, um, let's do maybe number 13. Yeah, number 13, I think this is probably in addition to using Opus 4. When people ask about how to get better performance out of Quadcode, there's three things that I recommend almost every time. Number one is use Opus 4.5 with thinking always. Don't try to use a different model because Opus will just give you better results and more efficiency overall. The second thing is make sure you have a good QuadMD. And then the third thing is this, this tip number 13, which is give Quad a way to verify its output. And so we, we just kind of saw with CoWork how good Quad is at using the Chrome extension in order to write email and in order to work with Sheets. And it's exactly the same thing.

• 39:07Speaker 01

  If I'm building an app, I always use the Chrome extension to have Quad test its own work. And if Quad can verify its own output, the result is going to be way, way better. And it's sort of like, um, you know, imagine that you're a painter and you're, you know, you make paintings and they have to be like pretty good. They have to be maybe even like photorealistic or something. Um, or just like, you know, some kind of like very detailed, uh, style. And, uh, you, you're, you have to wear a blindfold. You're just not going to be that good. It's not going to come out that great. Whereas the same thing for an engineer, like if you have to write code, but, uh, you can never run the code or you can never see the output and you can never see the website. It's just not going to be good. And so it's the same thing with Quad. As the model gets more intelligent, that first shot is going to get better and better.

• 39:51Speaker 01

  But really you want to give it a way to verify the output and it'll be much better. So this is like running tests if you're an engineer, uh, starting a server. Also, if you're an engineer or, you know, seeing, seeing the output in a simulator or in a browser.

• 40:06Greg Isenberg?

  Amazing. And the ultimate tip, I guess, is just get your hands dirty, right?

• 40:11Speaker 01

  Yeah, that's it. Yeah. I mean, there's no right, there's no one right way to use the stuff. Like, you know, see, see what's useful, see what's not, find your own workflows. It's sort of, uh, I, I heard someone describing Quadcode as like a find your own path book. You know, like one of those books where you have to like, do you do, do you go to the dungeon? Or do you explore the forest? Like this kind of thing, or, or like, uh, like an old, like RPG video game. It's just kind of like that. It's like, it's very free form. There's no one right way to do it. So just see what works for you.

• 40:39Greg Isenberg?

  Boris, I appreciate you taking the time, the generosity to spill the sauce and just to, to share with us how we can get the most out of both. Cowork and Claude Code. Everyone's thinking about it and everyone's trying to, especially on this podcast, you know, the Startup Ideas Podcast, you have millions of people who are trying to figure out how I can be more productive and how I can build businesses around some of these things. So, thank you. Thank you for the time. I'll include links on where to follow Boris. He doesn't tweet a lot, but when he tweets, it's worth paying attention to. And I just have, I want to leave with one thing, just because my audience would kill me if I didn't ask this. So, as you know Boris, I'm from French Canada,

• 41:21Greg Isenberg?

  and we speak French, obviously, in French Canada, and I call Claude Claude. Am I the only one?

• 41:33Speaker 01

  Man, you're probably not the only one. A lot of the world speaks French. Which one sounds better? What feels right to you?

• 41:40Greg Isenberg?

  I mean, to me, Claude sounds better. It's like Jean Claude Van Damme, even though people would say Jean Claude Van Damme. It's like, that's my take. That's my hot take. To me, it sounds better.

• 41:53Speaker 01

  You know, Greg, I'm gonna, today around the office, I'm just gonna call it Claude, and we'll see what people will say. I'll report back.

• 41:59Greg Isenberg?

  Okay, report back. All right. Sounds good. Boris, thanks again for coming on, and I'll see you next time.

• 42:05Speaker 01

  Yeah, thanks so much, Greg.