WEBVTT

00:00:00.000 --> 00:00:04.480
Cloud Code is difficult to learn because there's just so many different concepts

00:00:04.480 --> 00:00:11.200
that you need to learn. And it feels like every single day that goes by, there's a new concept that you have to understand.

00:00:11.200 --> 00:00:15.645
In today's video, we're gonna be breaking this down in the simplest way possible.

00:00:15.645 --> 00:00:26.525
I'm gonna be teaching this like I was explaining it to a 10 year old. Let's get into it right away. The first thing is is what actually is Claude code and what separates it from something like ChatGPT?

00:00:26.605 --> 00:00:31.280
Well, ChatGPT talks to you, but Claude code actually takes actions

00:00:31.520 --> 00:01:26.090
on your behalf. So you can message Claude saying, hey. Build me out a website, and it will literally build out the entire website for you. This whole thing was generated using Claude code for me. You can also generate blog posts for you. You can even generate web applications like a dashboard that runs your entire business. And all of these slides that I'm showing you was also generated using Claude Code. The next thing is is IDEs and coding workspaces. Now, technically, this isn't Claude Code, but this is almost a requirement for most people to use Claude Code. So I wanted to include it in there because it's one of the first things you're gonna hit when you go to use Claude Code. IDE stands for integrated development environment, and you do not need to know any software engineering or anything technical whatsoever. That's the whole reason you use Claude so that you don't have to do anything technical. There's three main IDEs or coding workspaces in the marketplace.

00:01:26.330 --> 00:01:36.090
Versus code, anti gravity, both of those are free, and you have Cursor, which is also paid. Now, essentially, you can head over to a site like antigravity.google

00:01:36.090 --> 00:01:50.025
and download the free desktop. And again, this is a Google product. And once you're inside, you'll you'll be in a coding workspace just like this. Now where Claude code comes into the picture is it's an extension that lives inside

00:01:50.025 --> 00:02:04.230
of your coding workspace. So on the left hand sidebar here, you can add plug ins, search for Claude code, and then start using it immediately from within Versus Code. Now the next thing is projects

00:02:04.230 --> 00:02:05.430
and files.

00:02:05.750 --> 00:02:08.710
Anytime you're building on a project with Claude code,

00:02:09.030 --> 00:02:23.935
you have something called a file system. System. K? You can think about this really just like Google Drive, but for your project. You have you can store whatever different files you want. You could have videos. You could have images. You could have text files. You can have folders to organize everything.

00:02:24.335 --> 00:02:27.990
But the cool thing is is that you can have multiple

00:02:27.990 --> 00:02:29.190
different projects

00:02:29.190 --> 00:02:30.070
inside

00:02:30.230 --> 00:02:31.910
of your coding workspace.

00:02:32.070 --> 00:02:43.685
So right now, I technically have one project here called Claude Code Concepts. Okay? And then I have another project called project two. We could go ahead and hit file,

00:02:44.005 --> 00:02:54.740
add to workspace, and then I can add project three over here. So let's say you have multiple clients. You could have a new project for every client from within the same,

00:02:54.900 --> 00:02:56.340
um, workspace

00:02:56.420 --> 00:03:02.580
so that you can move back and forth between all of them just by messaging Claude and keeping things nice and organized.

00:03:02.740 --> 00:03:07.195
And, of course, again, you can add any files that you want to this project.

00:03:07.435 --> 00:03:09.275
The next thing is prompts.

00:03:09.435 --> 00:03:14.235
So prompts you're probably already familiar with, but anytime you're messaging

00:03:14.395 --> 00:03:25.980
back and forth with Claude, that is considered a prompt. So when you open up Claude by hitting this nice little Claude button right over here, and let's say we say that we send a message, hey,

00:03:26.060 --> 00:03:37.865
that is a prompt, and then Claude code is going to reply back to us. Now the one key about prompting inside of Claude code is that you want to be as specific

00:03:37.865 --> 00:03:38.905
as possible,

00:03:39.065 --> 00:03:53.690
and you want to give Claude a role. So instead of saying, hey, build me a website, which is gonna give you generic AI slop. You can say, build me a one page land one one page website for a wedding DJ business in Toronto.

00:03:53.850 --> 00:04:07.155
It's lead generation focused and so on and so forth. So the more information you provide with, the better it will be delivering you the outcome you're looking for. When I say give it a role, in this instance, you'd say, hey, Claude. You're a web designer,

00:04:07.395 --> 00:04:20.320
and it will act according to that position. Again, maybe you wanted help with investments. You could say, hey. You're an expert investor or you're an expert social media manager or whatever the case may be, and it's going to understand exactly

00:04:20.400 --> 00:04:21.040
how

00:04:21.200 --> 00:04:23.440
it should tailor its responses

00:04:23.520 --> 00:04:26.160
to you. The next thing is context.

00:04:26.320 --> 00:04:28.835
Now when you're using Claude code,

00:04:28.915 --> 00:04:40.115
the distinction between getting bad responses back like AI slop and fantastic responses back that you're really happy with is the context you provide Claude code with. The more it knows about you,

00:04:40.355 --> 00:05:06.005
your business, what your outcomes the outcomes are that you're looking for, the better it's gonna be at delivering you results that you're happy with. So let's say, for example, you wanna generate something like a LinkedIn post over here. If I just tell Claude, hey. Generate me a LinkedIn post. It's gonna go ahead and do a really bad job. It's gonna throw in a bunch of emojis that I don't want. It's gonna sound generic. It's not gonna have personality. It's not gonna sound like me whatsoever.

00:05:06.405 --> 00:05:09.300
But I could add in here files

00:05:09.300 --> 00:05:10.740
on my humor,

00:05:10.980 --> 00:05:13.620
on my tone, on my vocabulary,

00:05:13.620 --> 00:05:16.100
and then it can actually go ahead and understand

00:05:16.180 --> 00:05:22.420
what kind of jokes I like to make, how I sound in real life, and then it can actually write posts

00:05:22.420 --> 00:05:30.685
that sound exactly like me. Okay? So in here, just as a side note, Jono's humor is dry, self aware, and observational.

00:05:30.685 --> 00:05:36.365
It gives examples of what that looks like. I I swear, Claude knows my humor better than I know myself.

00:05:36.605 --> 00:05:42.860
And so these are kind of examples on how you can get the right results back from ThoughtCode.

00:05:42.940 --> 00:05:47.820
How you'd actually pull in things like humor and tone and vocabulary

00:05:47.820 --> 00:05:48.780
is

00:05:49.100 --> 00:05:59.655
you would go to something like your LinkedIn posts or your emails that you've sent off or wherever you have samples of writing. It could be call transcripts as well. It could be video transcripts.

00:05:59.735 --> 00:06:02.535
You will just take that, okay, that whole post,

00:06:02.855 --> 00:06:13.240
and then you would just paste it into Claude and be like, here is a sample LinkedIn post. Can you please pull up my humor, tone, and vocabulary and update all three files that you have on record?

00:06:13.640 --> 00:06:15.320
And now it's gonna go ahead,

00:06:15.800 --> 00:06:20.685
pull out all of the information from this, and then update all of these different files.

00:06:21.005 --> 00:06:23.965
Cool. The next thing is is references.

00:06:24.285 --> 00:06:45.075
So when you're dealing in Claude code, projects can often grow pretty fast and get pretty big. If you wanna reference a particular file, like for example, this tone file over here, we can drop in the and symbol. Okay? And when we drop in the and symbol, I'm just gonna move this over and so you guys can see it properly. Now we can start referencing

00:06:45.075 --> 00:07:00.100
particular files. So I can type in here tone dot m d, and now it's going to be able to read that particular file because I referenced. So you can actually see that it's gone ahead and read the exact file that I was referencing.

00:07:00.100 --> 00:07:39.305
This is especially, uh, useful if you have multiple files with the same name or very similar names. The next thing is permissions inside of Claude code. So when you're communicating back and forth with Claude, you can determine how much control you actually give to Claude code, and that comes down to this button right over here. Here are all the different modes. Let me explain this in a very simple way, and we're going to remove plan mode for now, and we're just gonna talk about these other four. The further down this goes, okay, the more control that you give to Claude to make autonomous decisions on your behalf. So when you say, hey. Ask for edits.

00:07:39.465 --> 00:07:44.105
Anytime Claude does anything like editing a file

00:07:44.265 --> 00:08:01.280
or connecting into an external application, which we'll talk about later on, it's gonna ask for your permission. When we talk accepting edits, which is the next layer down, okay, what's going on here is that it's going to edit files in your file structure over here automatically.

00:08:01.280 --> 00:08:02.800
But anytime you're doing

00:08:03.120 --> 00:08:29.950
anything kind of, like, outside of editing these exact files, So for example, connecting into Gmail or connecting into external applications or whatever the case may be, it's gonna ask for your permission. With auto mode, it's going to only ask for your permission if it thinks that it's gonna do something dangerous. And with bypass permissions at the bottom here. This is where it's just gonna do everything on its behalf, and sometimes it can make mistakes, overwrite things that you didn't wanna overwrite,

00:08:30.110 --> 00:08:45.055
but it does go a lot faster. And with plan mode here, the distinction is is that it thinks now and then it acts later. It will create an entire plan for you. And once you approve that plan, you're happy and it thinks through all of the different contingencies,

00:08:45.055 --> 00:09:13.235
then it will go ahead and build it out. So anytime you're building a large project, it's usually advisable to start with plan mode and then switch over to one of the other four categories after the planning is done. The next thing is tools inside of Claude code, and this is the hands part of Claude. It allows Claude to actually take actions on your behalf. So when you look at this conversation here, you can see that Claude has read, okay, a particular file,

00:09:13.475 --> 00:09:28.370
and then it did something called web patch. So it actually went to this URL, and it read this documentation here, this this page. Okay? Then it went and it fetched this web result, and it read this page as well, understood what's going on here.

00:09:28.690 --> 00:09:33.915
And then it wrote this article right over here called techstack.md.

00:09:34.075 --> 00:09:58.520
So Claude is taking actions on your behalf, and these are tools that it has access to. These are out of the box. There's no configuration required, but it has the ability to read a file. It has the ability to find a file by its name, which is called glob grep, which is search inside of files. Then it can write and edit. It can do bash commands, which we'll talk about a bit later on. It can search for a URL

00:09:58.680 --> 00:10:07.535
and search on Google and so on and so forth. The next thing is the context window inside Claude code, and this is Claude's short term memory.

00:10:07.695 --> 00:10:11.855
So if we just open up any one of these individual conversations,

00:10:12.175 --> 00:10:18.140
everything going on here is the context window. Okay? The more messages

00:10:18.460 --> 00:10:22.380
that you send in here, the more Claude has to remember.

00:10:22.700 --> 00:10:49.200
So Claude has a limit on how much it can remember just like a human would. So if you and I are having a conversation for ten years, you're not gonna remember all ten years. You might be able to remember a couple hours. Right? Same kinda deal with Claude. It's not gonna be able to remember what you said, like, ten years ago. It's only gonna be able to understand a certain length. And then after that, it's gonna fill up and the quality drops. And then you have to reset the conversation,

00:10:49.200 --> 00:10:51.200
which we're gonna talk about later

00:10:51.440 --> 00:10:57.200
in this video. The next thing is the Claude dot m d file, which is the instructions

00:10:57.200 --> 00:11:04.935
you tell Claude to behave the way you want it to behave. A good analogy for this is you hire an employee,

00:11:05.175 --> 00:11:53.820
and you need to train that employee on what the job is and how to do it properly. The it's the same kinda deal with the claude.md file. This is the instruction file that you give to Claude to tell it how it should behave, what it should do, what it shouldn't do. So let's say that we're writing a LinkedIn post one more time. A rule that you have here is, hey, don't let me publish a LinkedIn post unless we qualify it as a nine out of 10. I don't wanna send off a five out of 10. I don't wanna send off a six out of 10. It needs to be at least nine out of 10. Another rule could be, hey, before you create a file, make sure it doesn't exist yet. We might not wanna like, so for example, you don't wanna duplicate your humor file or your tone file. You only wanna create that file if it already doesn't exist. Okay? So that's kind of the claude.md

00:11:53.820 --> 00:12:05.015
file. It just teaches Claude on how it should behave. The next thing is models inside of Claude code. So you typically have three different models, Haiku, Sonnet, and Opus.

00:12:05.255 --> 00:12:17.350
Inside of Claude code, I'm gonna move this over just so you can see it properly. If you hit the slash command right down here, you can switch between models and you have access to, again, Sonnet,

00:12:17.430 --> 00:12:21.395
Haiku, and the default over here, which is Opus 4.7.

00:12:21.475 --> 00:12:24.515
The higher up you go, the better the models become.

00:12:24.995 --> 00:12:41.880
Opus is definitely the most powerful. Haiku is the least powerful, and Sonnet is somewhere in the middle. The distinction between them though is Haiku is fast and cheap, which means that, um, you're not gonna be using as much of your Claude limits

00:12:41.960 --> 00:12:43.640
while using Haiku.

00:12:43.640 --> 00:12:51.515
Okay? So every time you're using Claude, we're gonna talk about this a bit later, you have current session limits, weekly limits, model limits, all of that kind of stuff.

00:12:51.915 --> 00:13:04.280
Opus is gonna burn through it very quickly. Haiku is gonna burn through it way more slowly, and then Sonnet is somewhere in the middle. Obviously, there's trade offs between cost and power. The next thing is tokens,

00:13:04.520 --> 00:13:22.855
which is essentially the currency that Claude code uses. So when we go back to this usage page over here, you have certain limits on a session basis, on a weekly basis, across all models, across claw design, and so on and so forth. And the currency

00:13:22.855 --> 00:13:27.175
used to fill up that limit is tokens.

00:13:27.175 --> 00:13:53.855
Okay? And they can add up quite fast. The definition of a token is approximately three quarters of a word. So let's take this phrase for example here. Build me a landing page for a wedding DJ. Okay? This takes up 10 tokens. Every token is essentially represented by a different color. So we have build over here. That is one token. Then we use another token for the word me. Then we use another token for the word a,

00:13:54.095 --> 00:13:55.855
then landing page landing,

00:13:55.855 --> 00:14:00.050
then page, and so on and so forth. So these are all tokens that we're using

00:14:00.210 --> 00:14:02.050
when sending off a message.

00:14:02.450 --> 00:14:19.715
Now you might think, okay. Well, 10 tokens, not that bad. It's not a big deal. But the issue is actually less about the individual message you're sending. And the bigger issue is that anytime you're interacting with Claude code down here, okay, there's input and output tokens.

00:14:19.875 --> 00:14:25.570
And what that means is that the input tokens are the entire conversation.

00:14:25.730 --> 00:14:28.130
So if you've just had a monster

00:14:28.130 --> 00:14:33.890
two hour conversation here where you're going back and forth with Claude, that whole conversation

00:14:34.130 --> 00:14:44.775
is technically input tokens that you're still burning through. And when it outputs a response back, that's also tokens as well. So every individual message by itself,

00:14:45.175 --> 00:14:49.095
it's really not that expensive. But when you get to, like, 200 messages,

00:14:49.335 --> 00:14:58.770
all of a sudden, you have to remember not only that individual message over here, but then the last 200 messages as tokens

00:14:58.770 --> 00:15:07.315
as well. And so that's why it's an exponential curve because the longer your conversations get, the more the tokens and memory expand.

00:15:07.715 --> 00:15:15.395
And all of a sudden, when you're at the very end, it can balloon really quickly, and that's the danger zone where your tokens or credits

00:15:15.715 --> 00:15:27.170
can all of a sudden explode. And then before you know it, you're just out of that current session or your weekly limits or whatever the case may be. The solution here is to reset the conversation.

00:15:27.570 --> 00:15:32.695
Cool. And how we can do that and many other things is through slash commands.

00:15:32.695 --> 00:15:41.415
Okay? So inside Cloud Code, if we type in slash here, k, we have access to a lot of different commands.

00:15:41.735 --> 00:15:45.015
One of those commands could be saying

00:15:44.730 --> 00:15:51.850
context. And I feel like I'm screaming at Claude code by typing in all caps here. But when we type in context, it will tell us

00:15:52.330 --> 00:15:55.130
how much of the current

00:15:55.210 --> 00:15:56.170
conversation,

00:15:56.170 --> 00:16:02.055
how much of the context we've used. Remember, it only has a predefined set,

00:16:02.215 --> 00:16:02.775
um,

00:16:03.095 --> 00:16:21.920
memory. So it can't remember ten years of messages. It can only remember, let's say, one or two hours. And this will tell you how full that memory is. And the higher up this goes, the more you're spending. Another option is to type slash clear. And what this will do is it will reset the conversation

00:16:22.000 --> 00:16:59.305
so that you're not burning money on credits. This is really important just because a lot of people burn their credits, and then they're locked out for, like, a week. And, obviously, you don't want that to happen to you. Okay? There's a lot of other slash commands that you can use as well, but those are some of the main ones that I like to use. We're gonna be talking more about slash commands later on. The next thing is memory inside inside of of Cloud Cloud Code. Code. So So let let me me explain this as clearly as possible. You can see up top here, we have many different conversations open at the same time. Okay? We have four that you can see right here. The problem is is that these

00:16:59.625 --> 00:17:00.505
conversations

00:17:00.505 --> 00:17:05.065
are isolated. So if I say something in conversation a, conversation

00:17:05.065 --> 00:17:06.505
conversation c

00:17:06.505 --> 00:17:24.630
won't know what I said. It won't persist across the different conversations. So you're starting from the ground up with every single conversation you have. With memory, this is a way that you can save information that will persist across every single one of these conversations.

00:17:24.710 --> 00:17:29.990
Okay? So as an example here, I can type in something like

00:17:30.635 --> 00:17:39.355
update the system memory with my favorite food, which is sushi. And then all of a sudden, in the next chat window, I can say, hey. What's my favorite food?

00:17:39.515 --> 00:18:00.765
And it will remember that it's sushi. Okay? So you can remember things about yourself, about your business, about the way you like to write, or whatever the case may be, and it will persist across every single conversation that you have with Cloud Code. Now the next concept is called compacting, and this helps your longer conversations stay sharper. This is a slash command.

00:18:01.085 --> 00:18:03.165
And as we were talking about earlier,

00:18:03.325 --> 00:18:08.285
every single chat has a context window. When it hits a 100%,

00:18:08.365 --> 00:18:09.165
automatically,

00:18:09.165 --> 00:18:11.485
Claude is going to compress that conversation.

00:18:11.645 --> 00:18:16.820
How it does that is it just takes the whole conversation and summarizes it so it resets

00:18:17.060 --> 00:18:35.205
essentially your context window. Now you can wait for Claude to do this, or you can do it manually by typing in slash compact, and then it will compress the whole conversation down. The benefit of doing this manually is that when your context gets to about 50% full, Claude actually starts forgetting things,

00:18:35.445 --> 00:18:39.365
and, also, you start spending way more money through tokens.

00:18:39.365 --> 00:18:53.750
The next thing is skills inside a Claude code, and this is the thing that I use the most inside Claude. They're prewritten instructions to get tasks done. Now one example could be creating LinkedIn posts, but the reality is is that anything you do two

00:18:53.830 --> 00:19:15.910
or more times, you can turn into a skill and have Claude code automate it. I like to actually think about it like on demand workflows. I try and create a LinkedIn post every single day. Claude code writes the first draft for me, and it comes out very good because I've told Claude what a good post looks like, and then it can replicate it every single time. So now I just come into Claude and I say, hey. Write me a a LinkedIn post.

00:19:16.070 --> 00:19:30.645
It will pull in things like my tone and my humor and my voice and my, uh, good examples of what a a LinkedIn post looks like and everything else, and then it will create the post for me. Here's what it actually looks like inside of Claude code.

00:19:30.885 --> 00:19:38.690
When I say on demand, I literally mean that I can type in a slash command here, oops, inside Claude, like slash

00:19:38.690 --> 00:19:39.490
LinkedIn.

00:19:39.970 --> 00:19:41.410
And on demand,

00:19:41.650 --> 00:19:52.075
I can call Claude to create a LinkedIn post. Now these skills can easily be created in Claude. You can open up a new conversation and say, please create a skill

00:19:52.395 --> 00:19:54.635
for posting on LinkedIn,

00:19:54.715 --> 00:20:08.310
and it will go ahead and do that. And as you use these skills over time, it's not gonna be perfect out of the box. You just incrementally improve it until it becomes what want it to be. The next topic inside Cloud Code is called hooks,

00:20:08.470 --> 00:20:10.630
and these are automated actions

00:20:10.630 --> 00:20:14.150
that you can have Cloud Code do at some stage

00:20:14.230 --> 00:20:21.115
during the conversation. So if you think about, like, a traditional conversation in Cloud Code, there's multiple stages. You start the conversation,

00:20:21.515 --> 00:20:35.930
and you end the conversation, and then certain things happen in between. Like, you send a message, Claude sends a message back, and so on and so forth. You can set a task or an action to happen at any of those stages. So for example, I could say,

00:20:36.410 --> 00:20:39.850
if I say the word pizza at the beginning of conversation,

00:20:40.250 --> 00:20:53.815
don't reply back, block the request. So in here, I'm gonna type in pizza, and the conversation is just going to stop. Nothing's gonna happen. It's not gonna reply at all. And then I can say, hey, and the conversation will return,

00:20:53.815 --> 00:20:57.175
uh, back just as normal. And then I can say pizza again,

00:20:57.415 --> 00:21:11.990
and nothing's gonna happen, and so on and so forth. Now a better use case for this would be don't upload my information online if you think I'm exposing passwords or secret keys that I don't wanna expose. Okay? So that's another example.

00:21:12.230 --> 00:21:28.080
To finish up on hooks, we can also have something at the end of the conversation when Claude replies to us. So we could say, make a noise. Okay? And that noise that you just heard was a hook. You can come into Claude and say, please create a hook for me,

00:21:28.400 --> 00:21:30.720
k, that makes a sound

00:21:30.960 --> 00:21:33.120
every time you reply.

00:21:33.200 --> 00:21:44.375
And it will go ahead and build that out for you. It's really as simple as that. The next thing is MCP servers inside Cloud Code. MCP stands for model context protocol.

00:21:44.455 --> 00:21:48.375
It's how you connect Cloud Code to all of your favorite applications

00:21:48.455 --> 00:21:49.735
like Airtable,

00:21:49.735 --> 00:21:52.935
Slack, Gmail, Google Drive, Notion,

00:21:53.095 --> 00:21:58.320
and so on and so forth. How you set this up is you'd go to claud.ai/settings.

00:21:58.480 --> 00:22:00.320
You'd come over to connectors here,

00:22:00.560 --> 00:22:23.210
and you can browse through hundreds of different apps to connect into Claude code. Once it's connected in, you're good to go. You can start using it. You can also hit the configure here. Okay? And you can change the permissions Claude has. So if you don't want Claude to be able to write or delete emails, you could say needs approval or blocked, and it won't be able to take those actions

00:22:23.210 --> 00:22:24.090
automatically.

00:22:24.330 --> 00:22:27.690
So just as an example here, we can connect into Gmail,

00:22:27.770 --> 00:22:31.130
and every email that comes through, we can automatically

00:22:31.130 --> 00:22:33.050
label it as miscellaneous

00:22:33.050 --> 00:22:35.050
or personal or website

00:22:35.050 --> 00:22:39.185
or whatever the case may be. The next thing is APIs,

00:22:39.185 --> 00:22:41.985
which stands for application programming interfaces,

00:22:42.065 --> 00:22:46.385
and this is how you can also connect Claude into all of your favorite applications.

00:22:46.465 --> 00:22:50.545
It's essentially the same result as MCP.

00:22:50.705 --> 00:22:56.060
The distinction is is that MCP is relatively new. Like, it didn't exist five years ago,

00:22:56.380 --> 00:23:01.740
and it allows specifically AI agents to easily connect into

00:23:01.980 --> 00:23:03.420
your favorite applications.

00:23:03.500 --> 00:23:19.585
The problem is is that MCP is new, and there's not, like, uh, there's not every single application has a connection into Claude code. But you can still connect Claude into all of your other favorite applications even if an MCP server doesn't exist through APIs.

00:23:19.910 --> 00:23:21.590
Now practically speaking,

00:23:21.990 --> 00:23:24.550
all you need to do is tell Claude

00:23:24.630 --> 00:23:26.390
to connect in an application.

00:23:26.470 --> 00:23:28.230
Ideally, you'd start with MCP,

00:23:28.230 --> 00:23:39.725
and only if MCP doesn't exist, then as a backup, you'd use an API key. Okay? This is how applications communicated back and forth with each other for decades before

00:23:39.805 --> 00:23:42.205
MCP servers actually existed.

00:23:42.445 --> 00:23:45.900
The only thing that you need is a password

00:23:45.900 --> 00:23:55.980
to verify who you say you are. So let's say I log in to Gmail here. It's gonna ask me for a password to verify who I am. And very similarly,

00:23:55.980 --> 00:24:06.925
to connect Claude via an API into an external application, you need a password in order to verify who you say you are. And you wanna store that password in something called the dot e m v file.

00:24:07.085 --> 00:24:16.890
This is where all of your secret keys belong like this, for example. The reason why you wanna store it here is for safety reasons so that when you deploy

00:24:17.210 --> 00:24:21.930
your project live on the Internet, you don't have security vulnerabilities.

00:24:22.170 --> 00:24:27.610
The next concept is sub agents inside of Cloud Code, and these are preconfigured

00:24:27.610 --> 00:24:28.490
specialists

00:24:28.490 --> 00:24:31.405
that you can reuse. They're very similar

00:24:31.565 --> 00:24:33.165
in concept to

00:24:33.965 --> 00:24:45.220
skills. The distinction between the two, I'm gonna use an analogy here, is think about you heading to a restaurant. Okay? With a sub agent, you can kinda think about you ordering food,

00:24:45.540 --> 00:24:55.380
that food being completed in the kitchen, and then returned back to you. You gave the order. You got the food back, but everything in the middle, you didn't really see happen.

00:24:55.460 --> 00:25:11.885
K? With skills, it's like you order the food, the chef cooks it on the table in front of you. You see the whole process. You understand everything going on. You can interdoc, ask them to do certain things, and then you get the food in front of you. Okay? Now the benefit in doing this is that it's self contained,

00:25:12.310 --> 00:25:17.350
and it should require less context in that particular conversation.

00:25:17.590 --> 00:25:28.755
The benefit of skills is that it's in your chat, you get to watch every single step. So in this instance, I could say, read this particular agent. Okay? And we can see our agents in this folder right over here.

00:25:29.075 --> 00:25:43.170
And give me an overview of this project. It's going to find that particular agent. It's going to do the job, and then it's going to return the results back to us. Again, this file structure over here is just boilerplate.

00:25:43.170 --> 00:25:54.690
You don't have to memorize any of this. You just ask Claude to build you an agent, and it's going to automatically build out this file structure for you. The next thing is agent teams inside of Claude code.

00:25:55.010 --> 00:26:00.485
The traditional way that Claude works is you might send a prompt like build me

00:26:00.805 --> 00:26:02.725
a five page website.

00:26:03.765 --> 00:26:09.960
Okay? And it'll receive that task, and it'll build the first page, then it'll build the second page,

00:26:10.200 --> 00:26:13.400
then it will build the third page. And this is sequential.

00:26:13.400 --> 00:26:25.425
You're not gonna start this third page until the second page is done, and you're not gonna start the second page until the first page is done. What that means is that it's very slow. With agent teams, what's happening is you have a manager agent

00:26:25.585 --> 00:26:27.745
that delegates responsibilities

00:26:27.745 --> 00:26:35.425
to employee agents. Okay? So what happens is if you're building a website page that has five pages,

00:26:35.745 --> 00:26:55.605
one agent or employee agent gets delegated the first page, another agent gets delegated the second page, and the third agent gets delegated the third page, and so on and so forth. What this means is that it's faster because it's not sequential. You're not waiting for each step be completed. It's doing all of the steps at the same time. It separates context,

00:26:55.605 --> 00:27:00.965
meaning you get better results as well. So that it's not one agent doing everything.

00:27:00.965 --> 00:27:09.660
It's three agents that specialize in a particular role doing that role. So you just you get better results in general. Now inside

00:27:09.660 --> 00:27:20.735
of Claude, this is more or less what it looks like. You can say spin up parallel agents. K? And just it works out of the box. Like, you don't to preconfigure anything or install anything.

00:27:20.895 --> 00:27:26.495
You just have to type something like build parallel agents. And you can see here, Claude has delegated responsibility

00:27:26.495 --> 00:27:27.615
to three

00:27:27.695 --> 00:27:32.450
separate agents, one for the home page, about page, and contact page.

00:27:32.610 --> 00:27:38.370
The next thing is plug ins inside of Cloud Code, and these are skills that you don't have to build yourself.

00:27:38.450 --> 00:27:42.850
So if you recall, we were talking about skills like generating LinkedIn posts.

00:27:43.170 --> 00:28:00.090
The problem with that is that you have to actually develop the skill yourself. You have to tell it what you want and also what you don't want. With a plug in, somebody else built it for you. Okay? They perfected it, and then you are essentially using their finished product.

00:28:00.330 --> 00:28:04.410
Okay? So inside Cloud Code, you can type in slash plugins,

00:28:04.650 --> 00:28:06.490
and you have access to

00:28:06.730 --> 00:28:10.490
hundreds of different plugins that other people have built,

00:28:10.730 --> 00:28:19.025
um, that you can use out of the box. A good example is this front end design plugin that allows you out of the box to build beautiful websites

00:28:19.025 --> 00:28:34.920
immediately. The next concept is browser automation, which allows Claude to control your Internet or your browser just like a human would. So I'm actually not touching my computer right now, but you can see Claude has taken control of my computer. It's logging into an application

00:28:35.000 --> 00:28:35.960
automatically,

00:28:36.280 --> 00:28:52.615
then it's downloading my invoices, and it's gonna upload that into my accounting software. It does this once a month for me so that I don't have to do this kind of stuff myself. Now this is actually different than Claude just searching a website for you. It's actually taking actions in the browser

00:28:52.855 --> 00:28:53.975
on your behalf.

00:28:54.215 --> 00:28:59.040
How you can do this is by heading over to the plug in store again

00:28:59.360 --> 00:29:00.480
and downloading

00:29:00.480 --> 00:29:01.360
Playwright.

00:29:01.360 --> 00:29:06.240
K? And what Playwright is is it's a type of code that specializes

00:29:06.240 --> 00:29:19.605
in browser automation. Once you have this installed, you can just tell Claude what you want it to do. It will take control of your Internet and do the task automatically for you. The next concept is extended thinking inside of Claude code.

00:29:19.685 --> 00:29:22.805
This gives Claude the ability to reason before acting.

00:29:23.045 --> 00:29:26.405
So you have two modes, fast mode

00:29:25.590 --> 00:29:26.630
extended thinking.

00:29:26.630 --> 00:29:29.910
In fast mode, you might get an answer back really, really quickly,

00:29:30.230 --> 00:29:44.965
but the answer might not be as well thought out as if you gave it the time to think about how it should best answer your question. With with when you have extended thinking enabled, it's gonna define the problem, consider approaches,

00:29:45.205 --> 00:29:53.810
pick the best, validate, and then give you a well thought out answer. In order to turn this on, you can hit the slash command down here,

00:29:54.050 --> 00:29:55.650
and you can enable,

00:29:55.730 --> 00:30:03.090
um, thinking right over here by toggling it on. The next concept inside Cloud Code is checkpoints,

00:30:03.090 --> 00:30:58.480
and this is a powerful one in case you ever make a mistake. It's essentially the equivalent of the undo button. Okay? And what it allows you to do is, yeah, just rewind the code to a previous state. So as you're having a conversation with Claude, okay, at some point in time, it's inevitable that mistakes are going to happen. And when mistakes do happen, you have this button right over here, this backwards arrow on every single message. You can move up the conversation until you find the right rewind section, click it, and then rewind the codes at that point in time, and then it's gonna undo all of the mistakes that happened. The next concept is GitHub, and this is not technically Cloud Code, but this is something that everyone should know how to use if you're actually using Cloud Code. You can think about it like Google Drive for code. You can upload your code online to have it safely stored somewhere.

00:30:58.560 --> 00:31:05.435
And there's two major benefits for this. The first one is is if you're deploying, like, a web application online,

00:31:05.755 --> 00:31:22.560
chances are you're gonna need to deploy that code to GitHub first. And then from GitHub, you would deploy it online through an application like Vercel, for example. Vercel just allows you to publish websites online so anyone can view them. But the more important thing, in my opinion, is having a backup

00:31:22.560 --> 00:31:26.560
of all of your projects. Because the thing is, if you

00:31:26.880 --> 00:31:37.985
lose your computer, it gets stolen, it breaks, or whatever the case may be, and you just spent six months building up this project and then you lose that project, that would be absolutely devastating.

00:31:38.225 --> 00:31:42.625
Having GitHub means that you can upload your code safely as a backup,

00:31:42.865 --> 00:31:45.425
and then when it comes time to, uh,

00:31:45.970 --> 00:31:57.810
if anything happens, you can always just pull the code from GitHub back into your computer. Now how you do this is you would sign up for a free account on GitHub. You'd hit the top right corner, go to repositories

00:31:57.810 --> 00:31:58.130
here,

00:31:58.665 --> 00:32:00.265
click a new repository,

00:32:00.345 --> 00:32:02.585
and then name it whatever you want,

00:32:03.065 --> 00:32:06.985
and make sure it's set to private. Create the repository.

00:32:07.065 --> 00:32:19.910
It's gonna give you a snippet of code right here. You can just copy this into Cloud Code, and it should push or upload all of your code from your project into GitHub.

00:32:20.150 --> 00:32:23.750
The next concept is scheduled tasks

00:32:23.830 --> 00:32:38.315
inside of Claude code. So let me give you an example before we break this down. Let's say you want Claude code to run your entire email inbox. Every single time emails come in, you wanna automatically label those emails, whether it's miscellaneous,

00:32:38.315 --> 00:32:43.355
personal, website, you name it. You can have Claude at some interval,

00:32:43.435 --> 00:32:47.890
whether it's every minute, every fifteen minutes, every hour, every day,

00:32:48.130 --> 00:32:51.730
do a particular task for you. And this is a scheduled task.

00:32:51.810 --> 00:32:54.690
So what I'm telling Claude is every fifteen minutes,

00:32:55.010 --> 00:33:00.575
I want you to monitor my Gmail inbox and categorize everything. Create draft emails if necessary,

00:33:00.575 --> 00:33:10.655
forward emails, if it's an accounting email, and so on and so forth. So how we can do that is we can literally just come in to Claude, and we can say, schedule a task

00:33:10.815 --> 00:33:12.335
for every fifteen

00:33:12.335 --> 00:33:16.340
minutes. Okay? And what this will do is it will

00:33:16.500 --> 00:33:17.220
create

00:33:17.380 --> 00:33:22.820
a script on your computer that's technically outside of Claude. So it's on your computer,

00:33:22.980 --> 00:33:29.975
and every time interval that passes, whether it's fifteen minutes or hour, it will do the task that you have in mind,

00:33:30.135 --> 00:33:32.935
like sorting your email inbox.

00:33:32.935 --> 00:33:37.255
The next thing is the terminal inside Cloud Code. This is the last concept.

00:33:37.415 --> 00:33:50.590
This is, um, your traditional nineteen sixties terminal. I'm gonna actually close this and open the app one more time. So you can interact with Claude code completely from within this black box.

00:33:50.830 --> 00:33:55.790
All you need to do is type in Claude here. You need to trust the folder,

00:33:55.870 --> 00:34:01.285
and now you have access to Claude just in a different, um, in a different setting.

00:34:01.445 --> 00:34:14.150
So I can say, hey. It's gonna reply back to me. We have the slash commands over here. We can type in context, for example. It's gonna give me a response back. And you can do essentially everything that you could do inside antigravity

00:34:14.150 --> 00:34:16.550
just inside the terminal here.

00:34:16.790 --> 00:34:20.550
Personally, I don't like using this that much because, essentially,

00:34:20.710 --> 00:34:25.615
you can run everything in a way better user interface from within,

00:34:25.855 --> 00:34:31.695
um, from within Cloud Code. And almost all the time, you need to use the terminal.

00:34:32.095 --> 00:34:43.800
You can actually just ask Claude to do it on your behalf. Like, you don't have to open it up. You just tell Claude, hey. Do this thing for me, and it does the thing for you. If you ever need the terminal inside something like

00:34:43.960 --> 00:34:44.840
antigravity,

00:34:44.840 --> 00:34:56.495
Versus code, cursor, you can always come up come up to the top and toggle it. And now we have access to the terminal over here so we can do anything that we want from within the terminal. There's legitimately

00:34:56.655 --> 00:35:25.105
and it's rare, but there are some instances where Claude needs you to enter into the terminal. It can walk you through how to do it step by step when you're messaging it back and forth. You can open up the terminal, take the actions that are required, and then you're all set. That's it for this video, guys. Thank you for watching. I hope you found value in this. If you did, make sure to hit that subscribe button and that like button. I also have a free community where I give all of my YouTube blueprints away for free to automate your business and your life, and I also have a paid community where there's two transformations.

00:35:25.265 --> 00:35:35.185
The first one is for those of you looking to create your own AI automation agency, your business. I'll show you in the shortest time frame possible how you can find, close, and fulfill your first deal within thirty days or less,

00:35:35.345 --> 00:36:09.125
and there's hundreds of people that have made this work, even those without freelancing and business experience before. And the second transformation is for those of you who are business owners, I'll give you the exact blueprints that allowed me to scale to seven figures, automate 80% of my business using tools like Cloud Code. Now, obviously, you know, as you go through these transformations, it's not like a linear path. You're gonna have setbacks, and there are seven calls every single week where we can jump on together and talk back and forth to get you unstuck. And if you don't wanna have to implement any of this stuff yourself, I have an agency that can help you out with that entirely. So thanks guys for watching, and I'll see you