Claude Code for Web/Mobile just released and it’s INSANE (must watch)

Anthropic finally did it. They added the one feature everyone's been waiting for. The ability to use Claude Code wherever you are. Whether you're on mobile, on the go, in your browser, anywhere you are, you can now use Claude Code to build out your apps. And this changes everything. I cannot stress that enough. If you implement these new features into your workflow, you are going to produce 10 times as much code. I'm going to show you why Claude for web and mobile is so important. how it's going to make you a hundred times better than your competition and show you the perfect workflow for using these onthe-go agents. If you stick with me to the end, you're going to be a Claude for web and mobile master. Let's get into it. So, this was just released moments ago. You

can now use Claude code in both your web browser. So, I'm in Google Chrome right here as well as the Claude mobile app. So, I just have my iPhone simulator open here and it has the Claude app here. And what you're able to now do is connect to any of your GitHub repos. So anywhere your code lives and spin up AI agents on the go wherever you are to work on your codebase. This means you don't need to be sitting at your computer in your development environment anymore to build apps. You can be on your mobile phone at the movie theater. You can be at the ice cream parlor getting a chocolate ice cream cone. You can be anywhere spinning up AI agents to do work for you 24/7. This is going to increase your productivity tenfold. This is really amazing. Just to give you a quick example of how this works before I get into how to set it up in some really advanced workflows. Right now, I'm

working on this Poly Market scanning app. It just scans Poly Market 247 for big trades, insider trades, things like that. Say I was about to go to bed and I wanted to spin up an AI agent to add a light mode to this app to do this work while I'm sleeping. I can do that very easily. I would just pull open my phone right before I go to bed. I would choose my Poly Market GitHub repo, which I'll show you how to set up in a second, and I just say something like, "Please add the ability to switch to light mode on the home screen. " And I'd hit send on that. And this would spin up an AI agent on my phone that would then write this code to add a light mode to my website. And as you can see, it's completely crossplatform. So it showed up in my cloud code on web immediately. And this AI agent is now working on the cloud, working on my app, writing code, and when I wake up in the morning, the code will be fully done for me to review and ship to my app. Before when using claude code, you needed to be in your ID, right? sitting at your computer fully engaged looking at your monitor, sitting here writing prompts and wait for the agent to work. That is now torn out the window. You don't need to be sitting at your computer. You can be anywhere on the go having agents work for you 24/7. So, as you can see here in the cloud on anthropic servers, an AI agent is now going through my codebase and writing all the code. I can even enable notifications. This is awesome. So I can get a little beep when the agent's done working. So I'm going to actually enable that. That's awesome. And that gives you an idea of the power that's just been unlocked for you with this new functionality. Let's go into setting this up. Then I'll go into kind of an advanced workflow which is going to make it so you get apps out 10 times faster. So let's go into setup first. So

setup is super simple. I'll put the link down below for this. You just need to install the clawed GitHub app onto your GitHub. So for anyone who's newer to coding, hasn't done much of this before. If you haven't yet, sign up for GitHub. It's a repository where you store all your code on the internet, sign up for that. Any apps you're working on, just ask the agent to push your code to GitHub. It'll set that up for you. But all you need to do is go to the link I have in the description, install the Claude GitHub app, and now Claude has access to all your repositories and can write code for you on the go. The way this basically works is Claude is not writing code on your computer. It's writing code on the cloud and then storing it in your GitHub. Then you have the ability when you get back to your computer to pull that code down, review it, and commit it back to your main branch. Once you have that installed onto your GitHub, you're good to go. And you'll now have all your repos here listed in the cloud code for web. So you can start doing work on all of them if you want. So, let's talk about 10xing your productivity with Claude code for

web and mobile. There are basically two main workflows I think about when it comes to Claude for web and mobile. That is on the go. So, when I'm not at my computer or if I'm at my computer using Claude for web and mobile together with my development environment. And I'll go into what that means exactly in a second. And I'll also go over these main tips of getting the most out of these. But basically, there's two times you want to be using Cloud for web and mobile. one, when you're not near your computer, right? So, you're on the go, maybe you're at the gym, maybe you're picking up food and you think of ideas and you spin up agents. That's when you want to be on the mobile app for Claude Code. And by the way, this mobile app, this is just the Claude mobile app. So, you just go into Claude on your phone now and you can choose code and you can spin up these agents. So, you want to be using it on the go. You would just go in here, go into your app, and spin up agents. If you're on the go, the best functionality to have it build out is actually bigger tasks. The reason I like to spin up agents that do larger tasks for your app on the go is I'm not doing any work simultaneously with those agents cuz I'm not on my computer. So, I can give the agents the ability to do these bigger tasks and I'll be confident it's not overlapping with code I'm currently writing. The big issue when you typically multitask with AI agents is the AI agents could clash with each other. they can write code that conflicts. But if you're on the go, you're not writing any code. So you can give your agents bigger tasks to do because they're working on their own. You're not going to clash with anything they're building. So when I'm on the go, I like to do way bigger tasks. The other workflow is when you're at your computer and you're actually using Cloud Code in your development environment, whether that's inside Cursor or Visual Studio. Here you want to be thinking about this a little differently. Here is where I like to do smaller tasks. So let me show you this quick workflow. when I'm at my computer, I'm using Claude code in my development environment. So, I'm here in my Poly Market app. I'm building out my Poly Market scanner app that I just showed you a second ago and I want to work on some functionality here and I also want to improve my productivity by using those agents on web and mobile. So, here's how I think about that when working in the IDE. So, I use the Claude Code IDE plugin for Visual Studio, which is completely free. I go in here and I'm working on larger tasks. So because I'm handholding the agent inside the IDE, I want to work on larger, more complex tasks. And when I'm on web and mobile, I want to give it smaller tasks, smaller tasks that are separate from the bigger task I'm working on. The reason being when I spin up smaller tasks with the agent on web and mobile, I can be more confident they're not in conflict with my larger task. So let's spin up some smaller tasks and then I'll get to work

on my larger task and show you how I get all this code committed. So first thing I want to work on is redesigning these bet cards. So I show in my scanner the top large bets that just got placed on ply market so you can see maybe what bets people are super confident in. I want to redesign these. I want them to look a lot better. So let's go inside the clawed agent here and let's give it a prompt. Redesign the large bet cards on the home screen to be more visually appealing and stress the value of the bet more. So I want to be the biggest part so I can see how big the bets are. So, I'm going to hit send on that. And that is now going to spin up a brand new agent to actually be working on the app. And I'm going to enable notification so I can get a little ding when that agent's done working. So now that agent is spun up in the cloud and it's working on that task. But I'm not done yet. Here's how you really increase your productivity. So I'm going to spin up yet another agent to start working on here. So I'm going to say improve the styling of the trader profile. Maybe show an aggregate of their bets so we can see which markets they bet the most. So, I wanted to work on the styling of the better card. So, if you click on a better, you can see what trades they've placed, what kind of positions they're holding, their total volume. I want to add more stats and visuals here to see maybe what markets they bet the most. So, I'm going to go in, and this is completely separate from the last task I did. That's important here. You don't want to give overlaps to these agents because their code might conflict. So, this is a completely different component we're working on. I'm going to hit send on that. And now we have three AI agents working on different visual tasks inside our app. And now here's how we kick it up a notch. We have those three agents working on different tasks. Now we can go into our IDE and we can start working on our bigger task. So right now there's no sort of filtering or anything on the main polyarket dashboard here. I can't filter by certain bet size or certain traders or anything like that. This is a pretty big piece of functionality. So, I'm going to go into claude code in the IDE and I'm going to say let's add filters to the homepage. I want to be able to filter the large bets by bed

size, market, and anything else you can think of. And I'm going to hit send. Now, I'm working with my agent locally in my IDE to build out a bigger piece of functionality. The reason why I'm trusting it with a much bigger task is I'm working here with it, handholding it, approving things, watching how it works, asking it questions, answering questions it asks me. So, we can get a lot more complex with what it's doing. So, now let's take a look at what's going on here right now in the workflow. Before today, all you'd be able to do is just work on singular tasks inside the ID like this with clawed code. Now, after today, things are a lot different. We not are only working on functionality with an AI agent in our IDE but now we actually have three different agents working here. We have one working on my iPhone to build out a small piece of functionality. We have two others working on claw on web to build out certain pieces of functionality and all of this has handoff. All of this is crossplatform so that when these tasks are done, I can pull it down into my IDE and I can review the changes, combine the changes, and commit the code to GitHub. This just changed your AI coding workflow from one agent building out functionality to multiple agents building out functionality. And in a second, I'm going to show you how you can review and approve the changes those agents are doing. This is a really critical step you need to stick around for. And while this is working, by the way, if you learn anything so far, if you like AI coding, if you like cloud code, make sure to leave a like. It shows me that you want more content like this as well. And if you like all this AI coding content, all I do is make videos around it. So, make sure to subscribe and turn on notifications as well. So, I'm going to prove everything Claude Code is doing inside the IDE here as our agents work. as those agents are working on the code. We're going to review what they build in a second, but I want to go over a few more tips with

you. So, a few more things you want to know as you use Claude for web and mobile is one, you want to avoid overlap of functionality. So, you're going to be spinning up a bunch of agents that work on a whole bunch of tasks. You want to avoid overlap between what they're working on. So, when giving tasks to agents on web, mobile, on your ID, always think about what part of your app they're working on and try to keep it delineated. try to keep them separate so that the code doesn't conflict. Like as you can see, I worked on wow, you can already see the filters being built out here. I worked on functionality on the main site. I'm working section down below the main part header and then I'm also having an agent work on functionality on the trader view. Right? These are all completely separate functions that the agents are working on. If I had them working on the same thing, there'd be overlap and conflict, but we're avoiding that for now. Here's a really important one is building the muscle of constantly thinking of ideas and spinning up agents. What does that mean? This is a brand new workflow you're implementing, right? You've never in your entire life had the ability to open up your phone and give an AI agent a task to write code. That's never happened before. You now have that ability. So, you need to build this muscle in order to get the most value out of it. So, I like to do different exercises to build this muscle of coming up with ideas on the go. One exercise I love to do is have agents running every night. Before I go to bed, I like to think of three tasks I can give my AI agent to build out before I go to bed. So, here's the challenge to you if you're using Claude Code. Before you go to bed tonight, pull out your phone, go into the Claude app, and force yourself to spin up three AI agents to work on functionality. And what this is going to do is it will build the muscle in your head that comes up with ideas on the go. And what you'll start seeing is as you're at the gym, as you're at a restaurant, as you're going for a walk, ideas will come up. And you'll be able to go on your phone and spin up those agents to write code. And this is going to increase the amount of apps and functionality and code you come up with exponentially. And you'll find you'll get apps out so much quicker because you'll be thinking of new ways to create functionality in apps wherever you are. So before we go back into the results of those AI agents, I challenge you after this video to now think of ways as you're going out as you're doing whatever to come up with new apps, features, functionality to build so you can start building that ideation muscle. All right, looks like all of the agents are done working here. They've all notified me that the work is done. You can see what they're saying here. It looks like the change has been committed to the branch. So when the agents are done working and they write you code, they create a new branch that you can then review and pull down into your instance. Let me show you how this would work and how we would implement these changes that the agents have made. So

I'm looking here. All changes have been committed and pushed to this branch. I'm going to copy go back into our IDE. I'm going to say please pull down the code from then the branch the agent gave us. I'm going to hit enter. The agent will pull down the new code that other AI agent was doing for us. We just have our AI employees going out the wazoo here. I'm going to hit yes. It is going to fetch that code for us. It's going to merge it and we'll be able to test it in a second. All right, the code has been pulled down. Let's check out the app. And boom, you can see the new bigger cards. Poly market large bets. Now they're big cards where you can see the value. You can see the market. If I click on the market, it pulls it open inside Poly Market. That's really cool. It improved the visuals tremendously here. So, we can see the bigger bets in a lot nicer way. Right now that we pulled down the code from the agent, we would just commit it now. Okay, this looks great. Please commit the code. And now it will ship that code into our repository in GitHub in the main branch and be good to go. Then from here, all we do is go into the other agents, see which branch they committed their code, pull that down, and do the exact same process. Pull it down, test it, push it back to the main branch. This is the workflow that is going to 10x your productivity using clawed code. This is such an amazing feature. It is so important if you want to get ahead of your competition to start leveraging this immediately. Build the muscle in your head of okay, how can I use these agents? How do I come up with ideas for these agents? You want to be disappointed if there's ever a second in the day where you don't have AI agents doing work for you in cloud code. If you get into that mindset, I promise you will ship 1,000 times faster. Over the next few days, I'm going to launch a new video showing you an even deeper and more advanced workflow with these AI agents. I wanted to just cover from a high level in this video. So, make sure to subscribe down below so that you get notified the moment that video comes out. I'll also be live streaming over the next couple days showing you how to use this live. So, turn on notifications for that as well and stop by the live stream, say hello, ask questions. I can't wait to see you there. Hope this was helpful. Let me know down below how you'll be using the Claude Code agents and I'll see you in the next