How to Use Claude Code

A lot has changed in the AI coding world and a big question I'm getting is am I still using cloud code? The answer is yes. It is still the best AI coding tool in my experience even with all of the new things that have come out. It's only been about 2 months since my last update video, but enough has changed where I wanted to make a quick update video to show you guys some of the cool stuff that I've picked up since the last one. If you're new here, welcome to the video. My name is Chris and I build productivity apps. Today we're going to be going over updates and workflow improvements since my last one. My workflow has generally stayed the same since the last video and if you haven't seen it yet, definitely check that one out. But there are some really cool things that I've picked up that are making me even more productive that I wanted to share with you guys.

I'll start with a really quick easy one. It's using the word ultrathink in your prompts specifically for very hard tasks. So when you tell Cloud Code to do a task and you just say please ultra think at the end of it, it'll actually think longer and harder about the problem. I have noticed that when I use this, I do actually get better results. And I usually reserve it for tasks that I think it's not going to get or it's already failed at one or two times. It's such a simple trick and when I first heard about this, I actually didn't believe it was true, but then I double checked and Anthropic does have this in the documentation, so it is actually a thing. So, if you're stuck on something

complex, just try it out and maybe it'll be able to solve it. Now, this is a big one I don't see a lot of people using, and it's background tasks. At the time of recording, this is actually a very recent thing Cloud Code added, and it's the ability to run background tasks for you. And here's why this is a big deal, at least for me. Let's say you're running a backend server. You can now tell Cloud Code, hey, can you run the server in the background for me? And it's going to go ahead and do that. And now Cloud Code has live access to your server logs, which is really helpful if you're debugging a problem. For example, here's an example of what I was doing before this feature existed. So, let's say I was running the Ellie backend server. I would typically run the server in a separate terminal. Anytime there were errors or logs I wanted to share with Claude Code, I would have to copy and paste them into Cloud Code. And then I would have to repeat this process a few times as I'm debugging. But now I can just tell Cloud Code, can you run the server in the background? And you'll see this little indicator at the bottom that says one bash running, which means Cloud Code is running the server in the background for you and it has access to all the logs that are coming in. So if I'm asking it, hey, there's a problem with the server, it's actually just going to go ahead and check the logs itself. No more copy and pasting. This might seem small, but I'm usually copy and pasting errors like a 100 times a day. So, this is actually a pretty big deal for me. Honestly, kind of surprised that not a lot of people are using this, but if you're working with any kind of server backend or front end, this is a pretty big time saver. The next thing that I've been doing is using Claude Code as a research assistant, especially for planning complex features. Let's say that I need

to implement a feature with PDF extraction. Instead of spending an hour researching and trying to find the best way to do this, I can just ask Claude Code, do a web search, and find the current best methods for PDF OCR extraction, and create a detailed plan for me in a markdown file. So, it's actually going to do the research for me, compare different approaches, and show me a detailed plan. And it's not just Googling, it's synthesizing the information from multiple sources, and it's giving me actionable recommendations. And here's another tip, I'm also using Claude desktop to do this research. A lot of people are sleeping on Claude and don't know this, but if you have a Claude code subscription, you also have access to Claude desktop with research mode, too. When you ask it a question or research a technical topic, it will scan hundreds of sources, sometimes taking up to 20 minutes, but it does incredibly thorough technical research. So, sometimes instead of doing it in Claude Code directly, I'll even use Claude Desktop deep research. And then I paste the findings directly into Claude Code to go implement. And this combination is just incredibly powerful for tackling complex problems. If you're interesting in mastering cloud desktop for your own projects, then definitely check out this Claude AI guide that HubSpot put together. Personally, I'm using Claude Code Overhat GPT, and I'm surprised a lot of people aren't using it yet. It covers things like Claude projects, which I'm constantly using, especially for things like writing YouTube scripts, and it covers artifacts, which is really helpful when doing technical documentation. If you're building apps like me, you can use the artifacts feature to generate readme files, API documentation, or even architectural diagrams. My favorite section is the one titled projects, your AI powered task assistant. It gives you a great breakdown of the projects feature inside of Claude, which I'm so surprised I don't see a lot of people using. And I'm personally using it for all of my YouTube and Instagram scripts. So, definitely check out HubSpot's guide link in the description. And a huge shout out to HubSpot for sponsoring this

portion of the video. Let's talk about MCPs. In my previous video, I was not using MCP servers. To be honest, I didn't really understand how they worked, but since then, I have started using them. I won't try to explain it here, but the simplified version is MCP is a way for you to give cloud code access to tools. Okay, so why is that important? It's because there are a lot of tools or these MCP servers that are actually super useful. So I'll give you some examples of the ones that I'm currently using. The one I'm using for all projects is called Context 7MCP. It's a free MCP service that gives Cloud Code access to a ton of updated documentation. Let's say I'm working with Superbase, for example. Instead of having to go to Superbase, copy the documentation URL and pasting it into cloud code. Instead, what I can do is just tell it, make sure you're using the latest Superbase documentation, and it's going to automatically use the context 7 MCP server in this case. And now it has access to the latest API documentation. The other big thing I'm using MCPS for are database MCPS. For example, with the Superbase MCP, Cloud Code can actually read my database and make modifications to it. So if a user reports a bug, I can just ask cloud code, hey, can you go use Superbase MCP to get the latest data from user 1 2 3 4 and it's going to go pull the data for that user account for debugging. Here's a real example. Ellie user was saying that their tasks were not correctly rolling over to the next day. So I literally asked Cloud Code, this specific user is reporting that there's a bug with the task rollover feature. Can you help me debug it? and it connected to my database, found the relevant data from the user, identified that there was a corrupted time zone saved to the database, and then created a fix for it. Before MCP, I would have to go write a SQL command or go manually dig through my database and try to get that user's information, which I would paste into cloud code anyway. But now, Cloud Code can go do that all on its own. And it's not just Superbase. I'm also using the Firebase MCP, the Convex MCP. There's even one for AWS. Basically, every major service and data provider has some sort of MCP. I could do this manually, but using MCPs with

Claude Code make this 10 times faster. This next one is perfect for solo developers, and it's using Claude Code to review pull requests for you through its GitHub action feature. Every time you commit, Claude is going to review your code for bugs, security issues, and best practices. And as a solo developer without a team to review my code, this is actually huge. So, setting it up is super simple. You literally just type this command and Claude Code sets up the entire GitHub action for you. I will be honest though, about 50% of the comments are kind of just fluff and not relevant, but it has caught a lot of stuff that is worth adding. Like here, it noticed that there was actually a place where I was potentially exposing an API key if it was accidentally logged. And then here, it identified another place that I should take a look at because there might be some memory leaks going on. This is the kind of thing that could save you from hours of debugging in the future or worse, some sort of security breach. At least at the time of recording, it does come with your cloud code subscription anyway, so there's really no reason not to use it. If you're a beginner just getting started with this stuff, this is also a really good sanity check just to make sure that

you're handling at least the basics. Next one is one that I haven't directly mentioned, but a lot of people have noticed, and it's that I dictate everything into cloud code. I literally cannot remember the last time I physically typed something into cloud code. I thought everyone was doing this, so I didn't know if it was worth mentioning, but clearly this was new to a lot of people. And I'm actually using something called Whisper Flow. And a huge shout out to them for being a channel sponsor. And the reason I recommend doing dictation, especially with this tool, is because you get way more detailed prompts. It's just more natural to communicate with Claude Code by speaking. When you're explaining a bug to someone, would you rather type something out or just talk to them? Talking is just so much more natural and you end up giving way more context on the problem. And why I chose Whislow specifically is because it actually understands developer terminology really well. So when I say something like MongoDB or superbase, it gets it right every time. Plus, if you're using cursor or windsurf instead of cloud code, you can actually tag files just by dictating. So you can say, can we make a change to at@ sidebar.tsx? And it'll tag that file correctly. Last thing I'll mention, which is really cool, is Whisl has this snippet feature that they recently added. You can actually save snippets that you frequently type. For example, sometimes I like to run claude code where it auto accepts everything, which to be honest, I don't recommend people doing, but I do it in certain low-risk cases. So, I have the snippet where if I say run claude dangerously, it populates it with the real command for me directly in the terminal. And I'm actually primarily using this outside of coding too. So, whenever I'm sharing my calendar link or work email, I have snippets set up for these two. I'll

leave a link in the description if you want to check out Whisperflow. So, the next one is that Claude Code has the ability to set up custom agents. All you have to do is type in the / aagents command and then you have the option to define what your agent does. I'll also be honest here. I haven't been using this one as much as I thought I would, but I have one specific agent that I made that's really useful. So, it's an iOS specific agent and I basically gave it instructions. Always use the latest swift syntax. Make sure to use Context 7 to get the latest Apple documentation to keep in mind what iOS version the project targets and to follow specific iOS design patterns. So when I'm doing specific iOS tasks that I'm pretty sure Claude Code is going to get tripped on or use the wrong version of Swift, I can tell it, hey, make sure to use the iOS sub agent for this. And now it's actually going to go ahead and execute this task with that sub aent. So this is really helpful when I'm dealing with Swift UI animations or complex UI kit integrations where the regular Cloud Code might not have that specific iOS context. But aside from this, I have not really found the sub aents that useful. I think they're a little bit overhyped to be honest. But this is a really cool one. People have also made a security review agent, but a little bit before recording this video, Claude actually released a specific slash command for

the security review. That use case isn't as relevant anymore to be honest. The last thing I'll mention is a small fun quality of life improvement, and it's the ability to add custom status lines. And what this means is you can actually customize what appears below Claude codes input box. I'm personally keeping it pretty practical. So, I have the current Git branch and the time since my last commit. I'm using Git as my checkpoint system. And so, seeing this information at a glance is super helpful. So, when Claude is about to make big changes, I can quickly see, I haven't committed in 2 hours. Let me go save my progress first. Some people get creative with this. I've seen people add mini dashboards, system stats, and even little Tamagotchi ASKI art. But for me, the branch and the commit time is perfect. The way you set this up is you just type / status line, and then you tell Cloud Code what you want in plain English. So, I would say / status line,

current git branch, and then time of last commit. So, that's my two-month update with cloud code. These features, especially the background tasks, the MCP tools, and the voice dictation, have really leveled up my productivity. This stuff and Cloud Code are evolving so fast. So, I'm pretty sure in a few months I'll probably have another update video with whatever features they come out with next. If you're on the fence about trying Cloud Code, it is still the best AI coding tool on the market, at least at the time of recording the video. If you have any other workflow tips, please comment below. I'm always on the lookout for new ones. And if you found this video helpful, check out my Instagram and Tik Tok. I post almost every other day about building productivity apps. And obviously, if you like this content, don't forget to subscribe. But thank you guys so much for watching, and I'll see you guys in the next video.

I brought on one of the best vibe coders on the planet to teach you how to squeeze the most out of Claude Cursor and all these vibe coding tools. We're talking about which models to pick, how to use MCPs properly, the exact servers to run them on, and a hack that gets you 20% more output from cursor. There's even a single keyword that you can type that literally makes Claude code work harder. I I'd never heard of it. If you want to get the most out of vibe coding platforms, this is the closest thing to multiplying yourself. The full breakdown is inside this video. And there's just it's it's a lot of tangible tips and tricks how to get the most out of vibe coding. Chris, welcome back to the pod. By the end of this episode, what are people going to learn? Yeah, so I'm Well, first, thanks so much for having me, Greg. What I hope people learn is just what my AI coding workflow is because I know a lot of people are getting into AI and there's a thousand tools out there. There's a thousand different ways to do this and I want to show them what I'm using to build my apps. And then I want to also show some tips and tricks that I have that will probably help level up anyone who is doing AI coding. Correct me if I'm wrong, but you're doing thousands of dollars at MRR with your apps. You've you've got a portfolio of successful apps, some beautiful looking things. So, you're going to basically show us tips and tricks and your workflow so that people can copy it and and do a similar thing. Yeah. Yeah. Exactly. Yeah, that's what we're going to do. All right, let's get into it. Okay, cool. So, um, I'll just give a little bit of context, uh, for anyone who who doesn't know me. My name is Chris. I build productivity apps and then I document everything on YouTube. So, I teach people how to build apps and just show what it actually looks like behind the scenes of doing it myself. I have a bunch of different apps that I've built. And the reason I'm showing them, it's not to plug them. It's really to show that these are very substantial apps. Some of them, or most of them, people are always surprised when they hear that it's just me building them. And to be honest, this would not be physical poss physically possible for a single person to do if it wasn't for AI. So that is my secret to being able to build all of these things and just sustain all this stuff myself and is to leverage AI coding tools like cloud code and cursor like we're going to talk about to be able to do this. So this is a little bit of context here. Um I'll let's just jump into it.

there are two tools that I'm currently using. And again, I don't want this to be an episode to just kind of show how to use cursor, how to use cloud code or anything because there are so many better videos out there. And there's a bunch on my YouTube channel as well if you want to check them out. But I did just want to show what I'm doing and then some rapid fire quick tips so that you guys can maybe apply this stuff to your own coding workflow. But there are two tools that I'm currently using and it's claude code and cursor. And what's surprising to most people is I am actually using both at the same time. And so usually people are like I just have to choose one and then I got to stick with it. But what I found is they have different strengths and weaknesses and that's that's why I choose to use both. And I'll actually show you this is kind of the setup. So this is what it looks like for me. So I'm I have cursor open. So this is cursor and typically what I do is I have a terminal on the right. So typically the terminal I think is on the bottom and you can just drag it to the right and then I just run claude inside on the right here. So now claude is running and then if I want to use cursor and their AI agents I just have to change tabs and then now here I'm using cursor. So I am frequently switching between both cloud code and cursor all the time uh for different purposes and we'll get into why that is. This is how I'm setting it up. And this is actually also how I do the iOS projects as well because a lot of people are always asking how are you doing this with Xcode because I am using Xcode to do the iOS projects. What I'm doing is I'm just opening the folder and the files in cursor. And now when I make changes here, it'll automatically reflect in Xcode and then I can run the app and everything. So this is the current these are the current two tools that I'm using. It's cloud code and cursor.

Um, in terms of the actual strengths and weaknesses of these, this is this is why I'm using it. So, Claude Code is extremely good. Um, I'm actually using this model called Opus 4.1. This is my favorite model. It's probably the most powerful model, the best model there is for coding, but it is super limited. Um, they changed their pricing since Cloud Code came out. It used to be unlimited usage. Now it's very limited to the point where I probably can exhaust the opus limit for the week in maybe three or four hours maybe less actually. So I try to use it very sparingly only for very very complex problems. So for very complex problems I'm using clawed code with opus and then but if I'm not allowed to use it because I've exhausted the limit what I'm doing for very complex problems is I'm using cursor specifically with plan mode. And I'm using and this is what plan mode looks like. You can choose between agent mode and plan mode and cursor. Plan mode just means that it's going to actually plan out its steps and thinking and you'll approve it. And here's the hot take I'm going to have here. I am using GPT 5.1 high for plan mode and typically I'm seeing people using sonnet or they're using even GPT5 codecs but for some weird reason and this is a tip I got from a developer friend of mine he was like you need to try GPT5 uh.1 high with planning it's just for some reason so good my hypothesis is that it was not technically built for coding but it's really good for writing and when you're doing planning and doing a lot of critical thinking and you're trying to plan out steps, maybe a writing model is actually better than a coding model at doing that. And then for the execution, when I'm done planning, I do use sonnet 4.7, I think. So I use a sonnet model to actually execute. So that's the configuration that I have running right now. It's I use cursor plan mode. That's the important mod. It has to be plan mode with GBT 5.1 high for the execution. And then if if it can't get it, I use claude 4.1 opus, which again I don't have much of that, so I try not to do it. And then I just switch between claude code sonnet 4.7, so not opus model, and then cursor plant mode. I just switch between them depending on which depending on the task.

And then the reason here here's when I would use which one as well. So if you're using if you're doing something very very complex like really complex like it's a bug I actually think claude for uh claw I actually think cursor with plan mode is better. If you're doing something massive like you're trying to architect a whole app in like three or four prompts claude is actually really good at doing that. And then if it's just really small details you can get away with with either if it's not like something complex. And then I just switch depending on what it is. And then for some reason Claude is just better at UI stuff. Um, so this is the configuration that I have going and I have tried Codeex. I've tried I I've tried almost all the coding tools right now at this moment of recording, these are currently the best ones.

Um, the other thing that I'll throw in here is um, if you don't have any coding experience, people are always asking me what should I use? Should I use cloud code? Should I use cursor? To be honest, my recommendation is to use a not don't use these platforms. It's actually to really start with something like create anything.com for example. You can also get away using vzero or bolt or something else. But what I found if you want to do mobile apps specifically, I've tested all of them. Create anything is probably the best one at mobile specific. It's just really good at design. It's really good at following instructions. So my recommendation is to use a platform like that first and then if you hit the limits, go graduate to something like cloud code and cursor. And by that point, you should have a better understanding of how to work with AI and how to prompt it to actually use these tools. But the this is the tool set. This is what I recommend. This is what I'm actually using. I I gotta ask because you know the vibe coding mobile app space is like the you know next big thing maybe. You know there's definitely a lot of opportunity there. A lot of people want to be able to do it. You know ROR and there's the Vibe Code app are are two of you know popular ones. Um in addition to anything um like have you have you seen them? Have you played with them? Any thoughts? Yeah, I honestly I played with them. I still think at least at the time of recording um anything is a bit better and the reason is for some reason the design sense is a little bit better and its ability to follow instructions is it's just it's so good. It's so good um compared to the other platforms. But again, you can get away with using any of them. They're all using the same models under the hood. I believe they're all probably using the cloud models under the hood. Um it just it's really just also down to preference, I think. So if you prefer the style choice that Vibe Code or ROR has, for sure you can totally do it. But then if you at least for me subjectively, I did kind of like the designs that I was getting with anything. Fair. Fair enough. And I can actually show you too. Um this is an example of here was something that I actually did create in anything to show kind of what you can do. Um so like like this was something I fully designed in anything with the custom illustrations and interactions. This does surprise people when I tell them that something like this and again these are like custom interactions that are that are happening here like these aren't components or anything. All of this stuff was built in anything in I think less than 24 hours. And so wait that was built this was design and built in 24 hours. Yeah, this one. Yeah, this one fully fully working. The AI actually works. This one's like an AI calorie tracking app that I wanted to prototype. You take photos of your food and it'll just immediately scan and figure out the calories and everything. Fully built. Um, this one was using anything 24 hours. Cool. Yeah. So, that that's my recommendation on the tooling. And then in terms of models, we kind of went over this. Um, we could go into a quick example of uh just kind of what what it looks like what it actually looks like to vibe code something. So, I know in another episode that we talked about, we were looking at interactions in animations. So, something that I kind of went semiviral in my opinion for was the interaction or the animation for my daily or my my calorie tracking app, Amy.

When you search in Amy, it's kind of like typing in Apple Notes. And then on the right, the AI is going to calculate all the calories for you and it'll just appear there. But there's this really nice animation that I have here where you can see that it kind of drops down. there's going to be this little shiny effect that's going on and it shows the sources. So, what I wanted to do is kind of show you guys what it looks like, like how I actually code this stuff really quickly. So, we can kind of go into that and then after that we'll just do some rapid fire tips on on how I do this. So, I have a blank Xcode project. This is just the starting Xcode project. When you run the app, it's just a simple hello world app that should build. Yeah. So, we see it's a hello world app. And again, I have this open in cursor and cloud code. So, what I'm going to do is I'm actually going to let's see if how far or let's just for a little bit. We don't have to do the full thing here, but let's try to replicate what I have here. Um where let's just replicate the animation part where it does the searching, the calculating, all that stuff. Let's try to do that so you guys can see what this looks like. So, the way that I would start is I actually let's just use claude. You can again you can either use cursor plan mode or cloud. Let's just use cloud for this case. Um, and one of the tips that I have is I dictate everything. Just I get way more detailed prompts this way. And I'm using a tool called Whisper Flow as well to do this. So, what I'm going to do is I'm going to say, can you modify this so that there's a button and when I click it, I want a an animation to run. It's to simulate an AI searching for nutrition info and calories. So, first I want when you click it, I want it to say searching and I want it to have this shimmering text animation. Then after 1 second, I want that to drop down. And then I want the text to say analyzing and I want that to drop from the top and replace it. And it's going to take its place. And then still with the shimmering effect. Then after that, I want it to say found 10 sources. And then just put three circles to the left of it. and maybe just find some random websites or just put I don't know YouTube, New York Times, Google just so we can get the favicons for those. Make those the sources on the left and then after show calculating then after that show some sort of hard-coded calories all just to show the animation. We just need to hardcode everything and then make sure that when the replacement happens during the animation, maybe we can make it so that it is cut off. So it's all contained on one line. This is the level of detail that I go with my prompts. And then I just ask Cloud Code to do this. So again, that's why I dictate because it would have taken me like 5 minutes to type this all by hand. Um, and this is this is kind of how I this is how I scaffold apps. This is how I'm making my my edits. It's just dictating everything. And I do the same thing in cursor plan mode. Um, I'll just show you too. If we do the same thing in cursor plan mode, um we won't run it there, but I can copy and paste what I just uh what I just dictated here. Um I'll run it in plan mode in parallel so we can see what this looks like. Okay, so now cloud code, we're back in cloud code and it's saying I'll help you make the sequence. Um this will include this. Do you want to do it? So it's asking permission if it can change the files. I'm just going to say yes, go ahead and do it. So now it's running. It's editing files. Um, and then we have CL uh cursor with plan mode. It's it's starting to plan out its steps. Um, again, we're not going to use this one. I just want to show you what plan mode looks like because it's pretty interesting. Okay. And then cloud code is done. So, it says that it did it. So, let's just run it and let's just see what happens. Hopefully, this is okay. Okay. Nice. So, okay. So, it it did actually make this animation, which is interesting. Obviously, not to the level of polish that we need here. So, I might make some quick modifications. So, I'm looking really closely. And here's a pro tip. When you're doing animations and interaction stuff, if you're running the simulator, you can actually click at the top. It says slow animations. It will run it at, I think, half speed or slower. So, you can actually see what's going on here. So, I can see here. Okay. Now, there's even something going on when I do that. Um, like I don't like how it's dropping down and then going back up, it looks like. So, what I'll tell it is something that's wrong with the animation is when something is leaving focus, it's shooting back up. Can you make sure that it drops down? Also, increase the time to 2 seconds for each of the animations so they can show. Let's also make the shimmering effect a little more extreme. So, we'll let this run. Um, and then here's here's cursor with plan mode doing the same thing. What I love about cursor with plan mode and why I think it's better at very complex problems is it's really good at following up. It's really good at asking questions. So here it's asking should the button be usable multiple times? So we'll just say no. We just want to re uh actually yeah replay on every tap for the three sources. Are you okay with stabilized placeholders? Yeah, sure. Let's do that. So it's asking permissions on like what it should do. And then we have cloud code still running here. Okay. So now this is done. So let's see how much closer it got. And again, I

don't think we're going to get as close as we want because I think it took me like 20 prompts to get to the level I needed to go, but okay, you can see it's a little bit better. It's already looking better already. And then again, if you just do this a few more times, it's inevitable you can get to the level that I have here. That's exactly what I did here. I think it did take again 10 to 20 prompts to be able to get it here. But that's like an hour or two of time to to get it to this level. And it's such a big difference compared to if we don't have it. Here's what it looked like before I added it. Again, there's no like it just kind of just says calculating. There's still kind of a shimmer effect and then and then it shows the calories, but it makes such a big difference. So yeah, that's um that's that's currently how I'm doing it. Uh let's just go back to plan mode. So I'll just show you what this looks like. So when you're using cursor with plan mode, it will actually build out this plan for you. And so it's actually saying what it's going to do. It says step one, it's going to do this. Step two, it's going to wait two seconds, say analyzing, and then you can review this plan. And then when you're ready, you can build it. And then here, I chose 4.5 sonnet as the model to build it. And then when you click build, it's actually going to go ahead and do it. Um, so that's that's actually I'm kind of curious what we can do is I'm going to completely restore this. So I'm basically just undoing everything Claude did. Let's just let cursor go ahead and build it. and let's just see what it comes up with so we can compare to see kind of what the differences between the two are. And then maybe you'll you'll kind of see why I switch between them so frequently and why I'm not just sticking with one. I love having them sometimes do the exact same task and then just comparing and seeing which one is better. But that's Who do you think Who do you think's going to win? I I actually think Claude Code will win because I found that when it comes to design and interactions and animations, it does have a little bit of an edge. Even if you're using the sonnet model and cursor, for some weird reason, I think it is. Let's see if I'm wrong, though. Let's see. I'm actually curious. Um, while we wait for this to go, though, um, what I'll do is let me let me give you a few more. We can just kind of hop into some tips. I know this one takes a little bit of time.

Um, so again, these are the tools I'm swapping between the two. These are the models I'm using. Opus 4.1, GPT5 high, and then uh, Sonnet for the actual execution. Um, here are the tips that I have that really I think like when I've shared these tips, people are like they they usually pick something up from here where they they add it to their workflow and they're like, "This actually made a difference." Um, so the first one, oh actually, you know, this is done. Let's just see what's going on here. Okay, so cursor is done. Let's see what it was able to do. That's actually not bad first try. Actually, you know what? If we're comparing just the first shot, cuz again, that original first shot for Claude was a little bit more choppy. This one was actually really good. You can tell though, it's so fascinating that it kind of came to the same conclusion. I think it's because again, we're using the same model here. When I'm using Cloud Code, it's using Sonnet 4.5. when I'm using the model here, I'm I'm using sonnet 4.5 for the execution. So that's why they look so so so similar. But it is actually interesting that we got a slightly better result when we did the plan mode first with cursor. So that's actually I I think I do I would choose this one um over the other one. Yeah, I think it's not bad. Objectively, this one was better than Yeah, the other one. First prompt. First prompt. So I think so too. I think so too. Okay, so this is a prime example of like even if you're using the exact same model, if you just use plan mode for example versus no plan mode on curs on cloud code, you can get pretty different results. And that's a big reason why I think you should try to actually, you know, test it with a bunch of different tools. Maybe have two AI tools that you're using for different scenarios. But yeah, this was a very fascinating one. Um, okay. So we'll go into like to be honest, the rest of my workflow that this is kind of what I do. I just dictate everything. I'm constantly trying things. Let me go into some rapidfire tips on how to get the most out of the AI coding tools. This is exactly what I'm doing in my workflow. And then if you need a basic to tutorial on cursor and cloud code, there's so many great ones out there. So the first one is, as we saw, there is a difference when you use plan mode, 100% every action that you take, use plan mode. You get it almost like you give the AI time to think and you will get better results. So, I already showed you what it looks like in cursor when you do plan mode. All you have to do is toggle plan mode here and it's going to give this beautiful plan on the left and when and you can review it, ask for changes and then when you're ready, you click build. Unfortunately, it's not as beautiful in cloud code. So, let's let me show you what this looks like. You can actually hit shift tab and it'll change it to plan mode here. And now when you ask Claude code to do something in plan mode, it's going to kind of do the same thing that cursor does where it's going to think through come up with a plan and ask you to review it. But what I have found at least at the time of recording, cursor's plan mode is stronger than claude codes, which is why I use cursor plan mode for insanely complex problems. It just somehow thinks about it a little bit better. It asks better follow-up questions. But that is tip number one. Um, and then here's here's claude code asking for things. It's like, "Yeah, here's my plan." You can already just tell like, "Oh, actually, this is not fair cuz it's it's it's looking at the current code right now." But typically, this is what happens. It tells you its plan, and then it's up to you to just review and approve it. It will not be as detailed as cursors plan. Like, cursor's plans are just so detailed. They're very, very good. So, that's tip number one. It's use plan mode. I'm pretty sure if you do this, the output will probably at least increase by 20% at minimum if you just do this. So, 100% do this. It's also good to just review what it's about to do as well. like it's better than just letting it run, you know, run through your codebase and then you have to retroactively go uh or yeah, you have to go back and try to fix it. This is just a way better way to do it.

Um, second tip, this is specifically with Claude Code. It's to use the keyword ultraink. So, this one is actually a special keyword that Claude Code has. And I'll show you. If you type in can you fix this issue and you type in ultrathink it actually changes colors because it is doing something when you type this in claude code is actually going to think a little bit harder about the problem. I'm assuming that it uses up more tokens and more usage when you do this, but to be honest, I think I use Ultraink in 90% of my messages. And I have not really found that it's impacted my my token usage versus if I don't do it, it seems like it's about the same. So, there's no reason not to do it. So, when you're stuck on a complex problem, just type ultrathink and Claude will think maybe I'm assuming it seems like it takes twice as long, so maybe it thinks twice as hard or something, but this is a keyword I'm very surprised people don't know about. So you will get a lot better results when you do this. I don't think there is one in cursor. It doesn't highlight, but I think you can still say like ultra think and cursor. If you're using sonnet as the model, I think it will work too, but there's no nice color animation or color thing here to show that it is actually doing something. So that's the that's my second tip.

The next tip is in cloud code, you can actually run background tasks. So this is where you can tell cloud code, can you run the server in the background for me? This is something I think they only added in the last month. So, this is a relatively new thing, but what this does is Cloud Code will literally run your server in the background. So, it's running just like you would in the terminal. But the important part is it now has access to your server logs. So, when you're running and when you're coding with cloud code, it can now access this during debugging. So, if you're like, hey, why is this not working? It will then you don't have to copy and paste things and say, hey, the server's crashing, take a look at this. It just has access to it. And this is a massive one which I just don't see people doing either. Um I think it's probably because it's a recent thing, but I'm constantly telling it, hey run, all you have to do is say run the server in the background for me and you'll see this thing that says one background task and it's basically running it. So I'm I'm constantly using this. This is another big one.

Uh the next one is MCP servers. So last time I came on the podcast, I was not using MCP servers. Um and to be honest, I didn't understand like what all the hype was about with MCP servers. I now understand like where they're useful especially for coding. So there's two MCP servers that I'm currently using. The first one is called Contact 7. It's a free MCP server. Basically it just lets you access the latest version of a lot of different documentation and it's very compressed and very well formatted for an LLM. So instead of what I typically would do is I would just get the documentation for something like let's say I wanted to integrate Posthog Analytics into my app. I would typically say, "By the way, here's the link to Post Hog. Go implement it for me." But the problem with that is now it has to go scrape it. Maybe it doesn't do it correctly. Or you can use context 7, hook up the MCP server, and you're basically giving Claude code and cursor tools. And now it has access to context 7, which now I can just say, "Oh, make sure to use the latest documentation for Post Hog. Please use the context 7 MCP." And when you do this, it's going to use like context 7, pull the latest documentation, really compressed, really really more digestible for cloud coder cursor and it it will just it will just use it way better than you trying to feed it in through a URL or something. So that's the first one. Second one I'm using now is superbase. Um, so this one is I'm probably going to get some heat for this, but because a lot of developers are probably going to say, "Oh, this is not secure. Why are you doing this?" But in my experience, this MCP, and you can use this for Firebase, you can use this for whatever database you're using, is so powerful to correctly set up a project for you. So, I'm constantly using this to set up projects from scratch. Because before I would have claude code do all the coding and everything, but then I would have to manually go set up my database, make sure I'm configuring rules correctly. I would argue that if you are using a tool like Superbase MCP where cloud code has full access to superbase, it can spin up everything for you. It actually might be more secure because it has caught things that I have manually configured wrong. Like it has set up the security rules better than I would have done to be honest. And so this is something where I actually do recommend if you're a beginner or if you're a seasoned developer, it's really helpful to use this. And if you're a developer and you don't trust it, at least use the Superbase MCP to read your configuration and just double check your work. So you can just say, "Hey, I set up the Superbase uh server. I set it all up. I've hooked it up. Can you just double check that I set it up correctly? Check all the security rules. Check all this stuff. Check the indexes so the performance is good." This is a really powerful MCP. And again, you can do this for Firebase. You can do this for AWS. They have an MCP, I believe, as well. And it's just such a such a powerful way. just give give Claude code cod or cursor access to these tools and anything you can do in the UI they they'll be able to do. Um when I'm in production though I will say I am way more cautious about using it because you it could just delete your entire server if it wanted to and just delete the database. So I am a little bit more cautious but I still do run this in production though because it is it just so much faster for my workflow to to use this. So those are the only two that I'm seriously using right now. I'm sure that's going to change in a few months though. Um, like I'm going to probably play with the Figma MCP now and and test this out more. But yeah, these two are very good.

Um, the next one is this is a very this is a very big one for solo developers or anyone that has no coding experience right now. There are a couple of AI coding tools that can review your code for you. And specifically if you open a pull request in GitHub. So let's say you make a bunch of changes and you open up like like if if you have any coding experience, you know that the proper way to do something is you add your code to GitHub and then another developer reviews it before it gets merged into production. If you're a solo developer, you have you don't have that luxury. There's really no one who can review your code. So, I'm using tools like Bugbot and Cloud Code has one as well where it can actually live inside of your codebase and anytime you open up a pull request or you want someone to review your code, it will do it for you. And I will say these tools when you hook them up, it is so much better than trying to do this inside of Cursor or Cloud Code itself because I think these are maybe custom models or something, but they're specifically trained to identify security issues and bugs. And so what I'm doing is I have them hooked up to all my repos and it has caught so many things for me. And again, it's stuff that I am a pretty experienced developer I believe, but I mean I'm working so fast. I'm moving so quickly. It's just inevitable that bugs will be introduced, security vulnerabilities will be introduced. It gives me so much peace of mind. And I think the cursor one is just $40 extra per month. Totally worth it. Totally worth it for peace of mind, especially from the security security perspective. So I recommend hooking this up. It's a hack for solo developers and for vibe coders who are really worried about the security. Best $40 you'll probably ever spend for to be able to sleep at night knowing it's

everything is secure. Um the next thing which is uh then the next thing is dictation. Um this is as you saw when I was dictating when I was trying to use cloud code I was dictating my prompt. It's because you can just get way more detailed prompts and then that will help steer the AI in a way better direction. I actually didn't think this was a big deal, but then when people started seeing me do this in my videos, I I didn't know people weren't doing this. Like, and that was something where people were like, "Wow, I just downloaded this. Yeah, my AI coding has dramatically improved because I'm dictating everything now." So, that's another hack. 100% recommend dictating. You can use Whisper Flow like I'm using. There's also some other tools, but Whisper Flow is really great because it has built-in developer terminology, so you can say developer terms and it kind of understands it already, too. Um the last tip that I have is to use claude for deep research on technical issues. So something a lot of people don't know is that if you are paying for claude code, you also have increased usage inside of claude desktop like the chat app and you can actually use it to do deep research for you. And so what I'm doing frequently is I'm actually asking it, hey this is what I'm about to do in my app. So I'm again I'm a pretty experienced developer I think. So, I ask it, "What's the best way to store data? I'm looking for something similar to this in React. What do you think?" And it will go and it will look for 12 minutes straight and look through all of the documentation and try to find the best way to do this. And then it'll just summarize everything for me. And then I can just take that and then review it obviously and then I'll send it over to Claude Code and say, "Hey, can we actually do it this way cuz I think this is a better way." So, this is a great way if you're a developer to double check, are you implementing them correctly? learn some new concepts and then if you're just getting started out this is also a great way if you can just ask it hey I've never done this before what is the best way for me to store data so this is something that I am very surprised I don't see a lot of people taking advantage of especially non-technical people especially people who are just starting to vibe code you like you don't have to call your developer friends anymore and say hey how do I set up this like how should I structure my app just use cloud especially if you're paying for cloud code already and then obviously double check it and if you don't know what you're doing you can ask a follow-up question. So you can say, why did you choose this pattern? Okay, what other patterns exist? There's also a great way to learn as well. So this is probably it's a win-win if you use something like this and then you can just feed it into cursor and cloud code and then it has access to this. It's able to implement it for you. And yeah, I I've just I found so many things that I've done not wrong, but I could have done better because I use Claude's deep research. So, I I know this wasn't a full-on coding tutorial, but these were just a couple of things that I've been telling people in my YouTube videos, and I've gotten a lot of comments saying, "Yeah, the these are very helpful tips." Like, people did not know Bugbot existed. People did not know deep research existed. So, hopefully there's some cool stuff that you can take and apply to your own AI coding workflow. I appreciate you. I think we're all trying to get the most out of these vibe coding platforms and little tips and tricks help like this especially a lot of us are you know solo devel solo builder solo developers right so it's not like we have people in in real life to talk to so this is helpful and I just want to thank you for coming on and and and spreading that spreading the sauce with us and um I'll include where you can go find Chris and get more of him in the show notes, so you can check check that out there. And uh Chris, don't forget about us. Come back on again. Yeah, for sure. For sure. Yeah. Thanks so much for having me, Greg. Really appreciate it. All right.