guys want more on that, I'll include the cloud. md below so you guys have everything that you need. Okay, so we've talked a lot about using Claude Code to build cool software apps and stuff like that. The last thing I wanna talk about is basically just automating or significantly streamlining the process of deploying things
Поиск по транскрипциям
hoping they would add some more features over the last couple weeks, like by having sub agents or some of the other features that are available in Claude Code, because I think I'd rather see faster models and just more features at this stage instead. But I will actually be trying out GPT-5 Codex mini more over
possible thing and then work up to a more complex solution. And you know, that's first trying single shotting things or trying, you know, single shot prompt to Claude Code SDK, which is now just sort of such a simple, easy thing to use. And then I think only as needed adding layers
this meta diagram here that explains the workflow. It took me two or three iterations to get to this point. This is the original diagram that the skill with claude code produced for me, which it still looks pretty good, but you can see there are a couple of imperfections here. Like I feel like the arrows look a little
press `control B` and then all five of them have moved to background right now. And this basically means that you can continue chatting with Claude Code whilst things are still running in the background. They added a slash `remote-env` command
some example configuration for the sandbox as well. And there's some more information and diagrams on how it works. And this is exactly what the web version of Claude Code is running and now we can enable
when I find that Claude Code has made a mistake or it just kind of went down the wrong track, but the conversation up until that mistake was still really good. Instead of arguing with it and saying, "No, go back to the previous thing. You should not have done that. " I just rewind to the earlier part
have your business model in the middle and then you wrap an AIOS around it. And right now these things are being built with a tool called Claude Code which despite the name does not actually require you to be a coder just so you know. And this is not a chatbot that you open in some browser
aents to perform tens or even hundreds of thousands of tokens of research across our codebase or the web and then just giving the needed summary to our main claude code context window. So instead of loading in tens of thousands of tokens of research into our main context window, it is now only something like 500 tokens
never heard of that will help you whip your AI agents into shape and build highly effective slot pipelines. It is March 12th, 2026 and you're watching the code report. In the past, if you were an indie full stack developer, it meant you had to have skills on the front end, backend. You had to understand DevOps, security...startup, like a front-end developer, back-end developer, security engineer, a growth hacker, Twitter engager, and many others. You can easily combine all these agents together in claude code, which can more efficiently help you go from zero to an actual product without needing to directly implement every personality and skill. That's cool, but when you put these
This right here is my Claude Code executive assistant. Let me show you a few things that it can do. Okay, so I'm going to start off by saying pretend that it's morning because it's not right now and use the morning coffee skill to help me plan my day. So, I'm going to shoot that...open up a new tab and I'm going to shoot off this message that says, "Spin up a sub agent to do research on the new Cloud Code voice feature and then create both a LinkedIn post and a Twitter style carousel for me. " It's created a to-do list and it's getting going on that
overall, I think Claude Code did a pretty good job, but it did have some mishaps like the version name and adding it a string and ignoring the fact that it's meant to be wrapped in a gesture root handler. And it seems that Gemini CLI is still going around in circles ever since it switched to the flash
tasks as possible. And so long story short, the main difference I'm talking about here is not using open claw or open floor. We are using clawed code. And if that sounds scary, stick with me because yes, this may sound like a dev tool, but it is actually the most powerful AI assistant and productivity machine that...breaking down why you must make the switch. Now, I'm going to do a side-by-side comparison of all the things you love about this and how Claude Code beats it in every realm. And at the end of the video, I'm going to be explaining what it actually takes to get started on building the system
since uh Devon has really improved over the past couple months and claude code came out I have dropped my cursor usage by like 70% or so. I still start fresh projects in cursor. sometimes things that I just want to explore or build myself or have an opinionated view on how to build. But I would say seven
want to add something to the end of the system prompt for that session, then you can do append-system-prompt instead. And it seems that Claude Code will also be integrated
that's the codeex app. Parallel agents, reusable skills, scheduled automations, and git built right in. And it is going head-to-head with clawed code. Is it better across the board? Not yet. But in the areas that matter most for automation and parallel workflows is ahead and it's moving fast. If you want to take tools like...That's it for today. If this helped, hit that like button, share it with someone who cares about AI tools, and drop a comment. Would you switch from Claude Code to the Codeex app? Let me know below. AI is moving fast, really fast, and you need to stay ahead of the curve so that you don't lose
checked it out already, this is inside the profit boardroom. So if you want to get the notes from today and all of my best trainings for using claude code. You can get that inside the AI profit boardroom available at aiprofitboarding. com. Inside the community, you can ask any questions you have. You can get help and support whenever...your regular plan usage. This charges extra usage. " Okay. Let's have a look here. How do we get access to extra usage? So, we got current session. Claude extra usage. Navigate to settings usage. Locate the extra usage section. I can't see it. Unless it means that one and then we've used extra there. Maybe that
Sporter says, "I'm late. Using claw code is more robust than using Opus inside anti-gravity. " Yeah, for sure. You can do a whole lot more with claw code than you can do with the API. Bear in mind, like if you're using the API inside anti-gravity, the one that's built in, you will have limits...rinse it, right? You're going to hit limits and then it's going to restrict you on what you can do. Can you ask Claude code to use Google design principles? I'm pretty sure you could, Gregory, if you wanted to. Antoine says, "A cheeky bit of notebook LM. " That's what we're talking about
both these podcasts, which they are great, and you really get into what Boris is saying, I can get behind it. But when you take this at face value, coding is largely solved. It's a very exaggerated claim that a lot of people are misinterpreting, thinking that software engineering is dying and that he's saying the same thing...what to build next. Engineering is changing and great engineers are more important than ever. " And so looking at this right now and Boris, he's the creator of Claude Code. So Daario is his CEO saying something that seems very contradictory. Software engineering is going to go extinct in 2026. Software engineering is more important than ever
thing, agent teams. This one blew my mind. Claude Code can now run multiple agents at the same time. They work in parallel. They coordinate with each other. Imagine you're automating your entire content workflow. One agent writes the blog post. Another agent creates the social media posts. Another agent designs the email newsletter all at the same time