I've been avoiding Claude Code for

months. It seemed too technical and too

complicated. However, my friend Mark has

been begging me to start using it. He is

hands down the best person to learn

Claude code from. So, I brought him on

this episode to teach me how to use it

from scratch. And I'm going to be

honest, after this episode, I went down

the Claude Code rabbit hole and spent

the entire weekend building a system

that literally used to take me 20 hours

every single week. And I'm using it

right now. Here's what nobody told me

about Claude Code. It reads your files.

It remembers your preferences. And it

learns how you work. So, the more you

use it, the smarter it gets. And it

doesn't just give you answers, it

actually builds things for you and saves

them to your computer. So, by the end of

this episode, you're going to know

exactly how to set this up, start using

it yourself, even if you've never

written a single line of code, and begin

automating all aspects of your work.

Believe me, if you've been meaning to

try Claude Code, and start using it

yourself, but it seemed too technical,

this is absolutely the best video you

should watch on how to get started. So,

with that being said, let's get into it.

All right, what is going on, guys? I'm

stoked for this episode. Personally,

I've been wanting to use Claude Code for

quite some time now. I want to bring on

the goat of Claude Code in my eyes,

Mark. So, yeah, I'm hoping today we

could a get me up to speed using Claude

Code, get my audience up to speed, and

build something cool in this podcast.

So, yeah, happy to have you, Mark.

>> Yeah, of course. Uh, it's pleasure to be

here. I know it's been a while since we

last touched base. We were probably

>> more in the Vibe Code world before, and

now we're getting into the real Cody

world now. So, that's good.

>> Yeah, 100%. So, I'm stoked to see what

we could build with Claude Code. I've

never actually been able to build

anything with it. So, to kickstart this,

I want to ask one question, and that is

Claude Co-work just dropped literally

yesterday before we were going to film

this podcast. So, for my audience, what

do you think? Is Claude Co-work

something that replaces the need to

learn Claude code? Do you think it's

like an entry like gateway drug thing?

Like, give me your rundown on that?

Because I like to use you as a filter

for AI tools to see like, should I pay

attention to this? Is it overrated?

What? So, give me your rundown.

>> Yeah, for sure. You stole my

description, first of all, so let's make

that a disclaimer. It it is the gateway

drug. Up until now, the average person

looks at a terminal and no matter how

many times someone like me shouts and

screams and cries, we can't convince

people to hop in a terminal cuz there's

like this mental block that terminal

equals code. Code equals I don't know

how to do it, so I walk away. So this

gives you this kind of like top offunnel

taste of what cloud code can do. So

cloud code or co-work rather is is a

decent like adjustment to dealing with

more hands-on agentic workflows without

dealing with all the setup, the

download, the uh blinking cursor on your

screen if you're using a terminal. It's

still full of bugs, but it's still like

one big step up from using the normal

cloudi.

>> Gotcha. So we're not using inside of an

IDE, for example. Where are we using

this? We're using this inside of the

cloud desktop app, right? So that's

something that's like more accessible

for most people cuz a lot of people

might have clawed desktop downloaded.

You could just toggle between chat and

co-work mode instead of having to go

into your IDE. So I think it'd be

helpful to show kind of a little rundown

of what the UI looks like real quick and

then that'll segue us into our next

section of actually using cloud code to

build something

>> for sure. So this is what it looks like.

So on cloud desktop you have chat, you

have code and now you have co-work. So

the whole point of co-work like we said

before is they basically took the most

common non-technical things coming

through cloud code and made them

available as one-click buttons and when

you click on these buttons instead of

you having to think about the prompt it

does the prompt engineering for you. So,

if you say organize files, which is the

main use case everyone's going off on on

X, you can just say go and fix this

folder, you would tell it which folder

you want to work in. And then you want

to specify if you want how you want it

to organize it or specifically what the

name of the folder is. They give you

some defaults like my downloads folder,

my photos, some old projects, etc. And

then when you go through the process,

you can pick one of the language models

of choice and everything that's

happening will appear on the right hand

side. In the world of cloud code,

everything is very monotone and happens

one thing at a time. So if you do need

that aesthetic artifact look, then this

will help you keep track of exactly

what's happening.

>> Okay. So you're saying we could make

edits to our folders, organize folders,

all this stuff, create presentations

from folders, and then even spin up like

a UI, kind of like a vibecoded user

interface directly inside of the cloud

desktop app now using co-work. Right.

>> Exactly. So before you could already

create the vibe coded apps with

artifacts on their own, but now they

just made it that much easier to be able

to keep track of all the files, all the

contexts being used and you can still

use connectors and add connectors. So

you don't lose that MCP flare. You can

layer it on and not everyone's going to

need to reorganize the same folder 10

times. So you need to find better use

cases, right? These are just some

examples that people can wrap their head

around. But when you go through the

experience, for example, I tested the

crunch data. It will go to the folder,

come up with a plan, and you'll notice

that when you click on them, you'll get

this prompt here that says, "Ask any

clarifying questions." So, they're

trying to encourage you to encourage it

to think and plan before doing things to

lower the likelihood that you break

something. Cuz in cloud code, if you

don't know what you're doing, sometimes

you can completely nuke your desktop if

you're not actually prompting correctly.

>> Yeah, that makes sense. Okay, so now

let's segue into actually using Claude

Code because obviously Cloud Codework is

good for super nontechnical people. I've

been playing around with it. It's been

great so far. It's been a good entry

into Claude Code, but I want to know

like does this get you like 90% of the

way? Do you think it gets you 50% of the

way? Where do you think it kind of

leaves non-technical people when it

comes to cla?

>> If we extend the analogy of the gateway

drug, key emphasis on drug, this to me

gives you 30 to 40%. This is not even

close to the firepower of Claude and

it's full of bugs. Why? Because they

used Claude code to vibe code it in the

span of a week. So the actual anthropic

team admitted that on X. So with any

vibe coded app, as you'll be familiar,

and I'm familiar, you're going to have

tons of bugs, especially when you go to

production, go to thousands and millions

of people. Tinker with it, play with it,

know that there's bugs, but this is only

meant to be the taste of what you get

with full firepower.

>> Got it. Makes sense. Cool. Cool. So, I

want to move on to a couple questions

before we actually go ahead, show you

how to download Cloud Code, and then

actually build something with it. Um,

Mark actually built something for me, a

cool use case I've been wanting myself.

And we're going to go through kind of

the step-by-step process, how we did

that, and then also the the finished

product of that. So, my first question

for you is like what's the biggest

misconception with cloud code? Cuz when

I hear that, I think, okay, if I'm not

coding an app or using it in my coding

environment, what's the point of using

cloud code? So, kind of break down what

the biggest misconception or, you know,

few misconceptions you see are. Yeah. So

obviously it was a platform originally

designed for developers which is why

they called it Claude code. But over

time a lot of non-technical people and a

lot of non-technical use cases popped up

which in my opinion I talked to a lot of

people I say they should have called it

claude creates because then it could

create code and artifacts. But the

misconception is that you only use it

for development or building code or vibe

coding. In reality, because it has

access to your desktop and your files

and you can create a local uh database

that runs on your computer, which we

will show you today, it can do whatever

you want. Like the limit is your

imagination and your ability to just

like learn by osmosis. So when you ask

it here, go to the nano banana API, make

an a thumbnail of me for YouTube, it can

go research, look for the nanobanana

API, tell you, hey, listen, I need an

API key. here's the URL to go get the

API key. Give it to me and we'll go from

here. You're going to see Python on

screen. You don't have to engage in that

Python. You just have to be aware that

something's happening to make that

functionality work. So, the less you are

worried about what's happening on screen

and you kind of take a peek at it. Even

if you're not technical, you will start

to see little patterns by osmosis and

you'll be surprised in 3 6 9 months

you'll be able to upskill yourself by

accident.

>> Okay. Yeah, I love that. And then I

guess my next question would be do you

have any like non- techy success stories

of like somebody because you run a

pretty big I wouldn't call it a claude

code community but your community is

built like a lot of your users in there

or your community members are wanting to

know everything about cloud code and all

the use cases you find for it. So do you

have any like non-technical like

whatever just somebody who might be a

bit archaic when it comes to technology

going from complete beginner to actually

being able to build useful things with

it?

>> Yeah. Yeah. So obviously I have a

mid-tier kind of size community, but we

get a lot of non-technical people coming

in that have decided that's it. I am

going to dig my heels in. I'm paying for

the max plan and I'm going to build

stuff. And we recently had someone

that's actually 70 years old, retired,

basically built a full mobile app in the

span of 3 or 4 months using Annaiden and

Claude Code. And stuff like that gets me

as a like a super nerd super excited

because I love seeing that progress and

people shattering limiting beliefs

because people will always come in who

are not technical and say, "Hey, listen.

Do you got something for me that's not

clawed code? Can I just use like chat

better cuz they're just so afraid of

just like leaping in and running into

those first issues." But as soon as you

get past that hump where one, you've

downloaded it, two, you go by trial by

fire. You try to build something and

something doesn't work. And then you

realize that you could technically ask

cloud code in a virgin window to help

you fix cloud code and you understand

this little feedback loop. Then they're

unchained. And then once the imagination

is open, they start building from very

minute use cases to things that they're

proud of and then just stacking those

skills on top of that.

>> Yeah, I love that. And that you just

literally explained me. I haven't used

cloud code because it just whatever I

have the like this mental barrier about

it. And I had that in the beginning with

AI in general and that's why I created

this YouTube channel to like show

nontechnical people you can use AI tools

and actually become like a speaker of

that language so to say. So yeah, I I

love that. Going on a little bit like I

guess my last question here before

diving into showing how to download

cloud code and then actually building

out our use case for this. What do you

think a downside or the downsides of not

using cloud code are now? cuz it seems

like this is where the AI space is

going. And just like if you want to be

able to like 10x your productivity, 100x

whatever like do you think we're if

we're not using cloud code, we're

missing out on opportunity here and it

might not be just claimed

could be kind of like a transferable

language we could use for these other

tools. So what do you think the

downsides of not learning this is?

>> Yeah, it's good that you gave that

disclaimer cuz I was going to give that

disclaimer to your audience. One, this

is not a Cloud Code shilling video. I

like to use Cloud Code cuz I've tested

multiple products. It's the one that I

resonate with the most with my

development style. But you do have

cursor, you have windsurf, you have open

code now, which is becoming competitive.

I think they have like a [clears throat]

million active users that are using open

source models. You can use whatever you

want. It's the idea that you use

language models in a terminal where you

are devoid of all these little pretty

icons on a UI and you go straight to the

source. That's the theme of this

episode. So I think that if you don't

opt into the terminal world, not

necessarily the cloud code world, you

are missing out because you are going to

the source. So when you go to the

source, you realize it's kind of like

waking up from a dream. You look around

at like 90% of AI tools. You're like,

"Oh, I don't need these. I can cancel

hundreds of subscriptions." And I

canceled a few months ago $1,200 a month

worth of subscriptions because I

literally realized I didn't need it

anymore. If I wanted to compress videos,

I don't need to pay for the service that

does it. I can just tell it and it

creates a Python script that does it for

me. You can start to tackle each

subscription of your time which is why I

can justify my very expensive

subscription to cloud code. So it's a

matter of using it from day one for ROI

heavy activities.

>> Got it. Last question. I lied. My last

one's not my last one. So what's like a

use case that you've built yourself that

you use for cloud code that like you're

hands off. It's saved you a bunch of

time. I know you and I have talked off

camera about it. So what's like one

thing you've built where you're just

like this used to take me hours or used

to take a team member hours and now it's

just kind of done with cloud code.

>> Yeah, there's one thing that not wasn't

possible but would be super painful for

me to do with the little time that I

have. And there's one thing that was a

major unlock. So the major unlock was I

have a YouTube command center which is

unbelievable. Now it's taken me probably

I've put in 100 hours into this command

center where I go back and forth and it

goes and looks at like things that are

trending, things that are new. We have a

bit of a conversation and then once we

land on a topic I kind of give it my

ideas where I want to take it and where

I want to go and then from that idea it

goes and creates 15 thumbnails very high

quality. It takes images of me

transforms them to go with that

thumbnail. Creates a thumbnail brief. It

creates an editing and a script brief

for my editing team and creates SEO

tags, titles, descriptions, everything

from one input. Which is why for me once

I started on this drug I got addicted

because once you can have one input and

you have not infinite but many outputs

as a result of that one that is the very

definition of leverage. So once I did

that every part of my life I started

creating what I call command center. So

this is my copywriting command center. I

started on LinkedIn. So I wanted to

understand how do I write copy on

LinkedIn without using AI but like

understanding the principles. How do I

do a crash course on everything? Let's

create a command center. So creating

those command centers helped level me up

because even as a developer, I get to

learn things I would have never been

exposed to otherwise.

>> Yeah, 100%. Being somebody that makes

YouTube videos, literally I spend 15

plus hours a week probably on this and

that bottlenecks every single other

thing when it comes to like my business.

Like my creative mind is not working cuz

I have to go and I have to come up with

these thumbnail ideas, title ideas. I

think one thing, and I could be wrong

here, but what sets it apart is you're

not just like saying go off and do this

thing and it does all of it. You have to

play around with it because if you

didn't come to that like idea or you

know whatever the title was going to be

like you had to kind of play around with

it to get that title. You know what I'm

saying? Instead of just saying hey go

create a title for me on whatever

whatever you think is going to work

well. So you have to have a little bit

of that back and forth. But I think once

you have that solidified it then could

take it and run with it and go ahead and

you know create those thumbnails for you

and whatnot. So it's really important

for your audience cuz you just made an

amazing point. There's this trend right

now about this thing called the Ralph

loop right. It's a very mind-numbing

thing for most people that are not

developers. It's basically this fantasy

that you just give tasks and you walk

away, go to the beach, and you come back

and a bunch of tasks have been executed.

It's one thing to execute a 100 tasks.

It's another thing for those tasks to be

meaningful and derive actual value. So,

if you spun up and you said, "Make me

a,000 thumbnails and a thousand titles,

but 80% are garbage." That's like a net

loss. You lost the money on the token

usage. You lost time and wasted effort

and electricity. Human in the loop plus

cloud code is the most OP combination.

>> We're going to clip that for for the

intro of the video cuz that Yeah, that's

fire. Cool. So, now that's a perfect

segue into showing what we're going to

build cuz we're going to build something

pretty similar. I guess real quick

before doing that, we should show how do

you quickly download this if you're a

nontechnical person. Where do you do

this? How do you do this in like 2

minutes? Let's show that and then we're

going to go into the build and show what

Mark built us.

>> All right, sounds good. Okay. So, when

you go to the beautiful domain

claw.com/rouct/claw-code,

you'll see something like this. And yes,

it is a terminal, uh, resist the urge to

cry, all you have to do if you're

non-technical is you just use this one

command in your terminal. And if this

immediately gives you an error, most

people, many people paste this, there's

some form of error because maybe your

computer's different, your environment

is different, there's something that

needs to be reorganized to make this

possible. If that is a barrier to you,

you can install something called warp.

Both of us not affiliated. It is a

terminal that you can run pretty much

for free. It has some AI in there with a

little a free tier. You can just tell it

that same command. You copy paste this

specific thing right here. And then if

there is an error, it will say there's

an error, but instead of passing it back

to you to figure it out, it will go and

figure it out for you on your behalf,

ask for permission, and then install

Claude Code for you. And then once it's

done, you will see your little amigo and

it will pop up. You'll see something

like that and then you will be good to

go. You'll see a screen just like this.

>> Perfect. Easy enough.

>> Yeah. So, this will be your highway.

Again, not affiliated, but it's a free

way to one, use a terminal if you ever

need to install cloud code, remove cloud

code, update cloud code. Really good

way. And you can do it for all kinds of

things. You can even ask that, by the

way, to organize files on your computer.

All of these IDEs, as long as they have

access to your computer, you're good to

go. So that's the installation part. Are

we good to jump into the concept?

>> Hold on. Before you go to that, let's

talk about where users are actually

going to begin interfacing with cloud

code.

>> Yeah. So you can use this in any

terminal. You could use warp like I

showed you. I like to use it in cursor.

You can use anti-gravity. There are so

many IDEs that I haven't even mentioned.

An IDE is just an editor. You can just

open any terminal and once you have this

installed and you use the magic words

claude, you should see your little crab

icon friend pop up and you're good to go

from there.

>> Perfect. Easy enough. Cool. Now, let's

move into let's talk about a what I want

to automate first and then we're going

to show what we actually or what Mark

actually built after that. So, let me

I'm gonna go ahead and share my screen

now. All right. So, looking at my

screen, what I want to automate is my

short form content. So, for some of

those people or majority of you guys

that don't know, I've been kind of going

hard on short form content. This is a

goal for 2026. I really want to tap into

this platform here both on Instagram,

YouTube shorts, and Tik Tok. All right.

So, about a week ago, I had this video

right here go absolutely bananas. It's

got about almost like 825,000 views,

bunch of engagement, and I've actually

grown. Like, I had about like three or

400 followers before this. This singular

video is like unlocking this whole new

channel that I could tap into. And

again, this is a huge goal of mine going

into 2026. And then here's a YouTube

short, too. I posted this 3 days ago.

And this one, I'll just refresh, is

absolutely running. So, the goal for

what I want to build is I want to build

out a system that could help me automate

this and so that way I don't need to be

super hands-on with it. Cuz right now, I

have somebody that's actually writing

scripts for me. I have to approve these

scripts. I actually go and I analyze

what videos did well so I could try to

recreate that success of that video. So,

if I had a clawed code system that I

could just like have on autopilot or I

guess I, you know, there'd be a little

bit of human in the loop there that

could just help systemize this process

for me, that would be absolutely like

the most valuable thing ever. So Mark

actually built that out. So let's go

into a little bit more about that.

>> Yeah. And if you see on screen there

before he unshared the screen, he had 89

cents from that video. So in exchange

for 89 cents that he's paying me, I

built the system for him and show you.

>> So let's get into it. Conceptually for

the audience so I don't lose you. Core

concept is Brock, like you said, wants

to go celebrity mode on short form. We

wanted to focus primarily on Instagram.

So the number one way we need to do that

is scrape. Now if we just ask ask claude

code go and scrape Instagram that is a

very mammoth task because there are many

proxy layer security all of these things

and to actually do the scraping we're

going to use a marketplace called appify

you can think of it as the app store

where you can take tons of scrapers

there's ones literally designed for

Instagram Tik Tok what have you and you

can essentially lease them or rent them

to execute your tasks for a small pay as

you go fee so we're going to use that

we're going to store it in a database

and then we'll use that to help create

those ideas for Brock. So again, we're

going to focus primarily on Instagram

and instead of paying 10 bucks every

single time like you're used to doing

using platforms like Lovable and Bolt

and what have you, we can just use

something called SQL Light. And what

SQLite is is literally a free database

you can run locally on your computer.

This frees you because every time I had

to experiment before I would have to

shell out another 10 bucks of Superbase.

So this lets you build Vibe code for

free and if you want to go to the next

level and then upgrade to Superbase

that's always something you can do

after. So that's the database we'll be

using and in there we'll be posting or

hosting things like the creators the

posts and the hooks that we scrape. In

terms of the workflow if you remember

before my YouTube command center I have

one input many outputs. In this case,

Brock just wants to say the words make

me viral as one command and then after

that write a topic or a link where

Claude can go and read about whatever

the tool is and then generate 20 hooks.

Then rank those hooks by a virality

score. That virality score I'll talk

about right below and then we'll pick a

top three and then create captions for

that. Bro can have one input, one idea

and then have multiple outputs.

>> Wait question. So go go back up a little

bit. So on the topic side of things,

context is really important here, right?

Cuz if I give like a little short

paragraph of what I want the context to

be about, it's probably not going to be

the best output, right? It's not going

to generate the best hooks cuz it's not

going to have context or will it take

that then do some web searching and then

like find the right amount of context

and then use that or like am I wrong

there? Could you break that down for me?

>> No, no, for sure. So the first time you

use this, everything we're using is a

language model. Language models are not

magic. They're not super intelligent.

They look for patterns. So if you say go

look at this claude code or co-work

feature and here's the link and you say

nothing else and there's no preferences

or examples of how Brock writes his

scripts, it will go and look at the

database where we've scraped other

creators and be like okay I think I'll

do a remix between the different

creators and my knowledge about writing

hooks as of I don't know 2024 or 2025.

That will be your first output. Then as

you iterate and say no no that's not how

I like to write hooks. Here's the

example of this 800,000 view video. Try

to mimic that style more and tell Claude

MD, which is like the command center

brain to update that in its memory. So

that's how this incrementally gets

better.

>> Got it. Yeah. So it's just going to

literally just get smarter and smarter

and smarter the more I use it

hypothetically, right?

>> Yes. As long as you keep telling it,

listen, um, this time this was your

mistaken flaw. Let's commit to memory to

avoid doing that moving forward. So you

have to be proactive in making sure that

it learns

>> 100%.

>> And when it comes to the virality score,

we kind of just made this up. Brock and

I just to come up with something there

would would be some criteria. So this

virality score is based off of

curiosity, emotion, brevity, relevance.

Relevance being like how trendy is the

topic, which on short form, even though

I'm not a short form guy, seems to be

really important, right?

>> And then you have uniqueness and

platform fit. These ratios could be off.

So these weights could be updated. You

just want to be able to design the

system. So if you need to update them,

you can. And then this leads to the

overall preview of the process which is

you scrape competitors, you get some

inspiration, maybe you add your own

examples as well. You have some

razledazzle. You generate the content

and then the final piece of the life

cycle which we won't cover in this

video, but we c you could do later on is

after you create the thing, tell it to

go scrape your own Instagram to see how

did it do. So it can actually learn from

what went well and what didn't go well.

That's where you have that full feedback

loop.

>> Yeah, that analyzing part is the part

I'm most excited about honestly. like

scraping the competitors is great,

coming up with ideas, understanding my

hook style, all that stuff, but like

analyzing what works because really what

I've noticed at least in short form

content, you find the like the hooks and

the like the format of what works and

just double down, triple down on that as

opposed to trying a whole bunch of

different things, seeing what works and

once you find something is really

important. That analyzing part of this

is what I'm probably the most most

stoked about.

>> Yes, sir. Yeah. So in terms of the

links, these are the links that Brock

provided to me of different creators he

wants to be inspired by on the short

form side. So these were we'll revisit

these shortly. And in terms of the

actual build, one thing I like to do

again cuz I am lazy is you can use

whatever research tool you want. In my

case, I like to use Perplexity Labs.

It's this icon right here. They have a

pretty generous free tier as well. And

what it allows you to do is give it an

idea. So for me, I just use Whisper

Flow. I just go off for like five

minutes about what I'm trying to build

and then I throw that into something

like Claude or Chad GBT and tell it can

you make this into a more refined prompt

for something like perplexity labs and

then we get something legendary like

this where there's no way I would have

actually written it myself where we

won't read the whole thing but it just

says act as an expert senior product

manager and/prompt engineer. I need you

to write a highly detailed mega prompt

designed for the absolute latest most

capable version of cloud code available

today. Why do I say this? I want it to

know about the latest advancements in

cloud code so it can refine the prompt

accordingly. So I don't have to worry

about what changed in this version, how

should I talk to it now. It does that

dirty work for me and I say please use

your browsing capabilities to verify

exactly what version is the

state-of-the-art. And then I tell it

what the goal is. We want to do a

competitor scraper. We want internal

analytics. We want a command center uh

dashboard later on, not a priority. And

then we go through the workflow. So once

I do this, it comes back if we zoom back

out here with a sample prompt. And I

tell it, can you just make this into a

markdown file so I can just drag and

drop it into a brand new virginized

claude folder? It's not even a cloud

folder. It's a folder that you import

and use cloud code to read what's in

that folder.

>> So you're just you're just adding that

to like your a folder on your desktop

essentially. It's as simple as that.

>> Literally just to show your audience,

you'd go open folder.

>> Okay.

>> You'd create a new folder and then when

you open in cursor here, you'll have

absolutely nothing except the name of

the folder. This will be empty. So for

me, this is where I drag and dropped the

exact file I just showed you here. This

was the only file in my cursor and

nothing else existed. Everything else

came about from using cloud code.

>> M yeah, easy enough.

>> Yeah. So this is the foundation. Now I

should have been a bit more intentional

to go through the prompt and make sure

that all the features that AI came up

with are the ones that I care about, but

I use this to do this quick and dirty.

That's that. In terms of Appify, one of

the scrapers will rent is called an

Instagram post scraper. This one scrapes

the actual posts, captions, etc., but it

doesn't take the transcript of the

Instagram videos themselves. If you

don't feel like going and shopping

around to see which app in this Appify

app store can do that, you can use their

MCP server that can just go and navigate

their database for you. So, if you tell

it, listen, I need to do X, Y, and Z for

the cheapest cost, you will go look at

all what are called actors in the app

store, pick the cheapest ones and the

ones that are most highly rated and

recommend those to you. And then you

build your workflow after.

>> Yeah, that makes it so easy. Got to love

the MCP.

>> Yes, sir. And then in terms of using and

installing the MCP, this is where

non-technical people might just tap out.

They made it easy as well. So, if you

just go to mcp.appify.com

exact URL, you'll see something like

this. You can pick what matters to you.

I would just click on things related to

data storage. I would just pick

everything if you're just starting out,

you don't know what you're doing. And

then at the very bottom on integrations,

all you have to do is pick on something

like cursor or cloud code. And then it

will give you the oneline command. And

if you click on add API token, it will

put a placeholder. All you have to do is

go and get your appy API key from your

account, which if you go to your account

is literally right here. You grab this,

you paste that exactly in here, right

there instead of these little curly

brackets. You take this command, you

open a brand new terminal session with

cloud code, and you paste it. So, I will

show you in one second after I block my

API key what it looks like and we'll go

from there.

>> Yeah, I got one thing to say on that cuz

I've used Amplify in the past for

certain builds and edit end for example

to try to create the same thing. And

finding an actor that actually works

sometimes was a pain because it worked

in the past and then something broke and

it wasn't up to date. They weren't like

servicing it, whatever. I don't even

know. But I think the MCP thing makes it

so much more simple. And I'm glad that

you brought that up because then it'll

just go ahead find which one is working

right now. So you don't need to go and

do that yourself.

>> Or it will actually just test them. So

it'll run it. It'll be like this one

sucks. Let me go search for another one.

This one sucks. I'll go search for

another one. It will do the dirty work

for you, which is why I like that. So

this is what it looks like in cursor.

Obviously I have blocked my API keys. I

pasted that exact command I showed you

before. So that claude MCP add ampify. I

just had to add my API key right here.

And then it went executed that command

and then it comes back at the bottom

saying successfully added. And all you

have to do is restart a brand new

session in cloud code and it will take

effect. And I'll show you how you can

verify that you have that MCP server.

When you have a brand new tab, you just

have to write MCP and then put MCP

status. You'll see right here we have

this connected. So we know we are in

Valhalla. We are good to go. We are in

the promised land and beyond that all

you have to do is I just said are you

able to find this? So I told it go and

look for this appy scraper. I just want

to double check it's working. You can

see right here as soon as you see this

little green icon and you see mcp

something the mcp is working. So it

found it and it tells me about it. It

tells me about the success rate the

total number of users which is awesome

cuz like Brock said it's always aware of

what is being used. So, it can rank the

actors by usage and success rate. And it

tells you what it does, the pricing, the

input parameters of what it needs and

what you can offer it. And then I said,

can you can I scrape the transcript of

videos? And it says, no, you can't,

which is where I discovered that. So, it

can do metadata, performance, but it

can't do that. So, then it went and

found three alternatives with their

respective su success rates and their

pricing, which is why this is so

awesome. It's very hands-off. You are

the boss, and it tells you what is the

best choice and why. Once we do that, I

say, "Cool. Can we test it on this?" We

take Nexv's short form. We ask it for,

let's say, the first three videos. It

doesn't work. And then it hangs. And

then I basically try to understand why

is it hanging until it finally comes

back with the following. So this is the

caption. This is everything about that

video. So I'm like, cool. Now we're

cooking with gas. We try a few more

posts and I I say, can you try three

posts at once and see what happens? So

the first one works perfectly. You can

see right here, this is the source URL.

If I scroll to the very right and I grab

this, you can see, let me see, right

here. 0 to 40 seconds, 0 to 8 seconds.

Okay, stop building your automations

from scratch. Instead, use this AI tool.

So now I know, cool, that is a script.

And our next job at some point will be

how do we extract what we think is the

[music] hook? Because short form is

short. So how do you know which one is

the hook if you don't see the first 5

seconds or the first line or the first

two lines? So, there's going to be some

judgment there and there's some nuance

which is why this is not perfect. One

thing I did notice is that the MCP had

an aneurysm and when I tried to make it

do three at once. So, it turns out at

least for this actor, it needs to do one

at a time, not all at the same time. So,

once it did that, it was able to do one

one and then we were good to go. And

then you can see right here, this is the

transcript that comes back from each and

every video along with the original URL.

So, that's kind of like the end of the

first session. And I basically say the

following because every session in cloud

code is a brand new blank slate for the

most part outside of whatever you have

in this file called cloud MD. You can

think of claude MD as your memory bank.

The same way you'd have memory and

chatbt. The one thing that we have to

know is I don't want to have to go

through every single time with blank

screen and say go and get me the

transcript of this video for it to have

to go in circles to realize one it

doesn't have one actor to do that. It

has to do two of them. And then two that

it has to do one at a time. So instead

of me having to worry about that, I just

say take note on how you're able to

scrape these transcripts and what actors

you used and create a claude MD file

that I would have a full understanding

of how to execute this. So I don't have

to repeat myself each and every [music]

time. So you didn't even usually like if

you're interacting with like AI chatbt

claude whatever you'd say that like oh

give me a prompt to use to then always

know how to perform this task but inside

of cloud code this is like what stands

out to me is it literally went and

created that we could call that a skill

right is that considered a skill in

cloud

>> I won't I won't let you say skill

because that'll that'll be misleading so

>> it's not a skill it's just it's creating

this

>> knowledge base

>> knowledge base let's call it knowledge

base yes

>> okay got it yeah that's cool it

literally created that file instead of

just giving like a prompt that you would

usually get that you'd have to you like

save somewhere in your notes, use it

whenever like when you know whenever

you're using a custom GPT for example

but

>> yeah and if you click on it they make it

like a hyperlink especially in cursor

you can see like top priority is like

the make me viral command that's after

we actually built it out but if as you

go through it takes notes on the

different data models you have the hook

ranking algorithm we ended up making

everything that it needs to use so he

has a section here on actors used so now

it knows this is the app ampify actor

name this is the cost and the second one

we used to actually grab the transcript

of the video is this one. So it keeps

that running memory which is why this

[music] is powerful

>> and ideally it's going to be way quicker

every like at least after that initial

time because now it knows exactly what

to do so it doesn't need to go through

this treadmill thought process of trying

to figure it out.

>> Yeah. So if you compare it to something

like a chatbt, every single time you

fail in chatbt, if you don't if you

aren't proactive to go and document and

avoid it happening, it will keep

happening over and over again. But in

cloud code, every time something doesn't

go as planned, you can say go and learn

from this mistake as soon as you finally

get to the point where it did the right

thing. That's where you have that

feedback loop. Now [music] to make this

a lot more tactical, this session was

about executing the plan. So for me, if

you go to here, this is the plan. This

is an adapted version of what I created

in Perplexity Labs. This is the

original. And what I asked for in a

separate chat was, can you make this

thing instead of just a list of feature

requests and a wish list, can you make

it into a plan and make it so that there

are checkboxes so that you can keep

track of what you're doing as you

accomplish each task? Now, why did I do

this? One, it's no secret that Claude

has a context window as of this

recording of 200,000 tokens. MCP servers

actually take a lot of that. that. So,

it can take anywhere between 2 to 15% of

that session. So, instead of me running

into a maxed window every single time

and worrying about that, if it keeps

checking off what it's completed, I can

always go back and be like, listen, go

pick up where you left off on the plan.

So, I can see like, okay, cool. I

haven't started phase 2.3. Let's keep

going from there.

>> Yeah, that makes sense.

>> Yeah. [music]

So, that's super helpful, which is why I

ended up creating this plan. And the

plan, you'll see right here, as it

completes things, it will tell you this

is completed, this is not completed, and

it'll keep editing the source plan until

we're good to go. And you can see here,

it's using the MCP server to test out

again the different appy posts,

scraping, and then if we go to the very

bottom here, it's using and creating

what's called the SQLite database. So,

like I said before, if you click on

database and click on short form, this

is what it looks like behind the scenes.

So, you don't need to use a superbase.

It creates all of your database for

free. You can see all the columns here.

And if this is too ugly for you, I had a

separate chat where I said, can you make

it so that we can have some form of UI

to look at this. So this was the chat. I

said, can you make it so we have UI? I

hate looking at it here. So I talked to

it like my friend and you can talk to it

as well. And you get something like this

where you can click on it and when I uh

load it back up, you'll be able to see

the different tables like hooks and

posts, etc. That's basically you'll be

able to interact with it on a browser.

>> Yeah. much easier to look at than the

the IDE that we're looking at here.

>> Yeah, it's basically like having a

Google sheet on steroids. And the most

important thing, like I said, is it's

free. So, one thing I wanted to do now

is put everything into practice. And I

noticed that we encountered a bug. I

thought that things were running super

smooth. We have the MCP. It learned how

to scrape. And I started storing things

in our database and started creating the

viral hooks algorithm so I could create

this post creator. And then I realized

that there was one fundamental flaw. And

I'm just gonna wait to just pull that up

so your audience doesn't have to watch

me scroll.

>> Yeah, sounds good.

>> Okay, so here at some point I realized

that it was making a fundamental

mistake. It was scraping everything, but

it would put the caption in the

transcripts column. And you might say,

why do I care? Well, you care because it

was training on these hooks that were

actually the caption. So, it learned to

say, "Comment X and I will send you Y

instead of the actual hook of the

videos." And I got confused because I

started getting tens of hooks that all

started with comment Y for X. And I'm

like, this is not a hook. So then I went

to look at the database and I'm like,

you literally put the captions in the

transcript and you never actually

captured and saved the transcript. So at

this point, that's why I said I just

noticed that your hooks are the

captions. This is wrong. So it went

through, it deleted all the things uh

that were incorrect. And then it

reloaded and went through and just kept

only the posts. And then we start adding

on the transcripts. So when we finally

go the the next step, which is okay, now

that we have transcripts in there, we

come up with the virality score, it goes

through and it creates like a ranking of

all the posts in the database. So if we

go to the database and you check the

scores, you'll be able to see that

they're actually implemented and

calculated on the fly. So that allows us

to do the following. If I go into here,

so if we say make me viral, this new

feature, this is the command that in

claude MD, our memory bank or knowledge

base as we've now call it, I just said

go and look at this feature and come up

with material. You'll notice that

despite that, we still have a couple of

them that were biased from before. I

think Claude MD did hadn't updated yet.

It says comment co-work to get free

access, but we still did have some real

hooks for the most part. So 8020 80%

were actual hooks, but we still wanted

this to be 100%. So

>> here, go up one more time.

>> Yeah,

>> I want to point one of these out. Like

for example, number two, that hook

pretty solid. Claude just became your AI

co-orker that actually finishes tasks

without you. Like that's something that

I would actually use in one of my short

form videos. So that's I mean goes to

show that it's at least working.

>> Yeah. And maybe you could use the

comment coowork in the caption. This is

solid for the caption as long as it

knows what to do. But I just wanted to

show this because it's important to know

that especially if you go on X,

especially the dark depths of X, people

will say this thing will replace

software engineers like remove

everything from existence. It still

makes mistakes. It should have been

smart enough. If it can use an MCP

server to see what actor we need, it

should be able to look at it and be

like, oh, this is probably not a hook.

But you have to be aware that like you

can't just go off to the beach and come

back and expect good results, especially

if you're not a non techie. So human in

the loop watching this is essential.

Yeah, that's like the key word for this

episode, I think, is human in the loop.

Because otherwise, we could build out

this system if we're not constantly

iterating with it. It's probably not

going to be the best. So, that's why

this is a good starting point for us and

for me to start using. I'm excited to

see what this looks like a month after

playing around with this, having to test

out different videos that I post and

giving my thoughts and, you know, kind

of expertise on it.

>> Yeah. And the thing is, you can go much

deeper than this. So, right now, this is

the scoring algorithm where you can see,

right, like we said before, curiosity,

emotion, etc. It's using its judgment

like Claude is going through and ranking

everything that we have in our database

with a score. Brock can look at this and

be like, "No, you are so wrong. That

last video was a complete flop or this

video did incredibly well." So, this

will take tinkering. And if you had vibe

coded a front end, every single time you

would change the way you the the process

flows and the automation flows, you'd

have to go and rework the UI to match

it. So, that's where like the UI and

everything that we focused on for the

past year, which is, oh, cool. I just

built a clone of X, it's not about the

clone, it's about like what is beneath

it? What is the system underneath it? So

when Brock spends a couple weeks until

it's actually really good, then he could

ask, cool, can we just spin up a UI and

maybe we'll use Gemini as the LLM to go

do the analysis or Anthropic or whatever

to execute everything that we've been

doing in the terminal. So in a way you

you leave the final part for last where

if you have a UI, if you have a product

of your own, it's now fully polished.

That's actually like a super good point

because I was going to say looking at

this viral scorecard thing here. I was

like, man, this just seems like a lot of

numbers. I'd love if it were in a

dashboard. I was literally going to

mention that, but that's such a good

point because if I don't have this thing

dialed in, so to say, like right now,

it's just going to be a pain in the ass

having to go back and forth and try to

vibe code. My audience knows how to vibe

code and how it could be such a pain so

many so much of the time. So, yeah,

that's interesting. I'm excited to see

what it looks like when it's an almost

like its own little mini like internal

software that I could use instead of

having to use something that might be a

little bit more intimidating like cursor

or something like that.

>> Exactly. So, and then the whole point is

that it gives you all of these as

outputs. So, it tells you now as a top

three hooks. So, tells you why it's a

hook, why it's a good hook rather. So,

this one Claude code just gave

non-coders. Lily picked the same one, by

the way, that you said is a good one,

which is interesting that it agrees and

it comes with the rest of them. Still

has this weird comment thing you would

have to remove from it. And then it

comes up with the captions. And what's

funny is it wrote the captions as as

these. This changes everything. It

doesn't have the comment

>> even though that's the hook, right?

That's uh Wait, would that be the hook

or like the script? I mean,

>> I think it could be a caption, but it's

interesting that I didn't put the

comment X or Y, even though we it's very

prevalent in the small data we have. So,

there's a lot of nuance here. This is

super.

>> However, this would be really sorry to

cut you off, but this would be super

easy for me to give cloud code one

prompt and say, hey, listen, for every

or for every description or yeah, I

guess it'd be considered a description.

I want it I want to use a keyword where

it says comment X, I'll send you Y. And

then it'll fix that. Now, every single

time I use it, it'll like understand

that, right?

>> Yeah. And even better, since we have the

Ampify MCP already used, you could say,

"Can you go on my Instagram, look at the

top five performing ones, go grab my

style of captions, and go grab my style

of hooks on the ones that performed

well, and in the database, I want to

change the score. Now, I want to add a

Brock uh waiting where if it's a hook by

me that did well, I want you to weight

it higher than the other creators cuz

other creators aren't me. So, this is

where the nuance comes in and instead of

you obsessing on updating a front end

and some button not working and you

spend an hour fixing the button even

though the process needs to change, you

focus on the stuff that actually moves

the needle.

>> Yeah, this is this is great, dude. This

is honestly better than I thought it was

going to be if I'm being completely

honest with you. Like, I'm stoked to

play around with this.

>> Good. Good. Okay, just everyone in the

audience, this is a process. And the

thing is, if you use something like an

anti-gravity or a cursor, this is my

special weapon is obviously you're

dealing with claude here, but let's say

you need virgin eyes on your your code

or anything that you're generating, you

can always bring in cursor for free for

like they have a pretty generous free

tier as long as you don't use max mode.

And you can be like, cool, what does

codeex or GPT 5.2 think about my system

to generate hooks? So you can bring in

different advisors, if you will, to take

a look at the same codebase, whether

you're vibe coding something or just

producing something at scale.

>> So you're saying as these models get

better, you could then use that as

almost like the orchestrator to

understand how could I optimize this

kind of is what you're saying.

>> So let's say you actually ended up

building this UI and for whatever reason

cloud code wasn't cutting it. It just

wasn't getting you. Maybe you bring in a

virginized expert in the form of Gemini

3 Pro and you say, "Hey, look, both of

these share the same codebase. So this

codebase, anything that's in cursor can

see this. So cloud can see this and

anything in cursor can see this. So with

that, you can go like in ask mode and be

like, listen, can you take a look and

give me advice on how I could structure

this better? Or even more hacky, you

could say, go and search the web for

best practices for prompting cloud code.

Can you help me draft a prompt that

would fix this problem that's happening

in my codebase? And then it could go

search the codebase and then go and

search the best way to prompt it. And

then you can copy paste the prompt from

here to here. So there's so many ways

you could use this dynamic duo.

>> Yeah, I love it. That's super important.

Like I didn't know you could do that. So

that's that's a good tip.

>> There you go. But yeah, with that like

obviously we could go so much deeper,

make this infinitely better, but it's

the idea of just like you attach a

couple tools, you throw some API keys,

you give it some prompt, and then you

start the progress. like to build upon

that, not that we're going to do this in

this video, but a use case I would see

for this is I have been using or I've

been creating thumbnails for my short

form videos on Instagram just because it

looks better on my profile, whatever.

So, literally I could do what you did

for YouTube where you have this using

Nano Banana via the API for Gemini and

it goes and actually creates these

thumbnails for you using an image

generation tool. And that might be the

next thing that I personally go in and

actually try to build out because that'd

be super helpful. you built something

that's a bit more intricate than like

short form video. I feel like the system

you built with YouTube is like five step

a couple steps ahead of this and it's

just crazy to see like what we could do

with Claude code. So this video is

giving me FOMO Mark. So I'm going to

need to hop off like dive in.

>> Yeah. On that thumbnail thing just like

to inspire people. So, the way I I

created it is I have Nano Banana create

the concept and then it draft it out as

a doodle and then it takes that doodle

and it takes that pumps it to Nanabanana

again to create version one of the

thumbnail and then it loads that into

Gemini to get its opinion on the image

as a YouTube expert and then after it

roasts it, it injects its feedback back

to the Nano Banana to fix it. So, I have

this feedback loop where before I take a

look at it, it's already pre-roasted

itself, which is why again, this is such

a high lever skill. If you're non

techie, this is the time, this is the

perfect time to jump in and just get

your feet wet.

>> Yeah, that's and that's I love to hear

that. One one other thing I want to

mention before we end this episode

because we obviously showed kind of what

we built here or what Mark built here.

Go back to that Excali board you showed

because correct me if I'm wrong, you

built this with Claude code, didn't you?

You didn't even build this out yourself.

No, I have a system that I built in

cloud code that helps me make

explanatory diagrams especially for my

YouTube where it's doodles so it makes

things a lot more consumable. So I will

walk through like I literally talked to

I'm like listen I'm about to hop on

Brock's podcast on his channel. His

focus is not as developery. I want to

break this down. So help me make three

to five images where you think this

concept would like be done justice and

then it takes care of it from there.

>> Dude, I [laughter] love that. That's

just hilarious. I love that you did

that. All right, so this episode's been

amazing. I'm excited to go ahead and try

this stuff now and actually begin using

this system, build other things on top

of it. But Mark, if we could give the

viewer of this, a complete non-technical

person, one actionable item to do right

now, like instead of just watching this

video, taking notes, and doing nothing

with it, what could they do right this

second to actually take that first step,

begin begin learning this, and hopefully

building the skill that could change

their life over the coming years?

>> Yeah. So I'll I'll give the advice with

a grain of salt because I know people

will look at this and even if we prove

that it's effective, they still won't

download the terminal. So if that is the

friction point, you literally have

something that's dropped from the

heavens in the form of co-work which is

not perfect. It's still not an imperfect

product, but it will give you this

little taste of what it could look like

to run agentic workflows. You won't get

the breadth, you won't get the depth,

but it will get you more comfortable and

hopefully it will give you FOMO that if

you had instead of a basic engine, you

had the full firepower of a V9, V8

engine that you could run that much

farther. So, instead of having to go

from zero to deep end, you can go from

zero to shallow, get your feet wet, get

used to it, and then when you're ready,

make a couple commands, and then start

your Cloud Code journey.

>> And keep in mind, this is a tool that

dropped literally yesterday. So, this is

your sign from the heavens, like you

said, to go and try this and test this

out. There's no excuses now. Um, Mark,

this has been awesome, man. I appreciate

it. Thanks for building this for me.

Thanks for explaining it. Where could my

audience find you?

>> For sure. So, um, mark_ashiff on

YouTube. If you are someone that is

interested on the deep end of things,

you don't want to be just non- tech. You

want to go really hard. Um, you could

look check out my early AI adopters

community. That's where I go hard all

the time and I build all kinds of

things. And outside of that, hopefully

more on Brock's channel. [laughter]

>> Yeah. I want to give kudos to Mark's

community too cuz I've been in there for

I don't know probably over 6 months now.

Honestly, if I want to learn something

that's a bit more technical, that is my

favorite place to go. Kind of cuts

through the noise of everything else.

Don't have to go on YouTube or X and

like get my anxiety up and my FOMO up.

Instead, I'll just go straight to Mark's

community. It's a great place. So, yeah,

Mark, thanks for coming on, man. Sure.

We'll have you on soon. Have a good one.

guys.