Anthropic shipped the feature called

Claude Dispatch, which lets you

essentially run and manage an AI agent

through your phone. In this video, I'm

going to show you guys how you can use

it, why it's significantly better and

probably more preferable from a security

perspective than a lot of the

pre-existing solutions like Open Claude

et al. And then, how to set it up on

your end so you guys can run everything

that you need from the convenience of

your device. So, some of you guys will

know, I'm a big fan of using Claude Code

to do a lot of economic knowledge work

for me. This video is not trying to say

that Co-work is better than Claude Code,

but it is a different and easier

interface that a lot of less technical

people can use to get up and running.

So, in Claude Code, I have a bunch of

skills, which are essentially tasks that

I fire off one at a time. I say

something like, "Hey, scrape me 100 HVAC

leads in Texas." And this will actually

go through and then literally contact

the internet, run a bunch of scrapers,

and then return them back to me on

totally autonomously. The issue is

obviously, using my phone with a setup

like this is annoying. It's often pretty

fragile, and then it takes a fair amount

of setup. So, Claude Co-work solves all

this for us completely out of the box.

Okay, so totally hands-off demo, I have

Co-work set up with Claude Code

Dispatch. It's right over here, and uh I

just want to scrape 200 agency owners in

California with a 1 to 10-ish size. You

can see the second that I entered that

in, that was immediately reflected over

here on my screen. And the reason why is

because this is now running locally.

Now, I don't know, I'm just on the go,

right? I'm waiting for uh some train or

something like that, and I say, "Hey, I

could probably get a couple of phone

calls in." So, I launch it from here.

Immediately after we see actually see a

window open under Dispatch over here, um

as a new tab on sort of our Claude

Co-work ongoing conversations. So, what

it's doing now is it's actually running

the skill. Okay, it's doing a bunch of

the specific SOPs inside of the skill,

like generating search keywords, running

a test scrape, and so on and so forth.

And then, I'm going to see the results

back here on my phone the second that it

finishes. Okay, and then just a few

minutes later, I have all of them on my

phone here. I don't know if you guys

could see this, but um it's like data

set leads finder. I have all the phone

numbers. So, if I just wanted to, you

know, click on one of these and maybe

give them a ring, start doing some cold

calling, I could. Um I just initiated

and then completed that loop entirely

from my phone, which is pretty sweet.

But obviously that's not the only thing

that I can do. Um, I have this pretty

cool inbox cleaner flow, which I like

running. And um, what I'll do now is I'm

just going to initiate that inbox

cleaner again from my phone. So I'll

say, "Run inbox cleaner." And then my

hands are up here just so you guys could

see. Um, it's going to start a

conversation, um, go down to that tab

there. And then just like I did before,

it'll it'll run my own skills on my

computer using um, you know, Claude

co-worker. And just because I want to do

multiple things simultaneously, I'm also

going to have it run another skill.

Uh, what I'm going to do is

hypothetically, let's say I have found a

YouTube thumbnail that I really like and

I have a video that's coming up soon.

So, you know, let me just make this a

little bit bigger. Okay, there's this

awesome one here from um, I don't know,

uh, "Don't Create an LLC." It's by

Jasmine Dilucci. She's this person that

uh, I don't know, creates content all

about accounting and stuff like that. So

what I'm going to do is I'm just going

to share this. I'll copy the link and

then I'm also going to feed this

directly into Claude

um, Dispatch and I'm going to say, "Hey,

recreate this thumbnail

but with my face."

Then I'm going to paste in the link and

now we should also pass the next uh,

message in queue.

And what this is going to do is it'll

launch an additional Dispatch

conversation that uh, will allow us to

run multiple of these things. Okay, and

then if you see here, we're running all

three accounts in parallel, fetching,

classifying, then marking read for each.

Over here, we're actually reproducing a

thumbnail using my thumbnail generation

skill with which has some face swapping

uh, functionality built in. And I'm

going to get it on my phone in just a

few seconds. Now in my case, I didn't

uh, realize but one of these skills

actually required a little piece of

access from my computer that I hadn't

given it ahead of time. And so when that

occurred, I just had a little window

that popped up at the bottom of my

Claude Dispatch and it said, "Hey, you

know, we're trying to reach XYZ. Uh, do

you want to allow this request?" So I'm

the one that just instantiated the

request, obviously I'm allowing it. This

sort of like security and then allow

listing style permissions is what makes

this 10x more safe, uh, you know,

secure, and then scalable for business

and then enterprise applications than

something like open claw. Okay, and then

in this case it's now created a bunch of

files. I don't think this is the best or

most realistic look that I've ever had

before, but still not pretty bad and you

know, we initiated this from my phone.

And it's not just available over there,

it's also available over here. So

dispatch is reporting back right now

letting it know that you know, it just

finished the thumbnail thing. And now

it's asking me to allow it permissions

to go and grab those thumbnails which I

will do in a second. And now it's

actually showing them to me all on my

phone. So you know, I have them right

over here too, right? I can actually

take a look at them and then okay, I

guess I can't scroll through them, but I

don't know. That's another one right

over there. That's another one right

over there. And so I just generated all

these from my phone basically through

like an app, right? This app, but I

didn't actually have to like whip up an

app for it. I could just wrote this to

my computer, which is pretty sweet. And

then the inbox cleaner also finished and

in my case basically what this does is

it just automatically marks as read

anything that

I would consider to be some form of

spam, some people soliciting me, that

sort of thing. And then if there is any

like important email or whatever, it

goes through and then it pre-drafts a

reply based off of a bunch of old

replies that I've sent. And then it just

allows me to QA and sort of human in the

loop. So I then go through my inbox, but

I basically save like 90% of my time.

So that's pretty neat, right? Like it's

done my personal Gmail, it's done a

couple of other things.

Simple systems like this essentially

allow me to save two or three hours a

day. And before I was constrained with

doing all this stuff on my computer. I

had to lug around my big fat laptop with

me. But now you know, I could set up my

laptop or I could set up another

computer or some sort of Mac mini in the

corner and then I could just like sort

of port in, run whatever skills, run

whatever workflows I need even while I'm

over here. And then you know, naturally

I receive and then can send additional

data, follow-ups and everything like

that from here. Well, that's still super

secure. So in my mind this has solved

everything. I'm sure we're just a few

stones throws away from having this sort

of stuff in Telegram. Let me show you

guys how this all works under the hood.

So if it isn't clear, I think that most

of these autonomous agent tools are

pretty broken. And they're broken for a

couple of reasons. The first is these

open claw and DIY agent stacks, which I

think everybody and their mom is going

to try and tell you is like the future

and stuff like that. Um they are

terrible from a security perspective.

We've had tens of thousands of API keys

leaked. Uh very elementary sort of

security errors here have hit news

headlines over and over and over again.

It got so bad they had to change their

name multiple times and stuff like that.

And I mean like their core functionality

is pretty cool, right? Which is that I

get to text my model basically from my

phone and then have it do economically

valuable tasks for me. And the reason

why beginners and you know, people that

aren't very tech uh super into this sort

of tech love it is because it's like,

"Hey, I you know, I talk to my friend in

Telegram and then immediately underneath

I have my Claude bot in Telegram and

that's awesome."

Right? It's just like good from a user

experience perspective. But all of that

isn't really worth risking, you know,

your API keys, your credentials, your

credit card numbers, your identity,

right?

In addition to obviously massive

security issues, there's also like a

context explosion issue where you are

paying for the most part using your um

API pricing instead of like a monthly

recurring subscription, which Anthropic

subsidizes heavily and tends to be

somewhere between like four to eight X

cheaper. What I mean by this is you are

doing direct API calls to their back

end. And every single time you make an

API call, um it bills you usage twice.

Like that's, you know, every message 50

cents, you know, every time a skill

runs, that's $2. Every single moment

that you're having a conversation with

um models on, you know, Open Claw and

whatever, unless they're running locally

or running using something like Nemo

Tron.

What you're really doing is you're just

constantly like

burning your money in the background.

And then, you know, ultimately this pay

per token plus the security problems, in

my view, makes this like a non-starter.

You know, if I'm using this in a serious

business application, I'm basically

never going to recommend something like

Open Claw or whatever. And so, when this

came out, you know, I made a bunch of

videos talking about how horrific it was

and all of the API keys that got leaked.

And I was like, "You know, I bet it'll

just take a couple of months before

Anthropic launches a native feature that

does all this stuff." Um and that's what

Claude Dispatch is. So, with Claude

Dispatch, you basically connect

automatically to whatever your desktop

is, your computer. Um so your skills,

you know, all of the pre-existing MCP

connectors and all of your files. Uh but

it's also sandbox and local. And I mean

like, you know, if there's a company

that I trust to understand how to rein

in, you know, the downsides of like AI

agent flexibility, it's the companies

that have developed the best AI agents

out there. Um like Anthropic, they've

spent, you know, hundreds of millions

and not billions of dollars doing this

exact thing. So I trust them to, you

know, sandbox and make things pretty

local. Um it's also uh like a flat

monthly charge because it's technically

used as part of your subscription. Now

they're talking about how they're going

to make this available to pro plans

pretty quick. I think right now, as of

the time of this recording, it's on max

plans, but they're they're going to want

to try and get everybody on it. And so

what that means is instead of paying,

you know, I don't know, like it really

depends on your usage and I don't want

to pretend like I know exactly how much

you're using, using, but when I tried to

open Claude, I spent like a hundred

bucks or so in just my first few days

and then I was like, okay, now I turn

this off. Instead of spending that, you

know, you'll you'll probably just spend

20 to whatever the the the subscription

amount is. And it's going to be heavily

subsidized.

And then, you know, it's the same power

here, but I want you guys to know,

realistically speaking, you're probably

going to get significantly more usage

out of co-work because

out of Claude dispatch because they're

just going to like build in more and

more and better functionality. This is a

company that has access to basically all

of the information on planet Earth at

this point. Um I trust that they're

going to do a much better job with this

sort of infrastructure and architecture

than some random third party. In terms

of how dispatch specifically works, um

it's sort of like a multi-layer system.

You know, down at the bottom, its brain

is Claude co-work. And uh you know, I

usually make videos not on co-work

because that's the non-tech version of

this intelligence and an agent tech

model. Um I make more videos on Claude

code, but Claude co-work and Claude code

are basically, you know, the exact same

thing. It's just like support for a

wrapper that wraps around skills and

then, you know, pre-established SOPs. So

basically what happens is um Claude

co-work, which is your base sort of

agent here, has access to your skills

library and a bunch of MCP services to

do things for you. Dispatch on your

phone basically just um it communicates

through layers with, you know, your MCP

servers, your skills, back to Cloud

CoWork. Cloud CoWork does something, and

then it kind of communicates back up the

ladder to Dispatch. And that's what I

was talking about with um, you know, the

fact that this is like an agentic thing.

You're you're launching an agent. Those

agents can launch sub agents, and and so

on and so forth. All right, so I'm going

to show you guys how you guys could set

up uh Cloud Dispatch in just 5 minutes.

It's really easy. We're just going to

update Cloud Desktop, or just reinstall.

We're then going to update the Cloud

mobile app. We see Dispatch in the

sidebar. We're good to go. We can

actually enable it and then turn all

stuff on right now. If not, you know,

we're just going to restart our

computers until we see, you know,

whatever the the update logic is. Um

this is literally It's probably not even

going to take 5 full minutes. Let me

show you guys how all this stuff works.

In terms of how to set this up, this is

a pretty new feature. It was launched

sometime in the last 24 hours or so. And

so, many of you will not have this

Dispatch tab added to your Cloud CoWork.

That's okay. If you don't already have

this, what you need to do is you need to

update the application. So, just for all

intents and purposes, in case you don't

have Cloud Desktop set up, it's as easy

as heading to cloud.com/download,

then going from Desktop over here,

selecting your operating system, and

then choosing either Mac OS, Windows, or

Windows arm 64. You'll also have to pair

with the desktop app on your mobile, so

choose iOS or Android here. Once you're

done on desktop, you'll have an

interface that looks like this. Now, I

should note that there's actually three

different sections to Cloud Desktop.

There's chat, CoWork, and code. And for

this feature, you're going to need

CoWork, which you can also use hot keys

to bump to, in my case command two.

Now, once you're done, head down to this

Dispatch feature, and it'll say

something like CoWorking on the go. In

order to get this started, it walks you

through sort of the functionality, which

is that your phone is like a

walkie-talkie that can communicate with

Cloud and your computer. You just send

Cloud a message, and it'll work on tasks

locally using your computer. Um the one

caveat to this is you do need to

remember to keep your computer awake. Uh

this is a big thing that a lot of people

were doing with open claw. They would

purchase specific computers like Mac

minis or whatever, plug them in and just

have them working 24/7. This is the

exact same thing. You just have, you

know, your computer where you want to do

these tasks awake and then Claude

Dispatcher can take care of the rest of

it for you. Anyway, all you do is you

click get started and then you have to

pair with the Claude mobile app. So,

I've already downloaded the Claude

mobile app. All I'm going to do is open

this puppy up. Now, it looks like I'm

already signed in to my phone, so I have

the Claude desktop app open right over

here. It has a chat window um ready to

to talk to Sonic 4.6.

Next up, it'll ask, "Hey, can I give

Claude access to your files?" So, it'll

ask me when I click finish, "Should I

keep this computer awake?" which you're

going to want to click yes to, otherwise

dispatch is going to run into some

problems. Um give it the ability to use

Chrome and then ensure that all

connectors are on, okay?

Then just click finish setup. It'll ask

to access files in your desktop and

documents and so on and so forth. You're

going to have to click this button a

bunch of times.

And now you have the ability to

communicate with your phone and Claude.

Now, on my phone's end, all I need to do

is in my Claude app, scroll down to

where it says dispatch, click the

button, and then I'll get something that

looks like this. And as you can see, the

UX and stuff like that is very similar

to what we just did. So, all I need to

do is click pair with your desktop and

then it'll connect automatically with

the conversation that's in this window.

So much so that my hands are off the

computer now. All I'm going to do is

type, "Hey."

And I want you guys to see how this

immediately pops up on my computer as

well. And so, I'm actually having a

conversation with Claude uh co-work

through dispatch right now. It's fully

managed for me and then I obviously have

like a contiguous conversation history,

which is really sweet. And here is where

I could start by, I don't know, running

some skills. So, I'll say, "Run the lead

scraper skill. Get me some leads for, I

don't know, HVAC in Texas."

Let's just do 100 to start. I'm now

going to send it the message, and it's

going to go through the process of

connecting to the skill, which is in my

Cowerk instance, and finding all the

session information and stuff like that,

and then actually launching it. And then

I will have all of the information and

everything I need uh popping up on my

phone as well. And you can see when I

actually kick off a skill execution, I

create a new tab here that is prepended

with the words dispatch. In this case,

it's scrape HVAC leads Texas.

Uh that actually opens this up. And then

you can see the progress bar on the top

right-hand corner, just cuz this is a

pre-installed skill that I, you know, I

put together a while back. Um it'll go

through the debugging and everything

else it needs to. And you know, I'm I'm

not actually going to see a message back

like on my phone until this thing is

done and it delivers the results. In

this way, essentially what it's doing is

it's like spinning up new Cowerk

instances, uh new Cowerk conversations

almost as like sub-agents, going doing

the task, and then reporting back the

results of said task to me. Also,

hypothetically, if you were using

something like Cloud Code, and you

wanted this one-shot skill run

functionality from your phone, really

simple and easy way to do it is you

basically just get all your skills from

whatever your IDE or your Cloud Code

instantiation is storing them. So, in my

case, it's right over here. And then, in

my case, I just duplicated them to this

new folder, which is .cloud/skills. And

then I just said, "Hey, I want you to

add them all to Cowerk." It then goes

through, sends you a couple of brief

little requests. Then after all this

stuff is said and done, um you just get

a big list of skills that you can just

copy over to Cloud Cowerk. Uh and this

is going to allow it to work with

dispatch really easily. So, I'm just

going to click copy to my skills.

Actually, this one I think is already

part of it. I would just did this as a

demo, so this one should be good. That's

actually going to like add auto research

diagrams directly over to the system.

The next one, face variants for

instance, and so on and so forth. Then

you'll get this copied to your skills

message at the top, and now you can

access it in dispatch really easily.

Okay, hopefully you guys appreciated

this video. Um dispatch is really cool.

This is, honestly, a stand-in

replacement for 80 to 90% of all the

features that Open Claw and other

extraordinarily insecure implementations

of autonomous decentralized agents uh

provide for you. So, I'm using this

thing all the time now, and it's not

just because I'm like, I love Big Daddy

Anthropic, although I do, it's because I

just think this is a much safer and

better solution than something like,

you know, what most most other people on

on Twitter and X are probably shilling

you. If you guys like this sort of

video, please sub to the channel. Around

70% of you guys aren't for whatever

reason, so you'd be doing me a big

solid. Like and then comment down below

with whatever the heck you want me to

make videos on. I really make videos

based off of audience feedback at this

point. So, if you guys want anything in

particular you want me to record or

cover, let me know. I'm more than happy

to do it for you. Have a lovely rest of

the day. Catch all y'all in the next

video.