June 10, 2025 • 37 mins
Powerful AI tools like Manus and Genspark can supercharge your workflows — but how do you experiment with them safely, without risking your hardware or exposing sensitive credentials?**
In this hands-on live session, I'll walk through exactly how to set up a safe environment to test and run these tools — no technical deep-dives, no unnecessary risk, and definitely no panic if something breaks.
You’ll see step-by-step how to experiment freely while keeping your systems locked down. This is the same approach smart organizations are using to move fast *without* accidentally opening security holes.
Whether you're a curious leader or just tired of hearing "don’t touch that," this session is your green light to explore powerful tools without guardrails — because the guardrails are already built in.
About Leveraging AI
- The Ultimate AI Course for Business People: https://multiplai.ai/ai-course/
- YouTube Full Episodes: https://www.youtube.com/@Multiplai_AI/
- Connect with Isar Meitis: https://www.linkedin.com/in/isarmeitis/
- Join our Live Sessions, AI Hangouts and newsletter: https://services.multiplai.ai/events
If you’ve enjoyed or benefited from some of the insights of this episode, leave us a five-star review on your favorite podcast platform, and let us know what you learned, found helpful, or liked most about this show!
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
GMT20250605-155522_Recor (00:00):
Hello, and welcome to another live
(00:02):
episode of the Leveraging AIPodcast, the podcast that shares
practical, ethical ways toleverage AI to improve
efficiency, grow your business,and advance your career.
This is Isar Metis, your host,and we have a fascinating
session for you today.
Why fascinating, because we'regoing to dive into advanced AI
agents and how to use themsafely and.
I'll explain first of all, whatthe hell all of that means, and
then we're gonna dive into apresentation.
(00:24):
Then we're gonna dive to theactual tools and the process
itself.
But on a high level, a new typeof agents emerged, a few months
ago, Manus, earlier this year,and then Gens spark shortly
after.
Manus is a Chinese company.
Gen Smar is an American company,I think from California.
They do similar things.
They're kinda like a generalizedagents that can do more or less
anything, that you, that yourbrowser can do.
So it get access to everythingyou have access to in the
(00:46):
browser, including tools,including browsers and websites,
including writing code,including creating web
applications and so on.
and you can do a huge variety ofthings with it.
And I was very curious on.
How to use it and how, I canplay with it and how far can I
push the envelope.
But I was really scared becauseI run everything in Chrome.
Chrome is my entire universe,and if something gets corrupted
(01:06):
in Chrome, I'm screwed.
Like literally everything thatI'm running, runs in Chrome.
and in addition, Chrome savesall my passwords to everything
on the planet.
And so if it gets access tothat, I don't know what it.
Might get access to that I'm notinterested in, or if it changes
any of the passwords forwhatever reason, then I'm
screwed.
Stuck outside of tools that Iwant to use and so on and so
forth.
So I had this issue with givingit access to my computer or
(01:27):
giving it access to I.
my passwords or everything in mychrome or my Google account and
all these things, and yet Ireally wanted to test these
tools and that led me throughthis quest that I'm going to
share with you today in detail.
Now at the end of the episode,after I show you the process on
how to put these tools in a boxthat where they're confined, but
you can still do everything youwant.
I will show you a few examplesof what you can do with these
incredible tools just to inspireyou to try.
(01:49):
Yourself.
So let's get started.
I will start by sharing myscreen.
Those of you who are joining uslive, first of all, thank you so
much for joining us live.
those of you.
who are not joining us live.
you should join us live.
We do this every Thursday atnoon Eastern time.
you can join us on LinkedIn, youcan join us on Zoom, and then
you can ask questions and be inthe chat and so on.
But those of you who are here inthe chat, feel free to introduce
(02:10):
yourself.
Say where you're from, why areyou interested in agents and
what your current experience.
So I know, what we're dealingwith and, And that's it.
And we're gonna get started.
I'll say one more thing.
this is gonna be a more advancedsession.
We're gonna talk about a lot ofadvanced stuff, but a hundred
percent of the things that I'mgonna share with you today, I
did for the first time ever whenI did this, which was, I dunno,
two, three months ago when I didthis process.
(02:31):
So everything that I'm sharingwith you may sound sophisticated
and advanced and complicated,but I knew zero.
It when I got started and withinan hour later I was able to run
these agents without anyexternal guidance.
So hopefully, with my guidance,you'll be able to do it in less
than an hour and have access tothis amazing new tool and
capability.
in addition, we teach basiccourses.
(02:51):
We teach courses that we've beenteaching for the last.
Over two years.
So the first course was in Aprilof 2023.
We teach at least once course amonth.
Right now I'm actually teachingtwo in parallel.
Most of these courses areprivate organizations and group.
Invite me to teach their people,their organizations consortia,
different membershiporganizations and so on.
So if you're in suchorganization, feel free to reach
(03:12):
out to me on LinkedIn orsomewhere and I'll gladly share
the details with you.
But we do public courses thatanybody can join once a quarter
when we have the bandwidth to dothat.
As I mentioned, we're justfinishing, one course that
started a few weeks ago, andthen the next public course is
going to start on august.
So if you wanna know how to jointhe August course, and you
should, if you haven't taken anyformal AI education yet, it's
(03:32):
literally going to change yourlife.
It's gonna change your career,and if you're in senior
position, it could change yourbusiness.
So go check up the link.
we'll drop the link in the chatright now and we'll drop, the
link in the show notes if you'relistening to this, afterwards.
But with that, let me share myscreen and let's dive into the
topic for which we are, heretoday.
(04:30):
So we'll start with a generalconcept of what the hell are
agents and how they're differentthan a chat.
'cause we.
People who are listening to thispodcast, I assume most of you
are already using multiple chattools, whether it's Gemini Claw,
Chachi, pt, deep Seek, etcetera, you choose your poison,
or maybe you're more advanced,you're using all of them, or
some of them depending on thespecific use cases.
and you're asking yourself whatthe hell are agents and how
(04:52):
they're different.
And there's several differentways in which agents are
different than chats.
The main thing is autonomyagents have levels of autonomy.
Some of them are fullyautonomous, some of them have
levels of autonomy.
But if you think about a chatonly does what you tell it to
do.
You have to explain to it.
Go and check the information onthis website, summarize the
information.
Put it in the table in this andthat format.
(05:12):
Create a code to do this orthat.
You tell it what to do and itfollows your lead in your
instructions.
An agent has, as I mentioned,different levels of autonomy,
but.
It has autonomy, meaning yougive it a goal or a broader
tasks, a task, and it will giveitself sub-tasks and steps and
tools that will allow it tocomplete the task or the goal
(05:32):
that you've set for it.
And that process that is gonnago through is gonna be its own
process.
The more advanced agents alsoevaluate their own process, so
they stop on the way they seewhat they've done.
If they need to correct things,then they will correct them.
and This is the first thing.
The second thing is access totools.
So this is something where theline started blurring recently
where different.
Chat platforms like Chachi, PTand Claude are having more and
(05:54):
more connectors to externalplatforms, but it's still
relatively limited.
While agents usually have accessto any tools you're gonna give
them access to.
And if it's a browser basedagent, like the one we're gonna
look at today, it has access to,everything in the browser,
meaning can go, it can go towebsites, it can write code, it
can execute, things and so on.
And so they have access to toolsthat usually.
Chats will not have access to.
(06:15):
They can work in multi-tierapproach, meaning when you go to
an agent environment, you canhave an orchestrator agent that
will talk to other lower tieragents that by themselves can
have access to even lower tieragents and really work like a
team or chat.
It's usually just the chat.
And so these are the maindifferences between what are
agents and what are justtraditional ai, large language
models.
(06:35):
The next thing is.
What are Manus and Gens spark,and what kind of agents are they
and what they can do?
So Manus.
When it came out again out ofChina, kinda like blew
everybody's minds.
It was kinda like a second deepseek moment where suddenly a
tool out of China comes out ofnowhere that nobody heard about
and enables people to do magicalthings.
And what it allows you to do iscombine multiple things that
(06:56):
existed before.
Into one environment that isthinking and operating on its
own to try to help you completethe goals.
And since it came out, theyadded many more functionality.
As an example, right now, it hasthe ability to create complete
PowerPoint presentations.
I.
which means you tell it.
What is the presentation about?
You tell it where to researchand what to research, and you
will create an entirepresentation for you.
They now added in this past weekthe ability to generate videos
(07:19):
so you don't, again, differentthan video generation tools
where you have to create everysingle.
Component in every single sceneon your own and then stitch them
together.
It knows how to do all of that.
You tell it what the movie needsto be about, you define the
overall storyline, and it cancreate every single scene and
stitch it together and create alonger video, combined of all
these scenes all on its ownwhile defining all the different
components and all the differentsteps.
(07:40):
So the.
Power here is incredible becauseyou basically tell it what you
want to achieve.
And again, I'll show youexamples at the end, and then
they will go and achieve it.
They will figure out what shouldbe the process, what tools they
should have, that should use,and what are the different steps
that they should take, and thenthey go and execute.
And I've seen it happen in fiveminutes, and I've seen it happen
in 45 minutes, and it just takesas long as it takes for it to do
(08:01):
the thing on its own.
And it's the future thateverybody's.
Most likely not ready for moreor less available for you here
now it's not fully available.
It still has limitations.
It doesn't always work, but it'sa very.
Obvious view, like a window intothe future that we're walking
into, and hence why it's a verypowerful environment to
experiment with, to see whatthese tools can and cannot do,
(08:22):
and how to prompt them betterand how to work with them in
order to achieve things that youmight be able to achieve with
the chat or with severaldifferent chats.
But it will take you a lot oftime because you will have to do
all the steps when here you justtell it what you want it to do
and it will go.
Do it.
And so this is what these toolsare.
As I mentioned, my biggest thingwas security risk.
Like I did not know how I canactually get into a scenario
(08:45):
where I can run these toolssafely.
And so with that, let's talkabout what was the solution and
what was the outcome that I gotto, and you'll gimme just one
second.
Oops.
Okay.
so first of all, let's talkabout, before we dive into the
(09:06):
solution, let's talk about whatthe risks are.
And there's a variety of risks.
The first risk is just security.
Like I said, they potentially,because they have access to
everything in the browser, andif you're logged into many
things in the browser, that alsohas access to different
components that you have.
it may have access to differenttools and things that you don't
necessarily want it to haveaccess to, meaning it may have
(09:26):
access to your bank account andthings like that.
It may have.
Behavioral risks, meaning it maybe able to do things that you're
not expecting it to do as far asthe process that it's going to
follow, and then harm thingsthat are your regular processes,
things that you're doing inregular platforms that you're
using and so on.
It may also have integrationrisks.
Think about it.
(09:46):
It is your.
Chrome browser is integratedinto multiple aspects of things
that you're doing.
And through that it can get thesame kind of access to other
platforms.
It may ruin the integrationsthat you have, because it's
gonna make changes to differentsettings and different so on.
And, when you think about it,it's, and that's my real life
analogy, is it is a intern.
(10:08):
That doesn't know necessarilywhat are the risks of your
business or your personal lifeand what information is, is
specifically.
Classified or somehow sensitive,and you're giving it access to
all of that.
So think about bringing a newintern into your company and
giving it access to everything,every piece of software, every
piece of access, every passwordthat you have and saying, Hey,
(10:29):
go and do this thing.
And you don't really necessarilyknow how it's going to evolve
and how it's going to happen.
And so there's a huge wide rangeof risks and you need to know
how to.
Put it in a box and still beable to use it.
So there are multiple solutionsthat I found, and the way I
found these solutions, and we'regonna dive into this, is by
having a conversation withChachi PT about the whole
situation.
What I'm trying to do, and I'mgonna share this with you in a
(10:51):
minute, but I'm gonna first ofall share with you what was the.
What was the final solution,that I've used in order to do
this?
And the final solution, whichagain, we're gonna go through
step by step, and I will showyou and explain to you exactly
how you can do it on your own.
is basically following thisprocess, I created a Google
Cloud.
Environment, which again, ifthose of you who've never done
(11:12):
this and don't know what I'mtalking about, and it sounds too
techy and complicated, I did notknow anything about this when I
got started, right?
So it, it was the first time forme setting a Google Cloud,
environment as well.
The second component is avirtual machine.
What is a virtual machine?
It's basically a.
A computer within that cloudenvironment, so that computer
can be just exactly like yourcomputer, meaning you can
(11:35):
install things on it, you canrun things on it, you can open a
browser in it, and so on, butit's just not really your
computer.
The third component is a newGoogle user.
I did not wanted it using myGoogle account because as I
mentioned, it has access to toomany things, and so I created a
new Google user.
So that costs you nothing.
I created a free Google user,and that's the one I'm using to
access everything in that newenvironment.
(11:57):
I installed a chromium browser.
You can install Chrome as well.
Chromium is just an open sourceversion and it can run as
effectively.
It just takes less memory andhence you need a smaller.
Virtual machine, which thencosts you less money.
I also had issues withinstalling Chrome in the
beginning, and that's whyChromium was a good option.
And then the last component is aremote desktop.
What is a remote desktop?
A remote desktop is basically asolution.
(12:19):
That is very easy to set up.
And again, we're gonna gothrough that.
That allows you, from yourcomputer, from my perspective,
from my computer, to access thatcloud computer that lives
somewhere in a Google server,right?
So the combination of all ofthis gives me access to a
computer that is not my computerwith a Chrome browser.
That is not my Chrome browserwith a Google account that is
(12:39):
not my Google account.
And in there I can safely runwhatever I want because if it
craps out, nothing happens.
I can kill that instance of thevirtual machine.
I can install a new one andstart all over again, and
nothing serious can happen outof that.
Another way to do this, by theway, if you have an older
computer that you're not using,that's a very simple way to do
this, then you don't need any ofthat.
The disadvantage is you need twocomputers, right?
(13:01):
You need your own computer torun your thing, and when you
wanna run experiments, you needto switch to the other computer
and then run whatever you wanton that other computer with a
new Google account and a newchrome, browser, and you can do
the same exact thing.
that would've been my choice ifI wasn't successful actually
running it all from my computer,which obviously is a lot easier
because I can run everything onmy machine when I travel, I have
it with me, and so on and soforth.
So there's a lot of benefits indoing it this way.
(13:24):
So with that in mind, let's lookon how I actually did this, and
I see that there's a fewquestions.
is it using temporary mailaddress also to save, the same
way?
Yeah.
So it's basically a full Googleaccount that I'm using to do
this thing.
So it's, It's a full Googleaccount, just a free account.
What you're looking at right nowon the two sides, one is the
Google Cloud environment, andthe other is the conversation
(13:44):
that I had with, Chachi pt.
So I will start with the firstprompt and then we'll go through
that and I'll explain what I didand I'll show you how I followed
it.
Its instructions without knowinganything, a lot of it I still
don't understand and it worksand it's very helpful for me.
So the prompt was, I'm lookingfor a safe way.
To run Manus and other AI agentson my Mac, it needs to be a
separate universe than all myregular applications and
(14:04):
everything I use.
The best options would be to runit on a remote server.
The second best would be aparallel machine on the Mac.
I'm open to any othersuggestions and would like to
know what are the pros and consof each options.
How much would it cost, ifanything, and what are the
technical skills required to setit up?
Pretty generic.
And that helps me go through theprocess.
And it then, asked me a bunch ofquestions.
(14:26):
are you looking for man or otherAI agents?
Do you have a preference of thecloud provider, whether AWS,
Google, or Azure, and so on andso forth.
I provided answer to thequestions and then it gave me a
long and detailed answer and itbasically said, okay, safe
isolation options, running AIagents, remote versus local.
And then it said remotedeployment options, cloud
options.
One of them is GCP virtualmachines, so that's what I ended
(14:47):
up going up with.
Google Cloud platform, virtualmachine.
the pros.
Strong isolation, fine.
Grain control, free tieravailability and scalability.
So it's not really free, but youget 300 credits,$300 credits
from, Google when you set up anew virtual machine.
this thing is costing me between15 to$20 a month to run.
if I'm gonna go crazy, it'sgonna cost me like$25 a month.
So I get about, a year and ahalf to two full years of
(15:10):
running this.
Basically for free, and then Ican always set up a new account
and run it again.
but either way, it's a great wayto run this.
Disadvantages set up complexity,so you need to know what you're
doing, ongoing management.
You're responsible for thevirtual machine and operating
system.
I've been using it for three orfour months and I haven't done
any maintenance.
So there is no real ongoingthing and cost for larger
instances.
If you're going for biggervirtual machines and doing
(15:31):
bigger, more complex stuff, thenit's gonna cost you more money.
but this is not the case for meright now.
Then it gave me the option forAmazon Web Services and how to
do it over there, and then itgave me options on railway.
So I told it about railway inone of the options.
Railway is a.
Hosting platform that I use torun my N eight n platform, and
it has container solutions.
(15:52):
Those of you, again, who don'tknow containers, think about it
as a software package that haseverything the software needs
packaged for idiots like me torun.
So you don't need to know how toinstall and connect and APIs and
all of that.
There's a container, you drop itin, it installs everything
within the container, and you'reup and running without knowing
anything that you need to do.
So those of you who areinterested in running NA 10
without.
Basically on your own instance,you can use railway, but in the
(16:13):
same way, you can do this,right?
You can install a railwaycontainer that has chrome and so
on.
the disadvantages were resourcelimits in sleep, which is
something that would happen.
The hobby plan is$5 a month, andyou may need a bigger plan,
which would be$10 a month, whichwould be more expensive than the
free version that I'm basicallyhaving in Google.
And so on and so forth.
Mac Stadium, which is a remoteMac hardware rental, basically
(16:34):
allows you to run a virtual Mac,through your Mac on a browser.
And then local isolation optionson my Mac.
So you can run a virtualmachine, kinda like a parallel
or VMware on your device.
Those of you who are using Maxand using, parallel to run.
Microsoft Office as an examplein Windows, know what I'm
talking about.
So you can run like a parallelmachine on your computer.
but then again, there's pros andcons for that.
(16:56):
So after going through all ofthis, and it gave me a lot of,
and those of you who are notwatching the screen, just
listening to this is like a 10page long summary with clear
details on each one with a tablein the end that summarizes
exactly all the pros and cons.
And the first option was.
The Google Cloud as the mostfavored options.
So that's what I went with.
And literally the prompt that Iwrote is, what is the
step-by-step process of settingthe GCP solution?
(17:18):
And then he told me, step bystep for Google Cloud, create a
Google Cloud project.
I.
I went to Google and went toGoogle Cloud and it says, go to
the Google Cloud console andgave me a link to go there and
you click on your project.
So now on the other screen, onthe Google Cloud, on top,
there's a little square that hasthe projects and you can click
on your project, which I alreadycreated for this demo, and I
called it Chrome vm.
It has nothing in it yet.
(17:38):
You can see it's an emptyproject.
It's just a shell.
It's a name for me to createmore stuff.
And then it says Create aproject id, which I created.
Then set up billing.
So that's in here on the left.
If you click, there's a menu andyou have all the different
things.
And when I say on the left, it'sthe leftmost menu in Google
Cloud, and it has all thedifferent components that Chachi
PT told us to go to.
So you go to billing and you setup a way for it to charge you.
But as I mentioned, you're gonnaget$300 worth of free.
(18:00):
Credits, which is gonna be goodfor probably almost two years.
then it tells you need to enabledifferent APIs and you enable
these APIs for this project.
So how do you do that?
So it tells me what to do, saidin the cloud console, navigate
to APIs and services library.
So you can see here on the left,there's in the menu, one of the
says, says API services.
And you can see underneath thatwhere it says library in the sub
menu.
And you click on that and ittakes you to where it has.
(18:22):
All the different APIs thatGoogle Cloud allows you to run
on one of your projects.
Now again, those of you who getdiarrhea just from hearing the
acronym API, because you don'tknow what it means and it sounds
really techy, it doesn't matterbecause you don't need to know
anything.
So what you can see, it tells meto install or to make sure I
have Compute engine, API Cloudstorage, API Cloud, logging API,
and cloud monitoring API.
So like a good monkey, I'm justgonna copy the first one.
(18:45):
Compute engine API into thesearch over here.
And paste it in the search.
He'd search and it comes up andI'm gonna click on that and I'm
gonna enable that, to thisthing.
So literally I'm just copyingand pasting and click clicking,
manage and apply, and I'msetting up all the APIs that I
need.
I can show you a slightlyshorter way to do this.
So without navigating toanything, if you're just on the
(19:05):
home screen of the, of theproject, you just set on the
very top, there's a search.
It's like a general search foreverything.
Google Cloud.
So if you search here forcomputer engine API, which again
I copied from the instructionsfrom Chachi pt, you can see it
finds different things.
One of them is the APIcomponent, and you will take him
to the same exact place.
(19:25):
So even if you don't know how tonavigate and where to navigate,
you can just copy and paste tothe top search and activate
those things.
Then it's telling me toconfigure identity and access
management.
The short for this is IAM.
And again, it tells me exactlywhat to do.
Go to IAM admin.
So I'm again, good monkey, gohere, go to IAM and admin, and
then click on that.
And then just add users.
So it tells me how to do that.
(19:46):
create an instance, add theusers and tell me what to do and
what permissions to give.
And I just follow theinstruction step by step.
The next step tells me to set upthe virtual machine.
Same thing, go to ComputeEngine.
So I go back to the menu, I goto compute engine.
And I go to a virtual machine,which is VM instances, and
that's exactly what theinstruction says.
So I click on that and you cansee right now I have no
(20:08):
instances there.
What this will basically allowme to do is to create a computer
in this Google Cloud environmentthat we just set in.
Two minutes.
So I click on Create Instance,and then again it walks me
through exactly what to do.
There's all these really complexand scary options on the screen.
Those of, you're not seeing,there's like multiple things and
buttons to press and drop downmenus, but you be a good monkey.
give it a name.
And so the name is gonna bewhatever.
(20:30):
and then, choose a region.
So you can see here it saysregion and I can go and select
where I am.
So I'm in the southeast us.
So I'm gonna create a US East.
I'm gonna pick the server that'sclosest to me, which in this
case is in South Carolinabecause I'm in Florida.
and that's it.
Then the next thing it says, themachine configuration choose E
two, which is the default, whichis the low cost day to day,
thing.
So that's the cheapest versionthat I can run.
(20:50):
And then it says, what boot discdo I need to run?
So it tells me what operatingsystem.
So in the next side, left menu,it says operating system and
storage.
And here I actually started withthis initial recommendation of
running a Linux distribution.
And then after a longconversation with it where
things didn't work for me, Iasked it to start from the
beginning.
And we actually, ended up usinga different operating system,
(21:10):
which is called Ubuntu.
and again, I don't even knowwhat that means.
I don't know what thedifferences are.
I just know that it worked afterI had all this long conversation
that didn't work.
Let me scroll down to those, tothat section.
Here we go.
So these are the updated ones,and then it told me to install a
different operating system.
How do you create a differentoperating system?
(21:30):
You go here in the OS segmentand you click on change.
I.
And then you pick what operatingsystem you want.
So instead of Damian, I'm gonnachoose Ubuntu.
and that's it.
And now you can choose whicheverversion, which doesn't really
matter.
You just keep on updating theversions all the time.
And I, and then the next step,and I click select, and now I
have a new operating system.
How cool is that?
knowing absolutely nothing.
I can create a machine in thecloud that I can run.
(21:51):
And then there's the other,steps of creating data
protection and networking.
So I have to allow it.
HTTP traffic and https traffic.
Again, I'm just following theinstructions that it's giving me
and that's it.
And you hit create and it'sgonna create.
A new computer for you in thecloud.
Now that computer still doesn'thave anything in it, so later on
it will take me through thesteps of installing two things.
(22:14):
One, it will show me how toinstall.
And again, the instructions areright here and the code I need
to run is right here.
So it said in the SSH terminal.
Again, don't be scared.
Just find SSH.
And once this thing will stoprunning, you'll see here there's
an SSH button.
So I don't know what it means.
I don't know what it does, but Iclick on it and then it will run
its thing and ask me to confirmdifferent steps.
And once all the steps areconfirmed, and you can see
(22:35):
authorized SSH, and I can, Iwill tell it which Google
account to use and then I will.
Establish a few things and I geta terminal window.
Terminal window.
Looks like all dos, right?
It's just like the ugliest thingin the world, but you don't need
to know anything.
I've got the code.
All I have to do is copy thecode.
From here, there's even a copybutton and I click copy and I
paste the code in here and Ilater it run and it will do its
thing.
That's it.
It's that simple.
(22:56):
So I go through all these steps.
The first step will install, theupdates that I need.
The second step will install thedesktop environment, and the
third step will install GoogleChrome and then remote desktop.
So I literally, I'm gonna stophere by showing you all the
different steps, because thenext steps are exactly like this
is copying the code from theinstructions in Chachi pt.
And I'm gonna share with you alink in the show notes to these
instructions.
(23:17):
So any one of you can literallycopy.
Everything that I've done, stepby step and use it as your own.
And you can see it's running alot of code now in the terminal,
which I don't have a clue whatit's doing, but it's not on my
computer, so I don't reallycare.
It's running in this virtualmachine in the cloud.
And so what it ends up being,after I'm installing all these
different things, I'm gonnainstall remote desktop on micro
chrome browser, the one on mycomputer.
(23:38):
And you can see here that's instep six, configure Chrome
browser, remote desktop.
So it tells me exactly how toset it up.
very simple.
And once I'm done, what I'mgetting is I'm getting this and
I'm gonna make this full screen.
So what I'm getting now is youcan see I have a browser within
the browser.
In my regular browser here ontop, you can see I have the chat
(23:59):
that we had before and I havethis AI agent sandbox instance,
and it's a remote desktop intothis remote machine.
In here, I have my new Googleaccount with emails that I can
send back and forth from my realuniverse or my real computer I
can send emails to here withdifferent things that I need and
tools that I need and promptsthat I created and so on.
Because remember, this is not mycomputer.
(24:21):
This is another computer.
And then I have Spar, and I haveManus and I have a lot of other
things running.
So this is basically how thisthing runs.
I now have.
A new machine that you literallycan follow the same exact steps
that I'm gonna share with you tohave a separate machine that is
not my machine logged in with adifferent Google user that I've
created, and now I can dowhatever I want without risking
(24:42):
anything that I have while stillrunning on my own computer.
So let's, I promised you a fewexamples, and I'm gonna show you
two separate examples.
one of them, I'm gonna show youthe comparison between the two
different tools.
I used the same exact prompt onboth tools.
By the way, the prompt wascreated by Claude.
So I explained to Claude whatI'm trying to do, and I asked
Kate to create the prompt, andthen I copied the prompt here.
Now again, you cannot copy andpaste from your computer to this
(25:03):
because it's not the samecomputer.
So what I do is I.
Email this from my regular emailaccount to this new Gmail
account, and then it shows up inthe email tab that I have here
in the new machine.
I copy it from this.
Gmail in my virtual machine intospar or so on.
So in this particular case, mykids go to the local Scouts
(25:25):
chapter and we are now finishingthe year and planning for next
year.
And both my wife and I arevolunteering there since the
kids started going there aboutnine years ago.
And We are every year we arelooking for ways to raise money,
so we have the funds to run thescouts in the most efficient
way.
And one of the things that I'mdoing is I'm looking for grants.
And previously, in previousyears I did it manually.
I would go through dozens ofwebsites, looking for different
grants and where they're fromand other applicable and so on.
(25:47):
I said, Hey, wait a minute.
I have these agents, maybe theycan help me look for grants.
So I explain what I'm trying todo to Claude.
And Claude wrote this prompt,objective, automate the i, the
identification and initialvetting of grant opportunities
for a nonprofit in Maitland,Florida.
background local scouts, noprofit, blah, blah, blah.
Serving one, first through 12grades, youth run troops with
parent volunteers, activities.
(26:08):
What all the stuff basicallythat I told it is in there.
And then the scope.
Search scan.
Federal websites, county localsources, plus private sectors,
prioritize opportunities, blah,blah, blah, blah, blah.
There's a whole explanation ofwhat I would've done manually.
And then you hit go and youleave for 20, 30 minutes and it
does its thing.
So what do I mean by does itsthing you can see?
The first respond is I'll helpyou identify and vet grant
opportunities for your scoutnonprofit in Maitland, Florida.
(26:30):
Let me break this down intosteps and search the relevant
grants based on therequirements.
By the way, the last thing thatI ask for you to do is to create
a user interface for me to trackthe different grant
opportunities, what's the statuswith each and every one of them,
and to basically see all theinformation, which those of you
who are watching the screen cansee it on the right, but what
you can see is that it's.
It's now gonna use differenttools.
The first tool, it's usingsearch.
It says Grants for youth inOrange County, Florida, or
(26:51):
Scouts.
And if I click on view.
I can see all the websites thathe was searching, I don't know,
about 15, 20 websites.
And then it started loosesearching more and more things
each and every step.
It's learning more stuff andit's updating the plan on how
it's gonna execute on that.
So it's gonna do.
Deeper and deeper dives intodifferent things.
So if I dive into this one, youcan already see the grant
description, applicationsubmission information, so it's
(27:13):
diving deeper into each of thethings that it found previously,
and it goes on and on.
And it's creating tables andit's then summarizing the tables
and it's writing more stuff andit's doing additional research.
So you can see it's doing allthese things and finding
different stuff.
And in the end.
I ask it, like I said, to createa tool for me to track all the
information.
So if I keep on scrolling downthrough this very long process
and in the middle, I jumped inand gave it additional comments
(27:33):
when it was done with, differentsteps.
And at the end it created thisfor me, which is a website that,
again, those of you're notwatching, I apologize, but
you're missing out.
But it has a.
Color coded.
Website that has all thedifferent opportunities in a
(27:55):
table where I can search andfilter by anything that I want.
So I can filter by, either is ita federal, state, county, city,
private, Jewish community orinternational fund.
I can look by, statuses.
So I have a status dropped onmenu that I can update on my
own.
I can see the amounts.
I can see the deadlines.
I have a link straight to theopportunities that I can go
straight into there.
But the cool thing is, in thisprocess, what I asked you to do,
(28:18):
I said, I want you to help mealso write the request for
grants.
I want you to actually write theproposals.
And what I did in order to dothis, I created a whole task
section.
When I say I, I didn't doanything.
I ask it to create a tasksection, and this task section
allows me to give the.
AI agent additional tasks.
So you can see, I can choose aspecific grant.
It picks it automaticallybecause I'm in that grant.
(28:38):
And then I can select the type,research, Eligibility and
requirements, write submissiondocuments.
I can go to write submissiondocuments.
I can then write it a detailedprompt.
I can give it a priority, I cangive it a due date.
I can assign the task and thenit's going to execute on that.
It's gonna read everything inthat website and it's gonna
write a draft for me, and it'sgonna put it in the documents of
this particular opportunity.
This is pure gold.
(28:59):
I invested.
10 minutes.
It invested 45 minutes, and Inow have a extremely effective
way to go after grants acrossfederal, local, county, city,
private, and so on that arerelevant to what I need to do
with a website in which I cantrack the status of each and
every one of the activities andfilter and see progress and so
(29:20):
on.
This is nothing short of magic.
This process would've taken ateam of several people, several
different days to create, andyou need a web developer and you
need a researcher, and you needan analyst, and you need all
these things, or you yourselfspending hours to do this.
I did, like I said, the sameexact thing I.
On Manus.
Manus came out with something alittle different, by the way, on
(29:40):
both of them, both on Manus andon, spar.
You can publish this thing, sowhen you see this really cool
website up here, there's apublish button that I can, click
and then I can open it as abrowser window that then I can
share with people.
Then they can run it in a realenvironment, not in a virtual
environment, because this isjust a website that it created.
So this website is publicly actavailable.
I can send it to people and Ican collaborate on this process
(30:02):
with additional people because Ican very easily share that
website.
That is a tool to track ourprocess.
I did the same thing in Manus.
So let's look at the Manusexample.
you can see Manus took aslightly different approach.
Again, I didn't tell it exactlywhat to do.
I said I want an applicationthat will allow me to filter and
see, the different applic, thedifferent opportunities.
So it took a slightly differentapproach, but very similar in
concept, each and every one ofthem in a different box.
(30:24):
What's really cool here, goingback to the autonomy part of
this, and it's takinginitiative, it gave a score to
each and every one of theopportunities based on how.
Applicable it is, what's thedeadline and what are the funds
that are available?
And you can see scores in thesixties, in the fifties, in the
thirties, and then some of themare zero because it found them,
but it doesn't think it'sapplicable to us.
And so it actually helps meprioritize what's to go after
(30:47):
first, which is really awesome.
And again, it has a filteringcapabilities and, search
capabilities.
Just like we've seen on gensspark.
I like the gens spark, userinterface better, but from a
practicality perspective,they're both highly practical
for my needs.
The last thing that I wanna showyou is something that is more
business oriented, because mostof you are in businesses and not
in, Not in nonprofit, but youcan, you hopefully get the point
(31:09):
even from the nonprofit thing.
What I've done here is actuallysomething that one of my clients
has done initially and I justuse and follow their same
concept, is they are in thesmart home automation world and
they wanted to find.
Ways to look for additionalpartnerships in that world.
So if you're in the smart homeautomation universe, you cannot
do projects on your own.
You need an architect that willwork with you to implement all
(31:31):
the stuff that you're planning.
You need a builder.
A GC that will actually do thework.
You need an interior designer,so you need all these different
things.
And if you find more of them inthe area in which you work, you
have more chances of gettingwork.
And the way we've done this iswe've actually giving it names
and websites of existingpartners, one of each, one
architect, one interiordesigner, and one GC in order to
(31:54):
start.
And we basically told it toplay.
Six degrees of Kevin Bacon.
Basically go and look for peoplethese companies have done
projects with, and then look forpeople they've done projects
with, and then go and look forpeople they have done projects
with.
And then give me a userinterface in which I can see
each and every one of thesecompanies, what projects they've
done.
Where are they in the world, andwhat's their website?
It did all of that and itcreated a user interface, which
(32:16):
again, now I have a search whereI can search for specific, and
you can see here it saysarchitects and I have a list of
architects, and then I haveinterior designers, and I have a
list of interior designers, andI have builders and construction
companies, and I have them, butI can filter the list very
easily.
Let's say this is all inSouthern California because this
is what it's searching for.
So let's look for Orange County.
So if I type orange, you can seeit filters it out.
It found no architects and nointerior designers, but it found
(32:38):
several different builders thathave done relevant projects that
I can go and look at the actualprojects.
I can click on the links and soon.
You can build any tool for anybusiness purpose that you want
with this.
Now again, it doesn't alwayswork the first time.
It doesn't always work, period,but it gives you.
Again, a window into the future,and it gives you the ability to
use some of these tools in thepresent, like both this and the
(32:58):
other thing that I showed you isthings that are in use.
They're actually providingimmediate value after investing
a few minutes in creating them.
So let me stop sharing.
And I'll open it to, questions.
There's a question, spar versusManus, and which one do I like
better?
I'm on the fence.
Like I, what happens is, in somecases I see better, success with
(33:19):
Spar and in some cases seebetter success with, Manus.
And so it's, it just depends.
And in, in general, I thinkManus does better research.
And Gen Spar creates better userinterfaces, but that's on, five
or six projects.
I don't think that's likenecessarily the case a hundred
percent of the time.
that's why I'm always tryingboth, like literally everything
that I have, I'm dropping intoboth of them and I'm letting
(33:41):
them run.
And if one of them has a better,start, then I will continue with
that one.
If they both have a decentstart.
I will continue with both untilI get to a situation where I
know what to do next.
Jonathan said it would make itmuch easier if you could build
an agent to set up the secureagent.
I think we'll get there.
I think we'll get there wherethe agents will be able to do
everything that I did.
I don't think we're there yet,but as I mentioned, it took me
(34:02):
about an hour to figure thisout, right?
I went back and forth and what Idemoed to you now in 20 minutes
of the setup.
Actually took me about an hourto set up because a lot of
things didn't work in thebeginning, but after an hour it
did work, and now I'm using itall the time and I'm using it
safely and so on.
So the, it's as much as itsounds complicated, it's worth
investing one hour of your timeto having a solution like this
that is completely, disconnectedwith a very serious Chinese wall
(34:24):
between that and your realuniverse.
And then you can do whatever youwant.
Okay, so quick recap andsummary.
The.
AI agent world is the presentand it's definitely the future.
There are many companies whoprovide agents that are very
specific to specific things,like you can build voice agents
to take phone calls or to dooutbound.
You can build agents to manageyour emails.
(34:45):
You can build agents to docustomer service.
You can build multiple types ofagents, but then you have this
new universe of general agentslike Spar and Manus, and with
those, they.
Can do more or less anything youwant because they can browse,
research, summarize, connect todifferent systems and tools,
write code, deploy websites, andso on.
And I think that right now it'smore geeky like it's people like
(35:06):
me and more advanced users thatare actually playing with these
tools to do these differentthings.
But two things I think willhappen.
One is I think these will becomemore and more.
Mainstream as time goes by.
But the other thing that I'mpretty certain of is that Cha
GPT has something like this, andthe only reason they didn't
share it yet, and they have.
Shared a version of this, right?
(35:26):
So they have their solution thatis currently available only to
the upper tier.
And it's the same, but notexactly, doesn't have the same
freedom and capabilities asManus and Spar.
But there's zero doubt in mymind that in-house they have it.
They're just thinking of how andwhen to release it.
A, so that the public knows howto use it.
B, that it's safe, and C, thatit doesn't completely destroy
the bandwidth of their serversthat are already running very
(35:49):
heavily doing everything thateverybody's doing.
But once they figure out a wayand the right timing to release
something like this, it's gameover, right?
Because right now there's 700million or 800 million chat PT
users.
If you give them this capabilityto basically say, Hey, I want
you to do this.
Go do this on your own, and itwill.
You will jump from, I don'tknow, tens of thousands of
people are doing it right now tohundreds of millions of people
(36:10):
doing what I just showed you.
And because it'll be ChachiPiti, I think people will feel a
lot more comfortable than I'mfeeling with Gens, spark, and
Manus.
And then.
Just everybody will start usingsolutions like that and creating
their own applications and doingtheir own research and summary
and so on.
And because Chachi PT isbuilding more and more
connectors, whether through MCPservers or just native
connectors to, Google andMicrosoft environments and,
(36:31):
other big solutions out therelike ERP systems and CRMs and so
on, these tools will be.
The ultimate power extender ofevery single person, right?
You'll be able to ask it to doany research across any data,
internal and external, eitherone or the other, or a
combination, and get results inwhatever format and report it to
any other third party systemthat you would want just by
asking in simple English.
(36:52):
And so the ability to do thingsthat today takes teams weeks.
Be able to set it up in minutesand then enjoy them from that
moment forward are.
Coming and they're coming veryfast.
So my suggestion, go experimentwith what I just showed you.
Follow the instructions step bystep as I did, and as I showed
you right now.
And learn what these tools aregood at, what they fail at, how
(37:12):
to prompt them better so when itdoes become available, or just
start enjoying it right now.
But if it becomes available inyour work environment, you are
more ready than everybody else.
Thank you so much.
Hopefully you found this,valuable.
And, as I mentioned, there's acourse coming up in August.
Go sign up for that.
The courses fill up pretty fast.
We already have a few peoplesigned up even though it's a few
months away.
So if you're interested indetailed AI training that can
(37:33):
really accelerate your learningon how to implement AI in a
business in an effective way, gocheck out the course.
And thank you everybody forjoining us.
Live and thank you all of youfor listening.
If you're listening to thisafter the fact of watching this
on YouTube, I appreciate all ofyou.
Have an awesome rest of yourday.
Hello, and welcome to another live
(00:02):
episode of the Leveraging AIPodcast, the podcast that shares
practical, ethical ways toleverage AI to improve
efficiency, grow your business,and advance your career.
This is Isar Metis, your host,and we have a fascinating
session for you today.
Why fascinating, because we'regoing to dive into advanced AI
agents and how to use themsafely and.
I'll explain first of all, whatthe hell all of that means, and
then we're gonna dive into apresentation.
(00:24):
Then we're gonna dive to theactual tools and the process
itself.
But on a high level, a new typeof agents emerged, a few months
ago, Manus, earlier this year,and then Gens spark shortly
after.
Manus is a Chinese company.
Gen Smar is an American company,I think from California.
They do similar things.
They're kinda like a generalizedagents that can do more or less
anything, that you, that yourbrowser can do.
So it get access to everythingyou have access to in the
(00:46):
browser, including tools,including browsers and websites,
including writing code,including creating web
applications and so on.
and you can do a huge variety ofthings with it.
And I was very curious on.
How to use it and how, I canplay with it and how far can I
push the envelope.
But I was really scared becauseI run everything in Chrome.
Chrome is my entire universe,and if something gets corrupted
(01:06):
in Chrome, I'm screwed.
Like literally everything thatI'm running, runs in Chrome.
and in addition, Chrome savesall my passwords to everything
on the planet.
And so if it gets access tothat, I don't know what it.
Might get access to that I'm notinterested in, or if it changes
any of the passwords forwhatever reason, then I'm
screwed.
Stuck outside of tools that Iwant to use and so on and so
forth.
So I had this issue with givingit access to my computer or
(01:27):
giving it access to I.
my passwords or everything in mychrome or my Google account and
all these things, and yet Ireally wanted to test these
tools and that led me throughthis quest that I'm going to
share with you today in detail.
Now at the end of the episode,after I show you the process on
how to put these tools in a boxthat where they're confined, but
you can still do everything youwant.
I will show you a few examplesof what you can do with these
incredible tools just to inspireyou to try.
(01:49):
Yourself.
So let's get started.
I will start by sharing myscreen.
Those of you who are joining uslive, first of all, thank you so
much for joining us live.
those of you.
who are not joining us live.
you should join us live.
We do this every Thursday atnoon Eastern time.
you can join us on LinkedIn, youcan join us on Zoom, and then
you can ask questions and be inthe chat and so on.
But those of you who are here inthe chat, feel free to introduce
(02:10):
yourself.
Say where you're from, why areyou interested in agents and
what your current experience.
So I know, what we're dealingwith and, And that's it.
And we're gonna get started.
I'll say one more thing.
this is gonna be a more advancedsession.
We're gonna talk about a lot ofadvanced stuff, but a hundred
percent of the things that I'mgonna share with you today, I
did for the first time ever whenI did this, which was, I dunno,
two, three months ago when I didthis process.
(02:31):
So everything that I'm sharingwith you may sound sophisticated
and advanced and complicated,but I knew zero.
It when I got started and withinan hour later I was able to run
these agents without anyexternal guidance.
So hopefully, with my guidance,you'll be able to do it in less
than an hour and have access tothis amazing new tool and
capability.
in addition, we teach basiccourses.
(02:51):
We teach courses that we've beenteaching for the last.
Over two years.
So the first course was in Aprilof 2023.
We teach at least once course amonth.
Right now I'm actually teachingtwo in parallel.
Most of these courses areprivate organizations and group.
Invite me to teach their people,their organizations consortia,
different membershiporganizations and so on.
So if you're in suchorganization, feel free to reach
(03:12):
out to me on LinkedIn orsomewhere and I'll gladly share
the details with you.
But we do public courses thatanybody can join once a quarter
when we have the bandwidth to dothat.
As I mentioned, we're justfinishing, one course that
started a few weeks ago, andthen the next public course is
going to start on august.
So if you wanna know how to jointhe August course, and you
should, if you haven't taken anyformal AI education yet, it's
(03:32):
literally going to change yourlife.
It's gonna change your career,and if you're in senior
position, it could change yourbusiness.
So go check up the link.
we'll drop the link in the chatright now and we'll drop, the
link in the show notes if you'relistening to this, afterwards.
But with that, let me share myscreen and let's dive into the
topic for which we are, heretoday.
(04:30):
So we'll start with a generalconcept of what the hell are
agents and how they're differentthan a chat.
'cause we.
People who are listening to thispodcast, I assume most of you
are already using multiple chattools, whether it's Gemini Claw,
Chachi, pt, deep Seek, etcetera, you choose your poison,
or maybe you're more advanced,you're using all of them, or
some of them depending on thespecific use cases.
and you're asking yourself whatthe hell are agents and how
(04:52):
they're different.
And there's several differentways in which agents are
different than chats.
The main thing is autonomyagents have levels of autonomy.
Some of them are fullyautonomous, some of them have
levels of autonomy.
But if you think about a chatonly does what you tell it to
do.
You have to explain to it.
Go and check the information onthis website, summarize the
information.
Put it in the table in this andthat format.
(05:12):
Create a code to do this orthat.
You tell it what to do and itfollows your lead in your
instructions.
An agent has, as I mentioned,different levels of autonomy,
but.
It has autonomy, meaning yougive it a goal or a broader
tasks, a task, and it will giveitself sub-tasks and steps and
tools that will allow it tocomplete the task or the goal
(05:32):
that you've set for it.
And that process that is gonnago through is gonna be its own
process.
The more advanced agents alsoevaluate their own process, so
they stop on the way they seewhat they've done.
If they need to correct things,then they will correct them.
and This is the first thing.
The second thing is access totools.
So this is something where theline started blurring recently
where different.
Chat platforms like Chachi, PTand Claude are having more and
(05:54):
more connectors to externalplatforms, but it's still
relatively limited.
While agents usually have accessto any tools you're gonna give
them access to.
And if it's a browser basedagent, like the one we're gonna
look at today, it has access to,everything in the browser,
meaning can go, it can go towebsites, it can write code, it
can execute, things and so on.
And so they have access to toolsthat usually.
Chats will not have access to.
(06:15):
They can work in multi-tierapproach, meaning when you go to
an agent environment, you canhave an orchestrator agent that
will talk to other lower tieragents that by themselves can
have access to even lower tieragents and really work like a
team or chat.
It's usually just the chat.
And so these are the maindifferences between what are
agents and what are justtraditional ai, large language
models.
(06:35):
The next thing is.
What are Manus and Gens spark,and what kind of agents are they
and what they can do?
So Manus.
When it came out again out ofChina, kinda like blew
everybody's minds.
It was kinda like a second deepseek moment where suddenly a
tool out of China comes out ofnowhere that nobody heard about
and enables people to do magicalthings.
And what it allows you to do iscombine multiple things that
(06:56):
existed before.
Into one environment that isthinking and operating on its
own to try to help you completethe goals.
And since it came out, theyadded many more functionality.
As an example, right now, it hasthe ability to create complete
PowerPoint presentations.
I.
which means you tell it.
What is the presentation about?
You tell it where to researchand what to research, and you
will create an entirepresentation for you.
They now added in this past weekthe ability to generate videos
(07:19):
so you don't, again, differentthan video generation tools
where you have to create everysingle.
Component in every single sceneon your own and then stitch them
together.
It knows how to do all of that.
You tell it what the movie needsto be about, you define the
overall storyline, and it cancreate every single scene and
stitch it together and create alonger video, combined of all
these scenes all on its ownwhile defining all the different
components and all the differentsteps.
(07:40):
So the.
Power here is incredible becauseyou basically tell it what you
want to achieve.
And again, I'll show youexamples at the end, and then
they will go and achieve it.
They will figure out what shouldbe the process, what tools they
should have, that should use,and what are the different steps
that they should take, and thenthey go and execute.
And I've seen it happen in fiveminutes, and I've seen it happen
in 45 minutes, and it just takesas long as it takes for it to do
(08:01):
the thing on its own.
And it's the future thateverybody's.
Most likely not ready for moreor less available for you here
now it's not fully available.
It still has limitations.
It doesn't always work, but it'sa very.
Obvious view, like a window intothe future that we're walking
into, and hence why it's a verypowerful environment to
experiment with, to see whatthese tools can and cannot do,
(08:22):
and how to prompt them betterand how to work with them in
order to achieve things that youmight be able to achieve with
the chat or with severaldifferent chats.
But it will take you a lot oftime because you will have to do
all the steps when here you justtell it what you want it to do
and it will go.
Do it.
And so this is what these toolsare.
As I mentioned, my biggest thingwas security risk.
Like I did not know how I canactually get into a scenario
(08:45):
where I can run these toolssafely.
And so with that, let's talkabout what was the solution and
what was the outcome that I gotto, and you'll gimme just one
second.
Oops.
Okay.
so first of all, let's talkabout, before we dive into the
(09:06):
solution, let's talk about whatthe risks are.
And there's a variety of risks.
The first risk is just security.
Like I said, they potentially,because they have access to
everything in the browser, andif you're logged into many
things in the browser, that alsohas access to different
components that you have.
it may have access to differenttools and things that you don't
necessarily want it to haveaccess to, meaning it may have
(09:26):
access to your bank account andthings like that.
It may have.
Behavioral risks, meaning it maybe able to do things that you're
not expecting it to do as far asthe process that it's going to
follow, and then harm thingsthat are your regular processes,
things that you're doing inregular platforms that you're
using and so on.
It may also have integrationrisks.
Think about it.
(09:46):
It is your.
Chrome browser is integratedinto multiple aspects of things
that you're doing.
And through that it can get thesame kind of access to other
platforms.
It may ruin the integrationsthat you have, because it's
gonna make changes to differentsettings and different so on.
And, when you think about it,it's, and that's my real life
analogy, is it is a intern.
(10:08):
That doesn't know necessarilywhat are the risks of your
business or your personal lifeand what information is, is
specifically.
Classified or somehow sensitive,and you're giving it access to
all of that.
So think about bringing a newintern into your company and
giving it access to everything,every piece of software, every
piece of access, every passwordthat you have and saying, Hey,
(10:29):
go and do this thing.
And you don't really necessarilyknow how it's going to evolve
and how it's going to happen.
And so there's a huge wide rangeof risks and you need to know
how to.
Put it in a box and still beable to use it.
So there are multiple solutionsthat I found, and the way I
found these solutions, and we'regonna dive into this, is by
having a conversation withChachi PT about the whole
situation.
What I'm trying to do, and I'mgonna share this with you in a
(10:51):
minute, but I'm gonna first ofall share with you what was the.
What was the final solution,that I've used in order to do
this?
And the final solution, whichagain, we're gonna go through
step by step, and I will showyou and explain to you exactly
how you can do it on your own.
is basically following thisprocess, I created a Google
Cloud.
Environment, which again, ifthose of you who've never done
(11:12):
this and don't know what I'mtalking about, and it sounds too
techy and complicated, I did notknow anything about this when I
got started, right?
So it, it was the first time forme setting a Google Cloud,
environment as well.
The second component is avirtual machine.
What is a virtual machine?
It's basically a.
A computer within that cloudenvironment, so that computer
can be just exactly like yourcomputer, meaning you can
(11:35):
install things on it, you canrun things on it, you can open a
browser in it, and so on, butit's just not really your
computer.
The third component is a newGoogle user.
I did not wanted it using myGoogle account because as I
mentioned, it has access to toomany things, and so I created a
new Google user.
So that costs you nothing.
I created a free Google user,and that's the one I'm using to
access everything in that newenvironment.
(11:57):
I installed a chromium browser.
You can install Chrome as well.
Chromium is just an open sourceversion and it can run as
effectively.
It just takes less memory andhence you need a smaller.
Virtual machine, which thencosts you less money.
I also had issues withinstalling Chrome in the
beginning, and that's whyChromium was a good option.
And then the last component is aremote desktop.
What is a remote desktop?
A remote desktop is basically asolution.
(12:19):
That is very easy to set up.
And again, we're gonna gothrough that.
That allows you, from yourcomputer, from my perspective,
from my computer, to access thatcloud computer that lives
somewhere in a Google server,right?
So the combination of all ofthis gives me access to a
computer that is not my computerwith a Chrome browser.
That is not my Chrome browserwith a Google account that is
(12:39):
not my Google account.
And in there I can safely runwhatever I want because if it
craps out, nothing happens.
I can kill that instance of thevirtual machine.
I can install a new one andstart all over again, and
nothing serious can happen outof that.
Another way to do this, by theway, if you have an older
computer that you're not using,that's a very simple way to do
this, then you don't need any ofthat.
The disadvantage is you need twocomputers, right?
(13:01):
You need your own computer torun your thing, and when you
wanna run experiments, you needto switch to the other computer
and then run whatever you wanton that other computer with a
new Google account and a newchrome, browser, and you can do
the same exact thing.
that would've been my choice ifI wasn't successful actually
running it all from my computer,which obviously is a lot easier
because I can run everything onmy machine when I travel, I have
it with me, and so on and soforth.
So there's a lot of benefits indoing it this way.
(13:24):
So with that in mind, let's lookon how I actually did this, and
I see that there's a fewquestions.
is it using temporary mailaddress also to save, the same
way?
Yeah.
So it's basically a full Googleaccount that I'm using to do
this thing.
So it's, It's a full Googleaccount, just a free account.
What you're looking at right nowon the two sides, one is the
Google Cloud environment, andthe other is the conversation
(13:44):
that I had with, Chachi pt.
So I will start with the firstprompt and then we'll go through
that and I'll explain what I didand I'll show you how I followed
it.
Its instructions without knowinganything, a lot of it I still
don't understand and it worksand it's very helpful for me.
So the prompt was, I'm lookingfor a safe way.
To run Manus and other AI agentson my Mac, it needs to be a
separate universe than all myregular applications and
(14:04):
everything I use.
The best options would be to runit on a remote server.
The second best would be aparallel machine on the Mac.
I'm open to any othersuggestions and would like to
know what are the pros and consof each options.
How much would it cost, ifanything, and what are the
technical skills required to setit up?
Pretty generic.
And that helps me go through theprocess.
And it then, asked me a bunch ofquestions.
(14:26):
are you looking for man or otherAI agents?
Do you have a preference of thecloud provider, whether AWS,
Google, or Azure, and so on andso forth.
I provided answer to thequestions and then it gave me a
long and detailed answer and itbasically said, okay, safe
isolation options, running AIagents, remote versus local.
And then it said remotedeployment options, cloud
options.
One of them is GCP virtualmachines, so that's what I ended
(14:47):
up going up with.
Google Cloud platform, virtualmachine.
the pros.
Strong isolation, fine.
Grain control, free tieravailability and scalability.
So it's not really free, but youget 300 credits,$300 credits
from, Google when you set up anew virtual machine.
this thing is costing me between15 to$20 a month to run.
if I'm gonna go crazy, it'sgonna cost me like$25 a month.
So I get about, a year and ahalf to two full years of
(15:10):
running this.
Basically for free, and then Ican always set up a new account
and run it again.
but either way, it's a great wayto run this.
Disadvantages set up complexity,so you need to know what you're
doing, ongoing management.
You're responsible for thevirtual machine and operating
system.
I've been using it for three orfour months and I haven't done
any maintenance.
So there is no real ongoingthing and cost for larger
instances.
If you're going for biggervirtual machines and doing
(15:31):
bigger, more complex stuff, thenit's gonna cost you more money.
but this is not the case for meright now.
Then it gave me the option forAmazon Web Services and how to
do it over there, and then itgave me options on railway.
So I told it about railway inone of the options.
Railway is a.
Hosting platform that I use torun my N eight n platform, and
it has container solutions.
(15:52):
Those of you, again, who don'tknow containers, think about it
as a software package that haseverything the software needs
packaged for idiots like me torun.
So you don't need to know how toinstall and connect and APIs and
all of that.
There's a container, you drop itin, it installs everything
within the container, and you'reup and running without knowing
anything that you need to do.
So those of you who areinterested in running NA 10
without.
Basically on your own instance,you can use railway, but in the
(16:13):
same way, you can do this,right?
You can install a railwaycontainer that has chrome and so
on.
the disadvantages were resourcelimits in sleep, which is
something that would happen.
The hobby plan is$5 a month, andyou may need a bigger plan,
which would be$10 a month, whichwould be more expensive than the
free version that I'm basicallyhaving in Google.
And so on and so forth.
Mac Stadium, which is a remoteMac hardware rental, basically
(16:34):
allows you to run a virtual Mac,through your Mac on a browser.
And then local isolation optionson my Mac.
So you can run a virtualmachine, kinda like a parallel
or VMware on your device.
Those of you who are using Maxand using, parallel to run.
Microsoft Office as an examplein Windows, know what I'm
talking about.
So you can run like a parallelmachine on your computer.
but then again, there's pros andcons for that.
(16:56):
So after going through all ofthis, and it gave me a lot of,
and those of you who are notwatching the screen, just
listening to this is like a 10page long summary with clear
details on each one with a tablein the end that summarizes
exactly all the pros and cons.
And the first option was.
The Google Cloud as the mostfavored options.
So that's what I went with.
And literally the prompt that Iwrote is, what is the
step-by-step process of settingthe GCP solution?
(17:18):
And then he told me, step bystep for Google Cloud, create a
Google Cloud project.
I.
I went to Google and went toGoogle Cloud and it says, go to
the Google Cloud console andgave me a link to go there and
you click on your project.
So now on the other screen, onthe Google Cloud, on top,
there's a little square that hasthe projects and you can click
on your project, which I alreadycreated for this demo, and I
called it Chrome vm.
It has nothing in it yet.
(17:38):
You can see it's an emptyproject.
It's just a shell.
It's a name for me to createmore stuff.
And then it says Create aproject id, which I created.
Then set up billing.
So that's in here on the left.
If you click, there's a menu andyou have all the different
things.
And when I say on the left, it'sthe leftmost menu in Google
Cloud, and it has all thedifferent components that Chachi
PT told us to go to.
So you go to billing and you setup a way for it to charge you.
But as I mentioned, you're gonnaget$300 worth of free.
(18:00):
Credits, which is gonna be goodfor probably almost two years.
then it tells you need to enabledifferent APIs and you enable
these APIs for this project.
So how do you do that?
So it tells me what to do, saidin the cloud console, navigate
to APIs and services library.
So you can see here on the left,there's in the menu, one of the
says, says API services.
And you can see underneath thatwhere it says library in the sub
menu.
And you click on that and ittakes you to where it has.
(18:22):
All the different APIs thatGoogle Cloud allows you to run
on one of your projects.
Now again, those of you who getdiarrhea just from hearing the
acronym API, because you don'tknow what it means and it sounds
really techy, it doesn't matterbecause you don't need to know
anything.
So what you can see, it tells meto install or to make sure I
have Compute engine, API Cloudstorage, API Cloud, logging API,
and cloud monitoring API.
So like a good monkey, I'm justgonna copy the first one.
(18:45):
Compute engine API into thesearch over here.
And paste it in the search.
He'd search and it comes up andI'm gonna click on that and I'm
gonna enable that, to thisthing.
So literally I'm just copyingand pasting and click clicking,
manage and apply, and I'msetting up all the APIs that I
need.
I can show you a slightlyshorter way to do this.
So without navigating toanything, if you're just on the
(19:05):
home screen of the, of theproject, you just set on the
very top, there's a search.
It's like a general search foreverything.
Google Cloud.
So if you search here forcomputer engine API, which again
I copied from the instructionsfrom Chachi pt, you can see it
finds different things.
One of them is the APIcomponent, and you will take him
to the same exact place.
(19:25):
So even if you don't know how tonavigate and where to navigate,
you can just copy and paste tothe top search and activate
those things.
Then it's telling me toconfigure identity and access
management.
The short for this is IAM.
And again, it tells me exactlywhat to do.
Go to IAM admin.
So I'm again, good monkey, gohere, go to IAM and admin, and
then click on that.
And then just add users.
So it tells me how to do that.
(19:46):
create an instance, add theusers and tell me what to do and
what permissions to give.
And I just follow theinstruction step by step.
The next step tells me to set upthe virtual machine.
Same thing, go to ComputeEngine.
So I go back to the menu, I goto compute engine.
And I go to a virtual machine,which is VM instances, and
that's exactly what theinstruction says.
So I click on that and you cansee right now I have no
(20:08):
instances there.
What this will basically allowme to do is to create a computer
in this Google Cloud environmentthat we just set in.
Two minutes.
So I click on Create Instance,and then again it walks me
through exactly what to do.
There's all these really complexand scary options on the screen.
Those of, you're not seeing,there's like multiple things and
buttons to press and drop downmenus, but you be a good monkey.
give it a name.
And so the name is gonna bewhatever.
(20:30):
and then, choose a region.
So you can see here it saysregion and I can go and select
where I am.
So I'm in the southeast us.
So I'm gonna create a US East.
I'm gonna pick the server that'sclosest to me, which in this
case is in South Carolinabecause I'm in Florida.
and that's it.
Then the next thing it says, themachine configuration choose E
two, which is the default, whichis the low cost day to day,
thing.
So that's the cheapest versionthat I can run.
(20:50):
And then it says, what boot discdo I need to run?
So it tells me what operatingsystem.
So in the next side, left menu,it says operating system and
storage.
And here I actually started withthis initial recommendation of
running a Linux distribution.
And then after a longconversation with it where
things didn't work for me, Iasked it to start from the
beginning.
And we actually, ended up usinga different operating system,
(21:10):
which is called Ubuntu.
and again, I don't even knowwhat that means.
I don't know what thedifferences are.
I just know that it worked afterI had all this long conversation
that didn't work.
Let me scroll down to those, tothat section.
Here we go.
So these are the updated ones,and then it told me to install a
different operating system.
How do you create a differentoperating system?
(21:30):
You go here in the OS segmentand you click on change.
I.
And then you pick what operatingsystem you want.
So instead of Damian, I'm gonnachoose Ubuntu.
and that's it.
And now you can choose whicheverversion, which doesn't really
matter.
You just keep on updating theversions all the time.
And I, and then the next step,and I click select, and now I
have a new operating system.
How cool is that?
knowing absolutely nothing.
I can create a machine in thecloud that I can run.
(21:51):
And then there's the other,steps of creating data
protection and networking.
So I have to allow it.
HTTP traffic and https traffic.
Again, I'm just following theinstructions that it's giving me
and that's it.
And you hit create and it'sgonna create.
A new computer for you in thecloud.
Now that computer still doesn'thave anything in it, so later on
it will take me through thesteps of installing two things.
(22:14):
One, it will show me how toinstall.
And again, the instructions areright here and the code I need
to run is right here.
So it said in the SSH terminal.
Again, don't be scared.
Just find SSH.
And once this thing will stoprunning, you'll see here there's
an SSH button.
So I don't know what it means.
I don't know what it does, but Iclick on it and then it will run
its thing and ask me to confirmdifferent steps.
And once all the steps areconfirmed, and you can see
(22:35):
authorized SSH, and I can, Iwill tell it which Google
account to use and then I will.
Establish a few things and I geta terminal window.
Terminal window.
Looks like all dos, right?
It's just like the ugliest thingin the world, but you don't need
to know anything.
I've got the code.
All I have to do is copy thecode.
From here, there's even a copybutton and I click copy and I
paste the code in here and Ilater it run and it will do its
thing.
That's it.
It's that simple.
(22:56):
So I go through all these steps.
The first step will install, theupdates that I need.
The second step will install thedesktop environment, and the
third step will install GoogleChrome and then remote desktop.
So I literally, I'm gonna stophere by showing you all the
different steps, because thenext steps are exactly like this
is copying the code from theinstructions in Chachi pt.
And I'm gonna share with you alink in the show notes to these
instructions.
(23:17):
So any one of you can literallycopy.
Everything that I've done, stepby step and use it as your own.
And you can see it's running alot of code now in the terminal,
which I don't have a clue whatit's doing, but it's not on my
computer, so I don't reallycare.
It's running in this virtualmachine in the cloud.
And so what it ends up being,after I'm installing all these
different things, I'm gonnainstall remote desktop on micro
chrome browser, the one on mycomputer.
(23:38):
And you can see here that's instep six, configure Chrome
browser, remote desktop.
So it tells me exactly how toset it up.
very simple.
And once I'm done, what I'mgetting is I'm getting this and
I'm gonna make this full screen.
So what I'm getting now is youcan see I have a browser within
the browser.
In my regular browser here ontop, you can see I have the chat
(23:59):
that we had before and I havethis AI agent sandbox instance,
and it's a remote desktop intothis remote machine.
In here, I have my new Googleaccount with emails that I can
send back and forth from my realuniverse or my real computer I
can send emails to here withdifferent things that I need and
tools that I need and promptsthat I created and so on.
Because remember, this is not mycomputer.
(24:21):
This is another computer.
And then I have Spar, and I haveManus and I have a lot of other
things running.
So this is basically how thisthing runs.
I now have.
A new machine that you literallycan follow the same exact steps
that I'm gonna share with you tohave a separate machine that is
not my machine logged in with adifferent Google user that I've
created, and now I can dowhatever I want without risking
(24:42):
anything that I have while stillrunning on my own computer.
So let's, I promised you a fewexamples, and I'm gonna show you
two separate examples.
one of them, I'm gonna show youthe comparison between the two
different tools.
I used the same exact prompt onboth tools.
By the way, the prompt wascreated by Claude.
So I explained to Claude whatI'm trying to do, and I asked
Kate to create the prompt, andthen I copied the prompt here.
Now again, you cannot copy andpaste from your computer to this
(25:03):
because it's not the samecomputer.
So what I do is I.
Email this from my regular emailaccount to this new Gmail
account, and then it shows up inthe email tab that I have here
in the new machine.
I copy it from this.
Gmail in my virtual machine intospar or so on.
So in this particular case, mykids go to the local Scouts
(25:25):
chapter and we are now finishingthe year and planning for next
year.
And both my wife and I arevolunteering there since the
kids started going there aboutnine years ago.
And We are every year we arelooking for ways to raise money,
so we have the funds to run thescouts in the most efficient
way.
And one of the things that I'mdoing is I'm looking for grants.
And previously, in previousyears I did it manually.
I would go through dozens ofwebsites, looking for different
grants and where they're fromand other applicable and so on.
(25:47):
I said, Hey, wait a minute.
I have these agents, maybe theycan help me look for grants.
So I explain what I'm trying todo to Claude.
And Claude wrote this prompt,objective, automate the i, the
identification and initialvetting of grant opportunities
for a nonprofit in Maitland,Florida.
background local scouts, noprofit, blah, blah, blah.
Serving one, first through 12grades, youth run troops with
parent volunteers, activities.
(26:08):
What all the stuff basicallythat I told it is in there.
And then the scope.
Search scan.
Federal websites, county localsources, plus private sectors,
prioritize opportunities, blah,blah, blah, blah, blah.
There's a whole explanation ofwhat I would've done manually.
And then you hit go and youleave for 20, 30 minutes and it
does its thing.
So what do I mean by does itsthing you can see?
The first respond is I'll helpyou identify and vet grant
opportunities for your scoutnonprofit in Maitland, Florida.
(26:30):
Let me break this down intosteps and search the relevant
grants based on therequirements.
By the way, the last thing thatI ask for you to do is to create
a user interface for me to trackthe different grant
opportunities, what's the statuswith each and every one of them,
and to basically see all theinformation, which those of you
who are watching the screen cansee it on the right, but what
you can see is that it's.
It's now gonna use differenttools.
The first tool, it's usingsearch.
It says Grants for youth inOrange County, Florida, or
(26:51):
Scouts.
And if I click on view.
I can see all the websites thathe was searching, I don't know,
about 15, 20 websites.
And then it started loosesearching more and more things
each and every step.
It's learning more stuff andit's updating the plan on how
it's gonna execute on that.
So it's gonna do.
Deeper and deeper dives intodifferent things.
So if I dive into this one, youcan already see the grant
description, applicationsubmission information, so it's
(27:13):
diving deeper into each of thethings that it found previously,
and it goes on and on.
And it's creating tables andit's then summarizing the tables
and it's writing more stuff andit's doing additional research.
So you can see it's doing allthese things and finding
different stuff.
And in the end.
I ask it, like I said, to createa tool for me to track all the
information.
So if I keep on scrolling downthrough this very long process
and in the middle, I jumped inand gave it additional comments
(27:33):
when it was done with, differentsteps.
And at the end it created thisfor me, which is a website that,
again, those of you're notwatching, I apologize, but
you're missing out.
But it has a.
Color coded.
Website that has all thedifferent opportunities in a
(27:55):
table where I can search andfilter by anything that I want.
So I can filter by, either is ita federal, state, county, city,
private, Jewish community orinternational fund.
I can look by, statuses.
So I have a status dropped onmenu that I can update on my
own.
I can see the amounts.
I can see the deadlines.
I have a link straight to theopportunities that I can go
straight into there.
But the cool thing is, in thisprocess, what I asked you to do,
(28:18):
I said, I want you to help mealso write the request for
grants.
I want you to actually write theproposals.
And what I did in order to dothis, I created a whole task
section.
When I say I, I didn't doanything.
I ask it to create a tasksection, and this task section
allows me to give the.
AI agent additional tasks.
So you can see, I can choose aspecific grant.
It picks it automaticallybecause I'm in that grant.
(28:38):
And then I can select the type,research, Eligibility and
requirements, write submissiondocuments.
I can go to write submissiondocuments.
I can then write it a detailedprompt.
I can give it a priority, I cangive it a due date.
I can assign the task and thenit's going to execute on that.
It's gonna read everything inthat website and it's gonna
write a draft for me, and it'sgonna put it in the documents of
this particular opportunity.
This is pure gold.
(28:59):
I invested.
10 minutes.
It invested 45 minutes, and Inow have a extremely effective
way to go after grants acrossfederal, local, county, city,
private, and so on that arerelevant to what I need to do
with a website in which I cantrack the status of each and
every one of the activities andfilter and see progress and so
(29:20):
on.
This is nothing short of magic.
This process would've taken ateam of several people, several
different days to create, andyou need a web developer and you
need a researcher, and you needan analyst, and you need all
these things, or you yourselfspending hours to do this.
I did, like I said, the sameexact thing I.
On Manus.
Manus came out with something alittle different, by the way, on
(29:40):
both of them, both on Manus andon, spar.
You can publish this thing, sowhen you see this really cool
website up here, there's apublish button that I can, click
and then I can open it as abrowser window that then I can
share with people.
Then they can run it in a realenvironment, not in a virtual
environment, because this isjust a website that it created.
So this website is publicly actavailable.
I can send it to people and Ican collaborate on this process
(30:02):
with additional people because Ican very easily share that
website.
That is a tool to track ourprocess.
I did the same thing in Manus.
So let's look at the Manusexample.
you can see Manus took aslightly different approach.
Again, I didn't tell it exactlywhat to do.
I said I want an applicationthat will allow me to filter and
see, the different applic, thedifferent opportunities.
So it took a slightly differentapproach, but very similar in
concept, each and every one ofthem in a different box.
(30:24):
What's really cool here, goingback to the autonomy part of
this, and it's takinginitiative, it gave a score to
each and every one of theopportunities based on how.
Applicable it is, what's thedeadline and what are the funds
that are available?
And you can see scores in thesixties, in the fifties, in the
thirties, and then some of themare zero because it found them,
but it doesn't think it'sapplicable to us.
And so it actually helps meprioritize what's to go after
(30:47):
first, which is really awesome.
And again, it has a filteringcapabilities and, search
capabilities.
Just like we've seen on gensspark.
I like the gens spark, userinterface better, but from a
practicality perspective,they're both highly practical
for my needs.
The last thing that I wanna showyou is something that is more
business oriented, because mostof you are in businesses and not
in, Not in nonprofit, but youcan, you hopefully get the point
(31:09):
even from the nonprofit thing.
What I've done here is actuallysomething that one of my clients
has done initially and I justuse and follow their same
concept, is they are in thesmart home automation world and
they wanted to find.
Ways to look for additionalpartnerships in that world.
So if you're in the smart homeautomation universe, you cannot
do projects on your own.
You need an architect that willwork with you to implement all
(31:31):
the stuff that you're planning.
You need a builder.
A GC that will actually do thework.
You need an interior designer,so you need all these different
things.
And if you find more of them inthe area in which you work, you
have more chances of gettingwork.
And the way we've done this iswe've actually giving it names
and websites of existingpartners, one of each, one
architect, one interiordesigner, and one GC in order to
(31:54):
start.
And we basically told it toplay.
Six degrees of Kevin Bacon.
Basically go and look for peoplethese companies have done
projects with, and then look forpeople they've done projects
with, and then go and look forpeople they have done projects
with.
And then give me a userinterface in which I can see
each and every one of thesecompanies, what projects they've
done.
Where are they in the world, andwhat's their website?
It did all of that and itcreated a user interface, which
(32:16):
again, now I have a search whereI can search for specific, and
you can see here it saysarchitects and I have a list of
architects, and then I haveinterior designers, and I have a
list of interior designers, andI have builders and construction
companies, and I have them, butI can filter the list very
easily.
Let's say this is all inSouthern California because this
is what it's searching for.
So let's look for Orange County.
So if I type orange, you can seeit filters it out.
It found no architects and nointerior designers, but it found
(32:38):
several different builders thathave done relevant projects that
I can go and look at the actualprojects.
I can click on the links and soon.
You can build any tool for anybusiness purpose that you want
with this.
Now again, it doesn't alwayswork the first time.
It doesn't always work, period,but it gives you.
Again, a window into the future,and it gives you the ability to
use some of these tools in thepresent, like both this and the
(32:58):
other thing that I showed you isthings that are in use.
They're actually providingimmediate value after investing
a few minutes in creating them.
So let me stop sharing.
And I'll open it to, questions.
There's a question, spar versusManus, and which one do I like
better?
I'm on the fence.
Like I, what happens is, in somecases I see better, success with
(33:19):
Spar and in some cases seebetter success with, Manus.
And so it's, it just depends.
And in, in general, I thinkManus does better research.
And Gen Spar creates better userinterfaces, but that's on, five
or six projects.
I don't think that's likenecessarily the case a hundred
percent of the time.
that's why I'm always tryingboth, like literally everything
that I have, I'm dropping intoboth of them and I'm letting
(33:41):
them run.
And if one of them has a better,start, then I will continue with
that one.
If they both have a decentstart.
I will continue with both untilI get to a situation where I
know what to do next.
Jonathan said it would make itmuch easier if you could build
an agent to set up the secureagent.
I think we'll get there.
I think we'll get there wherethe agents will be able to do
everything that I did.
I don't think we're there yet,but as I mentioned, it took me
(34:02):
about an hour to figure thisout, right?
I went back and forth and what Idemoed to you now in 20 minutes
of the setup.
Actually took me about an hourto set up because a lot of
things didn't work in thebeginning, but after an hour it
did work, and now I'm using itall the time and I'm using it
safely and so on.
So the, it's as much as itsounds complicated, it's worth
investing one hour of your timeto having a solution like this
that is completely, disconnectedwith a very serious Chinese wall
(34:24):
between that and your realuniverse.
And then you can do whatever youwant.
Okay, so quick recap andsummary.
The.
AI agent world is the presentand it's definitely the future.
There are many companies whoprovide agents that are very
specific to specific things,like you can build voice agents
to take phone calls or to dooutbound.
You can build agents to manageyour emails.
(34:45):
You can build agents to docustomer service.
You can build multiple types ofagents, but then you have this
new universe of general agentslike Spar and Manus, and with
those, they.
Can do more or less anything youwant because they can browse,
research, summarize, connect todifferent systems and tools,
write code, deploy websites, andso on.
And I think that right now it'smore geeky like it's people like
(35:06):
me and more advanced users thatare actually playing with these
tools to do these differentthings.
But two things I think willhappen.
One is I think these will becomemore and more.
Mainstream as time goes by.
But the other thing that I'mpretty certain of is that Cha
GPT has something like this, andthe only reason they didn't
share it yet, and they have.
Shared a version of this, right?
(35:26):
So they have their solution thatis currently available only to
the upper tier.
And it's the same, but notexactly, doesn't have the same
freedom and capabilities asManus and Spar.
But there's zero doubt in mymind that in-house they have it.
They're just thinking of how andwhen to release it.
A, so that the public knows howto use it.
B, that it's safe, and C, thatit doesn't completely destroy
the bandwidth of their serversthat are already running very
(35:49):
heavily doing everything thateverybody's doing.
But once they figure out a wayand the right timing to release
something like this, it's gameover, right?
Because right now there's 700million or 800 million chat PT
users.
If you give them this capabilityto basically say, Hey, I want
you to do this.
Go do this on your own, and itwill.
You will jump from, I don'tknow, tens of thousands of
people are doing it right now tohundreds of millions of people
(36:10):
doing what I just showed you.
And because it'll be ChachiPiti, I think people will feel a
lot more comfortable than I'mfeeling with Gens, spark, and
Manus.
And then.
Just everybody will start usingsolutions like that and creating
their own applications and doingtheir own research and summary
and so on.
And because Chachi PT isbuilding more and more
connectors, whether through MCPservers or just native
connectors to, Google andMicrosoft environments and,
(36:31):
other big solutions out therelike ERP systems and CRMs and so
on, these tools will be.
The ultimate power extender ofevery single person, right?
You'll be able to ask it to doany research across any data,
internal and external, eitherone or the other, or a
combination, and get results inwhatever format and report it to
any other third party systemthat you would want just by
asking in simple English.
(36:52):
And so the ability to do thingsthat today takes teams weeks.
Be able to set it up in minutesand then enjoy them from that
moment forward are.
Coming and they're coming veryfast.
So my suggestion, go experimentwith what I just showed you.
Follow the instructions step bystep as I did, and as I showed
you right now.
And learn what these tools aregood at, what they fail at, how
(37:12):
to prompt them better so when itdoes become available, or just
start enjoying it right now.
But if it becomes available inyour work environment, you are
more ready than everybody else.
Thank you so much.
Hopefully you found this,valuable.
And, as I mentioned, there's acourse coming up in August.
Go sign up for that.
The courses fill up pretty fast.
We already have a few peoplesigned up even though it's a few
months away.
So if you're interested indetailed AI training that can
(37:33):
really accelerate your learningon how to implement AI in a
business in an effective way, gocheck out the course.
And thank you everybody forjoining us.
Live and thank you all of youfor listening.
If you're listening to thisafter the fact of watching this
on YouTube, I appreciate all ofyou.
Have an awesome rest of yourday.
Popular Podcasts
Fudd Around And Find Out
UConn basketball star Azzi Fudd brings her championship swag to iHeart Women’s Sports with Fudd Around and Find Out, a weekly podcast that takes fans along for the ride as Azzi spends her final year of college trying to reclaim the National Championship and prepare to be a first round WNBA draft pick. Ever wonder what it’s like to be a world-class athlete in the public spotlight while still managing schoolwork, friendships and family time? It’s time to Fudd Around and Find Out!
Crime Junkie
Does hearing about a true crime case always leave you scouring the internet for the truth behind the story? Dive into your next mystery with Crime Junkie. Every Monday, join your host Ashley Flowers as she unravels all the details of infamous and underreported true crime cases with her best friend Brit Prawat. From cold cases to missing persons and heroes in our community who seek justice, Crime Junkie is your destination for theories and stories you won’t hear anywhere else. Whether you're a seasoned true crime enthusiast or new to the genre, you'll find yourself on the edge of your seat awaiting a new episode every Monday. If you can never get enough true crime... Congratulations, you’ve found your people. Follow to join a community of Crime Junkies! Crime Junkie is presented by audiochuck Media Company.
The Breakfast Club
The World's Most Dangerous Morning Show, The Breakfast Club, With DJ Envy, Jess Hilarious, And Charlamagne Tha God!