Limitless Podcast

Ejaaz:
This is going to break your brain. An AI model just built another AI model,

Ejaaz:
and it's probably the most important software launch in 2026,

Ejaaz:
worth billions of dollars.

Ejaaz:
I'm talking about Anthropic's latest tool called Claude Cowork.

Ejaaz:
It's basically vibe coding for everyone who isn't a coder.

Ejaaz:
And when you realize what this means for knowledge workers, you'll start to

Ejaaz:
realize why Anthropic is quietly the most important company in the world right now.

Ejaaz:
The way it works is you just connect it to your desktop or your browser and

Ejaaz:
you just explain in plain, simple English what you want it to do.

Ejaaz:
And the examples are pretty crazy. People have already used it to turn on their oven.

Ejaaz:
People are using it to monitor their plant growing by their windowsill,

Ejaaz:
as well as tidying up their desktop and even replacing their nine to five job.

Ejaaz:
It's doing the entire thing for them. And we'll get to that later on.

Ejaaz:
But it brings into question whether this is the end of jobs as we know it today,

Ejaaz:
or whether this marks the start of a new era where AI and humans basically do everything together.

Josh:
Yeah, it's hard to understate how profound the shift is. And I relate it to

Josh:
something that's very near and dear to me, which is photography.

Josh:
And you could kind of relate this to how,

Josh:
in early days the smartphone it kind of democratized photography where

Josh:
suddenly everyone was a photographer the bar to become

Josh:
one was low the cost of entry was very low and claude

Josh:
code work is doing the same for automation suddenly everyone

Josh:
goes from a novice at code to a full-blown system engineer just based on a single

Josh:
human-made prompt so previous ai assistants they were like having a really smart

Josh:
person on the phone they could give you advice but you still had to do the work

Josh:
claude code is kind of like having that person physically in your office with

Josh:
access to your files, your browser, and your tools.

Josh:
And then as I was going down this automation rabbit hole, and to your point

Josh:
about job automation, it led me to a study that shared that the average knowledge

Josh:
worker, they spend 28% of their work week managing emails and 20% searching for information.

Josh:
So that's nearly half of their team's work now that CloudCode can handle.

Josh:
Okay, so before we get into how this tool works, there's a really important

Josh:
story to tell about an unexpected surprise, Anthropic Discovered,

Josh:
which led them to building this product.

Josh:
So CloudCode, it launched originally in May 2025 as a terminal coding agent.

Josh:
Very intimidating, very difficult, very confusing for non-technical users.

Josh:
Less than six months later, that product was at a billion dollars of ARR.

Josh:
It's 10 times the usage. It grew 10x in three months, and it went completely

Josh:
viral. It was the fastest startup in the world to go from zero to a billion ARR.

Josh:
Companies like Netflix, Salesforce, KPMG, everyone was using it,

Josh:
and it was the biggest thing in the world.

Josh:
And software developers were starting to use CloudCode for other things.

Josh:
They got really comfortable, so they started using it for things like canceling

Josh:
subscriptions, tidying up their emails, vacation research, monitoring the plant

Josh:
growth, and turning on remote things in their house like ovens or lights.

Josh:
And it became a full-stack automation software. The problem was is that Cloud

Josh:
Code wasn't really built for this.

Josh:
But when users bend your product to do something you didn't originally design

Josh:
it to, that's normally a pretty high signal indicator of a problem that you

Josh:
need to solve for. So that's exactly what Anthropic did.

Josh:
Or rather, that's what Claude Code did because it built Claude Co-Work to do

Josh:
vibe coding for everything that isn't coding in 10 days with a team of four

Josh:
people written 100% autonomously.

Josh:
So it was this pretty amazing unlock that happened over the course of the last 10 days.

Josh:
And here we're seeing on screen the post from Boris, the founder himself,

Josh:
and how he confirmed that it actually was 100% built autonomously.

Josh:
And I think maybe we should double tap on that and see how exactly they were

Josh:
able to accomplish this.

Ejaaz:
Yeah, I mean, this is the craziest part of the entire tool, by the way.

Ejaaz:
It's the fact that it was built by another AI completely autonomously,

Ejaaz:
or rather with the aid of four humans, but they didn't really do anything.

Ejaaz:
They just kind of like acted as cloud code supervisor and just made sure it

Ejaaz:
was on the right track. And it only took a week and a half.

Ejaaz:
Typically, if you wanted to build a product like this, Josh,

Ejaaz:
I'm guessing it would take like months using traditional software engineering techniques.

Ejaaz:
So it is one of the coolest things that kind of came out of this.

Ejaaz:
And it's a sign that in the future, some of the hit products are going to be built purely by AI.

Ejaaz:
But I want to get into Claude Cowork itself now, Josh, and kind of give everyone

Ejaaz:
an explanation as to what it is, the rundown of the key features.

Ejaaz:
And then I really want to get into some exciting demos.

Josh:
The examples are going to be really fun. We have some good examples.

Josh:
We're going to do some live demos for you guys.

Ejaaz:
Exactly, exactly. But before we do that, let me talk to you about Claude Cowork itself.

Ejaaz:
The way it works is you can give Claude Cowork access to your desktop,

Ejaaz:
a folder on your desktop, or a web browser.

Ejaaz:
And you basically just tell it what you want it to do in plain English.

Ejaaz:
So write out your prompt, hit enter.

Ejaaz:
Claude Cowork comes up with a plan. It shows you the plan. It says,

Ejaaz:
hey, this is what I'm going to do.

Ejaaz:
Are you cool with this? And you just click yes, no, or can you just change this bit?

Ejaaz:
And then you're all good. Off you go. And then that's it.

Ejaaz:
Go for a walk, go make yourself a coffee. Hey, go watch a Netflix episode.

Ejaaz:
It's all done. And you come back literally 10 minutes, an hour later,

Ejaaz:
and suddenly all those tasks that you've been putting off for the last year,

Ejaaz:
It's me, I'm talking about me, is completely done.

Ejaaz:
And the way that all of this is enabled is pretty cool. They've got some nifty features here.

Ejaaz:
It's built on the same software stack that Claude Code is.

Ejaaz:
So it works very similarly to Claude Code, but it's for non-technical people.

Ejaaz:
You don't need to download a command-lined interface. You don't need to know

Ejaaz:
how to code. you just type in plain English and it's done.

Ejaaz:
The second thing is it runs on a sandboxed virtual environment.

Ejaaz:
What that means is when it operates your desktop, when it operates your web

Ejaaz:
browser, it's in its own environment in order to do that.

Ejaaz:
So it's siloed to the particular folder that you give it access to.

Ejaaz:
It can't just go rampant and start accessing anything and everything.

Ejaaz:
You specify what you want it to completely.

Ejaaz:
And then the final thing is you can pair it with your browser,

Ejaaz:
which means that you can do a bunch of web-based tasks, which Claude plugin

Ejaaz:
already allows you to do.

Ejaaz:
And so on its face value, this sounds interesting, right?

Ejaaz:
But like, I want to know what it can actually do in practice.

Ejaaz:
And some of the examples that I've seen so far and that I'm about to show you are pretty fun to do.

Josh:
Yes. And I want to start with these examples, particularly the first one in

Josh:
this post, which we're going to do live, which is a cleaning up of your desktop.

Josh:
So, EJS, you are notorious for having a slightly less than clean desktop.

Josh:
And it is normally full of content that most people wouldn't want cluttering up their desktop.

Josh:
So, what we have prepared is an actual prompt with Cloud Code that we will use

Josh:
to organize this desktop as a live demo and just kind of show you how Cowork works in the desktop.

Josh:
Production yeah so here's a live view for the unfortunate viewers

Josh:
who are watching on spotify or youtube of what this desktop looks

Josh:
like and he just i've just shared with you a prompt that i've actually

Josh:
worked with claude to create so this is the way

Josh:
i would advise everyone use it is instead of using your own prompts prompt the

Josh:
llm to create a full prompt that captures the entire scope of what you're looking

Josh:
for what this does is it will organize your desktop into a series of different

Josh:
folders based on productivity inbox projects finance and it will run checks

Josh:
to make sure that it's doing the right thing,

Josh:
make sure that it doesn't write the, delete the wrong files.

Josh:
And it will include organized file names as a way to index everything alphabetically.

Josh:
So it'll keep things very organized.

Josh:
And he created this, I mean, it's a fairly detailed prompt. There's a lot going

Josh:
on here. So if you paste this into Claude Cowork, you should see it start to

Josh:
get to work here and start actually

Josh:
organizing the files on your desktop without you touching anything.

Ejaaz:
All right, Josh, listen, I won't lie to you. I'm a little nervous about what

Ejaaz:
this is going to do to my desktop. What happens if your computer breaks?

Josh:
If the recording ends right here.

Ejaaz:
How do I know like Claude's not trying to nefariously get involved kind of maliciously here?

Ejaaz:
On our previous episode, we proved that or we suggested that it might be more aware than we think.

Josh:
Anyway, Claude was very high on the scheming index in our last episode.

Ejaaz:
So what you guys are looking at now is the main interface for Claude Cowork.

Ejaaz:
If you have a Claude Max plan, you have this neat little tab now on your desktop

Ejaaz:
app, which allows you to access Claude Cowork. and it starts off with a pretty

Ejaaz:
neat prompt which is let's knock something off your list and it gives you a bunch of ideas.

Ejaaz:
What I'm going to do is I'm going to paste that prompt which Josh created using

Ejaaz:
Claude into here to tidy up my desktop and you'll notice this little folder

Ejaaz:
section this drop down menu here where it says work in a folder.

Ejaaz:
I'm going to specify that it works in my desktop and I'm going to say allow

Ejaaz:
for this particular case because I don't quite trust it just yet. And let's go.

Josh:
Okay, so now how's this thing so we can kind of walk through how the best ways

Josh:
to interface with this are are.

Josh:
Which is plan, execute, and update. So the first stage that we did was the planning

Josh:
stage where I kind of prompted Claude to create a larger prompt.

Josh:
That was planning that outlined the scope of things.

Josh:
And then it's going to execute, which is the phase that we're seeing now.

Josh:
And then you can actually decide to update and you could push the update live to your machine.

Josh:
And we might want to take a peek at your desktop because it might be doing it right now.

Josh:
And that's the loop that happens with this. That's the recursive loop.

Josh:
It's the plan, execute, and update, which mirrors how a good human assistant works.

Josh:
They don't just do things. They show their work. they check in and they course

Josh:
correct as they go to make sure that the model doesn't drift as it goes on these

Josh:
long complex chain of thought processes.

Ejaaz:
And what I like about this step in particular is it doesn't just plan and then execute immediately.

Ejaaz:
It gets the humans not of approval first, which is very important towards like

Ejaaz:
AI working with humans in the future.

Ejaaz:
A few things I want to point out. It understood the prompt, it created a plan,

Ejaaz:
and it did this in its command online interface in its coded identified

Ejaaz:
what it needs to do and it gives you me

Ejaaz:
a little summary here it says you have 27 screenshots many older than

Ejaaz:
90 days several pdfs 15 folders images

Ejaaz:
and media files and an installer claude would you like me to proceed with the

Ejaaz:
dry run as josh.eats prompt described so it even knows that you sent this to

Ejaaz:
me that's freaking hilarious uh so i'm just going to be like yes run it see

Ejaaz:
what happens and it works pretty quickly i think we're going to see this happen

Ejaaz:
in a second.

Josh:
Really quickly. And while it does this, maybe I could describe a different example

Josh:
that I used personally recently with Cloud Cowork.

Josh:
And it's, I use a tool called Obsidian, which is a markdown note-taking application.

Josh:
So the app is basically a harness for markdown files that organizes them in

Josh:
a really unique way that connects them via backlinks.

Josh:
And it's kind of messy. There's just a lot of notes kind of spread out everywhere.

Josh:
But because Cloud can ingest markdown files, it was able to ingest all of the

Josh:
notes that I've made over the last three or four years and then draw unique

Josh:
insights from them and organize them in a unique way.

Josh:
And it's a really nice file management system in a way that I would never have tried to tackle myself.

Josh:
So that's been fun. If we're looking at the process here, what is going on?

Josh:
It's doing a lot of stuff.

Ejaaz:
And it's doing it, if you noticed, in rapid speed. So basically,

Ejaaz:
it's identified all the files and folders that are on my desktop,

Ejaaz:
and it's created a bunch of categories that were You might wind up

Josh:
With a lot of folders.

Ejaaz:
I think you're just going to make my life better, but also worse.

Ejaaz:
And so we have a bunch of file moves that it's already actively doing, active projects.

Ejaaz:
You can see here what it's actually doing. And what I like about it is it is

Ejaaz:
just obliterating this.

Ejaaz:
It's given me a few that it needs to review. So this is a cool point to make, which is,

Ejaaz:
Typically, when people are uncertain about using these AI products,

Ejaaz:
it's because they don't trust it and that they think the AI model is going to

Ejaaz:
do something that they don't want it to.

Ejaaz:
Claude Cowork has a context about what those things might be.

Ejaaz:
And instead of doing it, prompts you to say, hey, you need to give me an idea

Ejaaz:
of what you want to do with this.

Ejaaz:
There's a movie folder that you have a bunch of movies that you watch on the

Ejaaz:
plane with. Is there something you want me to do with this?

Josh:
So type approve to proceed with these changes. And in fact, you may not want

Josh:
to approve this because this is going to create 16 folders. So perhaps you want

Josh:
to prompt it to compress that into four or five of the most common categories.

Josh:
That way it will actually organize it into a way that doesn't add more folders,

Josh:
it actually compresses things.

Josh:
So maybe, yeah, choose the four or five most common themes among the folders.

Josh:
And it will apply some more smart thinking to that and generate you something

Josh:
a little more neat than 16 separate folders.

Ejaaz:
Actually, I've decided to disagree with you. Approve.

Josh:
Let's see what happens.

Ejaaz:
Let's get this bad boy going. Come on. I want to see this done live.

Josh:
So while we're waiting, what other fun use cases have you seen?

Ejaaz:
Okay, so another fun use case that I've seen, and I wish I had the example for

Ejaaz:
me on here, is someone, to his wife's disdain, lost their wedding photos.

Ejaaz:
And then he found it, but it was in a file that was corrupt and unreadable.

Josh:
This story was amazing.

Ejaaz:
It was an amazing story. So what he did was he went to the original photography

Ejaaz:
company and they said, hey, this is the software that we officially use.

Ejaaz:
Download it and just run it to like get your wedding photos out.

Ejaaz:
One problem. It was a Windows only app and he has a MacBook.

Ejaaz:
So it never worked in the first place.

Ejaaz:
So he was like distraught. And then he realized, oh, I could use Claude Cowork to do this.

Ejaaz:
So he asked Claude Cowork to identify the file in his browser and then code up.

Ejaaz:
Sorry not in his browser in his desktop and code up a

Ejaaz:
custom made app just so he could access the photographs and josh i kid you not

Ejaaz:
two minutes later he had it running slicker and better than the actual official

Ejaaz:
software that the wedding provider gave it to him himself it's pretty insane

Ejaaz:
okay that's amazing organization complete complete are we ready for the grand

Ejaaz:
reveal like yeah take a peek drum roll please

Ejaaz:
oh nice wait that dude looking good what the hell that is actually insane and

Ejaaz:
what's the best part about that is all of you just got to saw that live pop

Josh:
Into something let's see what let's see how.

Ejaaz:
It did let's see what are we feeling it's wrong why is my inbox here okay let's

Ejaaz:
go into inbox okay it's got some random screenshots in there don't know why

Ejaaz:
that's done that uh projects

Ejaaz:
okay yes i love this because okay this is pretty cool because it's identified

Ejaaz:
separate hobby and projects that i actually work on in my spare time and what's

Ejaaz:
interesting about this is i have other folders that were on my desktop that

Ejaaz:
weren't projects but it was able to somehow identify that these were personal

Ejaaz:
hobbies and do this for myself that's freaking awesome we're we're one for one

Ejaaz:
right now we're one for two uh pick one more josh you see anyone that's getting you?

Josh:
Let's go with that second one.

Ejaaz:
Media?

Josh:
Yes, let's go with the media tab. What's in there?

Ejaaz:
Oh, Josh.

Josh:
Oh, look how adorable those guys are.

Ejaaz:
Look at us. I mean, come on.

Josh:
So it worked. That's a mission success. That is a really nice demo.

Josh:
And you could kind of think about how this scales out to larger corporations, right?

Josh:
There's this one crazy stat where the average employee spends two hours per

Josh:
month on expense reports, which is kind of an outrageous thing for a company

Josh:
of a thousand employees. That's 2,000 hours of productivity lost monthly.

Josh:
And something like Claude handles this with just OCR to read receipts,

Josh:
categorize expense based on vendors and the amounts. And there's so many ways

Josh:
in which you could automate a business.

Josh:
And there's this interesting example that I wanted to highlight,

Josh:
which was the spreadsheet and accountants in general, where if you remember

Josh:
not too long ago, before computers and calculators became a big thing,

Josh:
there were buildings full of people whose job it was to actually do math,

Josh:
to do long-form math, to calculate the accounting of a business.

Josh:
And that entire building of people got replaced by a single spreadsheet.

Josh:
And what's funny about these companies, and you think about MicroHard with XAI,

Josh:
their entire goal is to have photons in and then bits out in the terms of like

Josh:
building native and unique software.

Josh:
So if you think about a building full of humans in a spreadsheet today,

Josh:
the spreadsheet is far more efficient.

Josh:
But not only that, if you compare a spreadsheet that is 100% automated versus

Josh:
a spreadsheet that has a single cell that a human has to monitor,

Josh:
well, the single cell that a human has to monitor is going to compute much slower,

Josh:
it's going to be a lot less accurate.

Josh:
It is going to just give you problems that an AI will not. And I think it's

Josh:
kind of a testament to how future companies will be structured.

Josh:
Because if you choose to do something like, let's say, expense reporting.

Josh:
And you don't use 100% AI for this, you don't use Claude Code or Claude Cowork

Josh:
to do something like this, well, anyone who does automate that part of the business

Josh:
will immediately unlock 2,000 additional productive hours.

Josh:
And this scales across the scope of pretty much any business that exists today,

Josh:
where so long as there is a verifiable outcome that you're looking towards,

Josh:
you can automate that in the world of bits at least.

Josh:
And this kind of plays out, you could see how this plays out over a long period

Josh:
of time. We're starting with bits where anything that you have to do on a computer.

Josh:
Any bit of software can be automated so long as it has a verifiable outcome.

Josh:
Then the world of atoms comes next where, well, if you have to move physical

Josh:
objects, the cost of that comes down with human-eyed robots as we scale.

Josh:
And you start to see this job replacement type argument become a little more real.

Josh:
The other side of this, the flip side, is that accountants since computers have

Josh:
gone up, I think, 50 times.

Josh:
The amount of accountants that exist post-computer versus pre-computer has multiplied

Josh:
so much because of the Jevons paradox.

Josh:
I mean, now that there's an abundance of accounting capability,

Josh:
a lot more companies want this for their books.

Josh:
A lot more people want to, a lot more companies, one, exist,

Josh:
a lot more companies, two, are able to actually keep an accurate record of account.

Josh:
And the net-net is a positive. So while this probably reshuffles things around,

Josh:
I don't think the net is going to be as negative as a lot of people perceive.

Ejaaz:
Well, with that prompt, I kind of want to get on to the final part of this episode,

Ejaaz:
which is kind of like the bigger picture.

Ejaaz:
Where does this tool lead us? And I want to run through a few examples with you now.

Ejaaz:
So number one, I think this tool is going to be useful for millions of people.

Ejaaz:
And I really mean that versus a fad.

Ejaaz:
We've been sold a few lies from the likes of OpenAI and Google's agents,

Ejaaz:
which sound good in theory, but haven't really been productive.

Ejaaz:
This is something that my mom or sister can access today and it will add net

Ejaaz:
new value to their lives.

Ejaaz:
And some of the use cases that we've discussed already on the show is just the tip of the iceberg.

Ejaaz:
We haven't even fully explored what this tool can actually do at great lengths.

Ejaaz:
And if we were to hypothesize here and if it went the way that Claude Code did,

Ejaaz:
and I'm showing a tweet from Boris Churney where he described the creator of Claude Code,

Ejaaz:
where he describes the journey that Claude Code took, it started off slowly

Ejaaz:
and then super, super quickly.

Ejaaz:
My hypothesis is going to be an AI literally just wrote 100% of a tool that

Ejaaz:
is going to be responsible for GDP's worth of economic value that is built on top of that.

Ejaaz:
And I don't think people have fully grasped how important that's going to be

Ejaaz:
for humanity in general.

Ejaaz:
The second thing, I need to throw a little bit of shade before we wind this episode up, Josh.

Ejaaz:
This tool was meant to be what Microsoft Copilot was going to be.

Josh:
We got to talk about Microsoft.

Ejaaz:
But instead, they spent one and a half years shipping absolute BS.

Ejaaz:
OpenAI dropped the ball completely when they should have been keeping tabs on Microsoft.

Ejaaz:
And Anthropic ate their lunch, or rather an AI model ate their lunch in 10 days,

Ejaaz:
a week and a half from scratch with four humans.

Ejaaz:
That is like a tiny fraction of a percent of Microsoft's entire workforce. Just insane.

Josh:
Yeah, so there's two points. On the FAD and the is this a FAD or not,

Josh:
you can kind of put it through the utility test, which is,

Josh:
I mean, the difference between FADs and these real transformative tools over

Josh:
time is how you're able to use this over the course of your day,

Josh:
over the daily work test.

Josh:
And these aren't really novel tasks. They're tasks that people actually need done repeatedly.

Josh:
So is it a FAD or not? No. I mean, this is what people need every day.

Josh:
And as this iterates, it's going to get better. On the Microsoft point,

Josh:
Microsoft has 220,000 employees and they had a three-year head start.

Josh:
And what Anthropic did in 10 days with four people, fully assisted by AI,

Josh:
is a testament to just how powerful it is and how unexpected I think it was

Josh:
when you get a killer use case like this.

Josh:
If you remember, ChatGPT was kind of an accident. It wasn't really supposed

Josh:
to be the entire business of open AI.

Josh:
A similar thing is happening with Anthropic and with, I guess,

Josh:
companion agentic protocols because they certainly didn't expect this to be

Josh:
as big as it was because they didn't have a large team on it.

Josh:
In fact, after this went viral, they posted a bunch of job listings to join

Josh:
this new kind of experimental team where they test these new things because

Josh:
you never really know what that killer use case is going to look like.

Josh:
And in the case of Anthropic, they've hit a home run. And it makes you wonder

Josh:
what Microsoft is doing.

Josh:
I mean, they have such a tremendous workforce. they have more money than they

Josh:
know what to do with. And all they're doing is building data centers,

Josh:
but have nothing to really show for it.

Ejaaz:
And finally, the last two points I want to make is, okay, on the point of work,

Ejaaz:
you kind of mentioned it, Josh, but I want to kind of like dig into like whether

Ejaaz:
this is going to replace people's jobs entirely.

Ejaaz:
The answer is kind of like yes

Ejaaz:
and no, it's going to replace a bunch of knowledge work that people do.

Ejaaz:
I'm showing this on the tweet that we have up here right now,

Ejaaz:
where he describes he interacted with Claude co-work and two hours later he

Ejaaz:
had done his entire week's worth of work so he didn't know what to do with himself

Ejaaz:
when he logged on every day he didn't know what to tell his manager because

Ejaaz:
all the work was done and he was just kind of like shipping it to him which was crazy

Ejaaz:
it's reminiscent of a trend that I think we're going to continually see in 2026,

Ejaaz:
which is something I'm calling recursive models or recursive language models.

Ejaaz:
Basically, AI models are smart enough now to understand what humans actually

Ejaaz:
want and to go and build it themselves.

Ejaaz:
So previously, they had the tools to do it, but they were dumb.

Ejaaz:
They kind of couldn't put context together.

Ejaaz:
Now they have it. And we're seeing things like law code build tools like this,

Ejaaz:
which I think are going to be worth billions of dollars, Josh.

Ejaaz:
If it was its own startup, I think we're going to see one of the quickest ascents

Ejaaz:
to a billion dollars in revenue. It might even be Claude Code.

Josh:
I very strongly agree. Okay, so how do you try this? For Claude Code,

Josh:
you need to get the Pro Plan, which is a $20 a month membership for Anthropic and Claude.

Josh:
For Claude Co-Work, which is what we demoed today, that is their max plan.

Josh:
That is $200 a month, which is a little more pricey. It's worth experimenting

Josh:
at least with Claude Code.

Josh:
I think as a person who is kind of working, if you're in the workforce today,

Josh:
it helps to flex the muscle to reach for an agent versus reaching for the things

Josh:
that you're used to, like Google or a manual work process.

Josh:
And one of the things that I'm personally working on is figuring out,

Josh:
how to retrain that muscle to know when to reach for the

Josh:
ai to know when to reach for the agent and having cloud code

Josh:
on my desktop on my phone it's been very useful in and

Josh:
kind of massaging that muscle to so oh instead of going to google or watching

Josh:
a tutorial i can actually just ask my agent to do it and it does it really well

Josh:
so that's a fun practice i think maybe for the prompts today what cool stuff

Josh:
if you have used these programs have you done what have you automated that we

Josh:
should try because one of the most difficult things is figuring out where to apply this.

Josh:
What part of your life can you actually improve?

Ejaaz:
Extra points for creativity. For anyone, let us know what you've done,

Ejaaz:
if you have access to this plan or to this product in the comments below.

Ejaaz:
And please also, like, like, subscribe, and follow us because we're putting

Ejaaz:
videos like this more and more.

Ejaaz:
Josh and I are inspired by Cloud Coworks. We want to stop building apps,

Ejaaz:
demos for you guys to show on the show.

Ejaaz:
If that's something you're interested in seeing, please let us know because

Ejaaz:
your feedback is very important for us.

Ejaaz:
And Josh, I don't know what the time is, but we are trying to keep this tight

Ejaaz:
under 25 minutes because it's on the latest resolution. We're close.

Ejaaz:
I think we might've done it. So if there's nothing else to add from you, I think that's it.

Josh:
That's a wrap. Thank you so much for watching. For the people who are regular

Josh:
listeners, the roundup is coming early next week. There's just so much going

Josh:
on this week that we wanted to cover.

Josh:
We're gonna move the roundup to early next week. There's so much to be included

Josh:
in that, along with things like Tesla autonomy, there's humans coming down from Earth.

Josh:
There's a lot of stuff happening, so stay tuned for that. We will see you guys in the next one.