Leveraging AI

196 | How to Safely Run Powerful AI Agents (Like Manus & GenSpark) with no RISK

• Isar Meitis • Season 1 • Episode 196

Share episode

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

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!

GMT20250605-155522_Recording_avo_1280x720:

Hello, and welcome to another live episode of the Leveraging AI Podcast, the podcast that shares practical, ethical ways to leverage 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're going to dive into advanced AI agents and how to use them safely and. I'll explain first of all, what the hell all of that means, and then we're gonna dive into a presentation. Then we're gonna dive to the actual tools and the process itself. But on a high level, a new type of 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 generalized agents that can do more or less anything, that you, that your browser can do. So it get access to everything you have access to in the browser, including tools, including browsers and websites, including writing code, including creating web applications and so on. and you can do a huge variety of things with it. And I was very curious on. How to use it and how, I can play with it and how far can I push the envelope. But I was really scared because I run everything in Chrome. Chrome is my entire universe, and if something gets corrupted in Chrome, I'm screwed. Like literally everything that I'm running, runs in Chrome. and in addition, Chrome saves all my passwords to everything on the planet. And so if it gets access to that, I don't know what it. Might get access to that I'm not interested in, or if it changes any of the passwords for whatever reason, then I'm screwed. Stuck outside of tools that I want to use and so on and so forth. So I had this issue with giving it access to my computer or giving it access to I. my passwords or everything in my chrome or my Google account and all these things, and yet I really wanted to test these tools and that led me through this 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 box that where they're confined, but you can still do everything you want. I will show you a few examples of what you can do with these incredible tools just to inspire you to try. Yourself. So let's get started. I will start by sharing my screen. Those of you who are joining us live, 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 at noon Eastern time. you can join us on LinkedIn, you can join us on Zoom, and then you can ask questions and be in the chat and so on. But those of you who are here in the chat, feel free to introduce yourself. Say where you're from, why are you interested in agents and what your current experience. So I know, what we're dealing with and, And that's it. And we're gonna get started. I'll say one more thing. this is gonna be a more advanced session. We're gonna talk about a lot of advanced stuff, but a hundred percent of the things that I'm gonna share with you today, I did for the first time ever when I did this, which was, I dunno, two, three months ago when I did this process. So everything that I'm sharing with you may sound sophisticated and advanced and complicated, but I knew zero. It when I got started and within an hour later I was able to run these agents without any external guidance. So hopefully, with my guidance, you'll be able to do it in less than an hour and have access to this amazing new tool and capability. in addition, we teach basic courses. We teach courses that we've been teaching for the last. Over two years. So the first course was in April of 2023. We teach at least once course a month. Right now I'm actually teaching two in parallel. Most of these courses are private organizations and group. Invite me to teach their people, their organizations consortia, different membership organizations and so on. So if you're in such organization, feel free to reach out to me on LinkedIn or somewhere and I'll gladly share the details with you. But we do public courses that anybody can join once a quarter when we have the bandwidth to do that. As I mentioned, we're just finishing, one course that started a few weeks ago, and then the next public course is going to start on august. So if you wanna know how to join the August course, and you should, if you haven't taken any formal AI education yet, it's literally going to change your life. It's gonna change your career, and if you're in senior position, it could change your business. So go check up the link. we'll drop the link in the chat right now and we'll drop, the link in the show notes if you're listening to this, afterwards. But with that, let me share my screen and let's dive into the topic for which we are, here today. So we'll start with a general concept of what the hell are agents and how they're different than a chat.'cause we. People who are listening to this podcast, I assume most of you are already using multiple chat tools, whether it's Gemini Claw, Chachi, pt, deep Seek, et cetera, you choose your poison, or maybe you're more advanced, you're using all of them, or some of them depending on the specific use cases. and you're asking yourself what the hell are agents and how they're different. And there's several different ways in which agents are different than chats. The main thing is autonomy agents have levels of autonomy. Some of them are fully autonomous, some of them have levels of autonomy. But if you think about a chat only does what you tell it to do. You have to explain to it. Go and check the information on this website, summarize the information. Put it in the table in this and that format. Create a code to do this or that. You tell it what to do and it follows your lead in your instructions. An agent has, as I mentioned, different levels of autonomy, but. It has autonomy, meaning you give it a goal or a broader tasks, a task, and it will give itself sub-tasks and steps and tools that will allow it to complete the task or the goal that you've set for it. And that process that is gonna go through is gonna be its own process. The more advanced agents also evaluate their own process, so they stop on the way they see what 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 to tools. So this is something where the line started blurring recently where different. Chat platforms like Chachi, PT and Claude are having more and more connectors to external platforms, but it's still relatively limited. While agents usually have access to any tools you're gonna give them access to. And if it's a browser based agent, like the one we're gonna look at today, it has access to, everything in the browser, meaning can go, it can go to websites, it can write code, it can execute, things and so on. And so they have access to tools that usually. Chats will not have access to. They can work in multi-tier approach, meaning when you go to an agent environment, you can have an orchestrator agent that will talk to other lower tier agents that by themselves can have access to even lower tier agents and really work like a team or chat. It's usually just the chat. And so these are the main differences between what are agents and what are just traditional ai, large language models. 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 of China, kinda like blew everybody's minds. It was kinda like a second deep seek moment where suddenly a tool out of China comes out of nowhere that nobody heard about and enables people to do magical things. And what it allows you to do is combine multiple things that existed before. Into one environment that is thinking and operating on its own to try to help you complete the goals. And since it came out, they added many more functionality. As an example, right now, it has the ability to create complete PowerPoint presentations. I. which means you tell it. What is the presentation about? You tell it where to research and what to research, and you will create an entire presentation for you. They now added in this past week the ability to generate videos so you don't, again, different than video generation tools where you have to create every single. Component in every single scene on your own and then stitch them together. It knows how to do all of that. You tell it what the movie needs to be about, you define the overall storyline, and it can create every single scene and stitch it together and create a longer video, combined of all these scenes all on its own while defining all the different components and all the different steps. So the. Power here is incredible because you basically tell it what you want to achieve. And again, I'll show you examples at the end, and then they will go and achieve it. They will figure out what should be the process, what tools they should have, that should use, and what are the different steps that they should take, and then they go and execute. And I've seen it happen in five minutes, and I've seen it happen in 45 minutes, and it just takes as long as it takes for it to do the thing on its own. And it's the future that everybody's. Most likely not ready for more or less available for you here now it's not fully available. It still has limitations. It doesn't always work, but it's a very. Obvious view, like a window into the future that we're walking into, and hence why it's a very powerful environment to experiment with, to see what these tools can and cannot do, and how to prompt them better and how to work with them in order to achieve things that you might be able to achieve with the chat or with several different chats. But it will take you a lot of time because you will have to do all the steps when here you just tell it what you want it to do and it will go. Do it. And so this is what these tools are. As I mentioned, my biggest thing was security risk. Like I did not know how I can actually get into a scenario where I can run these tools safely. And so with that, let's talk about what was the solution and what was the outcome that I got to, and you'll gimme just one second. Oops. Okay. so first of all, let's talk about, before we dive into the solution, let's talk about what the 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, and if you're logged into many things in the browser, that also has access to different components that you have. it may have access to different tools and things that you don't necessarily want it to have access to, meaning it may have access to your bank account and things like that. It may have. Behavioral risks, meaning it may be able to do things that you're not expecting it to do as far as the process that it's going to follow, and then harm things that are your regular processes, things that you're doing in regular platforms that you're using and so on. It may also have integration risks. Think about it. It is your. Chrome browser is integrated into multiple aspects of things that you're doing. And through that it can get the same kind of access to other platforms. It may ruin the integrations that you have, because it's gonna make changes to different settings and different so on. And, when you think about it, it's, and that's my real life analogy, is it is a intern. That doesn't know necessarily what are the risks of your business or your personal life and what information is, is specifically. Classified or somehow sensitive, and you're giving it access to all of that. So think about bringing a new intern into your company and giving it access to everything, every piece of software, every piece of access, every password that you have and saying, Hey, go and do this thing. And you don't really necessarily know how it's going to evolve and how it's going to happen. And so there's a huge wide range of risks and you need to know how to. Put it in a box and still be able to use it. So there are multiple solutions that I found, and the way I found these solutions, and we're gonna dive into this, is by having a conversation with Chachi PT about the whole situation. What I'm trying to do, and I'm gonna share this with you in a minute, but I'm gonna first of all share with you what was the. What was the final solution, that I've used in order to do this? And the final solution, which again, we're gonna go through step by step, and I will show you and explain to you exactly how you can do it on your own. is basically following this process, I created a Google Cloud. Environment, which again, if those of you who've never done this and don't know what I'm talking about, and it sounds too techy and complicated, I did not know anything about this when I got started, right? So it, it was the first time for me setting a Google Cloud, environment as well. The second component is a virtual machine. What is a virtual machine? It's basically a. A computer within that cloud environment, so that computer can be just exactly like your computer, meaning you can install things on it, you can run things on it, you can open a browser in it, and so on, but it's just not really your computer. The third component is a new Google user. I did not wanted it using my Google account because as I mentioned, it has access to too many 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 new environment. I installed a chromium browser. You can install Chrome as well. Chromium is just an open source version and it can run as effectively. It just takes less memory and hence you need a smaller. Virtual machine, which then costs you less money. I also had issues with installing Chrome in the beginning, and that's why Chromium was a good option. And then the last component is a remote desktop. What is a remote desktop? A remote desktop is basically a solution. That is very easy to set up. And again, we're gonna go through that. That allows you, from your computer, from my perspective, from my computer, to access that cloud computer that lives somewhere in a Google server, right? So the combination of all of this gives me access to a computer that is not my computer with a Chrome browser. That is not my Chrome browser with a Google account that is not my Google account. And in there I can safely run whatever I want because if it craps out, nothing happens. I can kill that instance of the virtual machine. I can install a new one and start all over again, and nothing serious can happen out of that. Another way to do this, by the way, 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 of that. The disadvantage is you need two computers, right? You need your own computer to run your thing, and when you wanna run experiments, you need to switch to the other computer and then run whatever you want on that other computer with a new Google account and a new chrome, browser, and you can do the same exact thing. that would've been my choice if I wasn't successful actually running it all from my computer, which obviously is a lot easier because I can run everything on my machine when I travel, I have it with me, and so on and so forth. So there's a lot of benefits in doing it this way. So with that in mind, let's look on how I actually did this, and I see that there's a few questions. is it using temporary mail address also to save, the same way? Yeah. So it's basically a full Google account that I'm using to do this thing. So it's, It's a full Google account, just a free account. What you're looking at right now on the two sides, one is the Google Cloud environment, and the other is the conversation that I had with, Chachi pt. So I will start with the first prompt and then we'll go through that and I'll explain what I did and I'll show you how I followed it. Its instructions without knowing anything, a lot of it I still don't understand and it works and it's very helpful for me. So the prompt was, I'm looking for a safe way. To run Manus and other AI agents on my Mac, it needs to be a separate universe than all my regular applications and everything I use. The best options would be to run it on a remote server. The second best would be a parallel machine on the Mac. I'm open to any other suggestions and would like to know what are the pros and cons of each options. How much would it cost, if anything, and what are the technical skills required to set it up? Pretty generic. And that helps me go through the process. And it then, asked me a bunch of questions. are you looking for man or other AI agents? Do you have a preference of the cloud provider, whether AWS, Google, or Azure, and so on and so forth. I provided answer to the questions and then it gave me a long and detailed answer and it basically said, okay, safe isolation options, running AI agents, remote versus local. And then it said remote deployment options, cloud options. One of them is GCP virtual machines, so that's what I ended up going up with. Google Cloud platform, virtual machine. the pros. Strong isolation, fine. Grain control, free tier availability and scalability. So it's not really free, but you get 300 credits,$300 credits from, Google when you set up a new virtual machine. this thing is costing me between 15 to$20 a month to run. if I'm gonna go crazy, it's gonna cost me like$25 a month. So I get about, a year and a half to two full years of running this. Basically for free, and then I can always set up a new account and run it again. but either way, it's a great way to run this. Disadvantages set up complexity, so you need to know what you're doing, ongoing management. You're responsible for the virtual machine and operating system. I've been using it for three or four months and I haven't done any maintenance. So there is no real ongoing thing and cost for larger instances. If you're going for bigger virtual machines and doing bigger, more complex stuff, then it's gonna cost you more money. but this is not the case for me right now. Then it gave me the option for Amazon Web Services and how to do it over there, and then it gave me options on railway. So I told it about railway in one of the options. Railway is a. Hosting platform that I use to run my N eight n platform, and it has container solutions. Those of you, again, who don't know containers, think about it as a software package that has everything the software needs packaged for idiots like me to run. So you don't need to know how to install and connect and APIs and all of that. There's a container, you drop it in, it installs everything within the container, and you're up and running without knowing anything that you need to do. So those of you who are interested in running NA 10 without. Basically on your own instance, you can use railway, but in the same way, you can do this, right? You can install a railway container that has chrome and so on. the disadvantages were resource limits in sleep, which is something that would happen. The hobby plan is$5 a month, and you may need a bigger plan, which would be$10 a month, which would be more expensive than the free version that I'm basically having in Google. And so on and so forth. Mac Stadium, which is a remote Mac hardware rental, basically allows you to run a virtual Mac, through your Mac on a browser. And then local isolation options on my Mac. So you can run a virtual machine, kinda like a parallel or VMware on your device. Those of you who are using Max and using, parallel to run. Microsoft Office as an example in Windows, know what I'm talking about. So you can run like a parallel machine on your computer. but then again, there's pros and cons for that. So after going through all of this, and it gave me a lot of, and those of you who are not watching the screen, just listening to this is like a 10 page long summary with clear details on each one with a table in the end that summarizes exactly all the pros and cons. And the first option was. The Google Cloud as the most favored options. So that's what I went with. And literally the prompt that I wrote is, what is the step-by-step process of setting the GCP solution? And then he told me, step by step for Google Cloud, create a Google Cloud project. I. I went to Google and went to Google Cloud and it says, go to the Google Cloud console and gave me a link to go there and you click on your project. So now on the other screen, on the Google Cloud, on top, there's a little square that has the projects and you can click on your project, which I already created for this demo, and I called it Chrome vm. It has nothing in it yet. You can see it's an empty project. It's just a shell. It's a name for me to create more stuff. And then it says Create a project id, which I created. Then set up billing. So that's in here on the left. If you click, there's a menu and you have all the different things. And when I say on the left, it's the leftmost menu in Google Cloud, and it has all the different components that Chachi PT told us to go to. So you go to billing and you set up a way for it to charge you. But as I mentioned, you're gonna get$300 worth of free. Credits, which is gonna be good for probably almost two years. then it tells you need to enable different APIs and you enable these APIs for this project. So how do you do that? So it tells me what to do, said in 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 that where it says library in the sub menu. And you click on that and it takes you to where it has. All the different APIs that Google Cloud allows you to run on one of your projects. Now again, those of you who get diarrhea just from hearing the acronym API, because you don't know what it means and it sounds really techy, it doesn't matter because you don't need to know anything. So what you can see, it tells me to install or to make sure I have Compute engine, API Cloud storage, API Cloud, logging API, and cloud monitoring API. So like a good monkey, I'm just gonna copy the first one. Compute engine API into the search over here. And paste it in the search. He'd search and it comes up and I'm gonna click on that and I'm gonna enable that, to this thing. So literally I'm just copying and pasting and click clicking, manage and apply, and I'm setting up all the APIs that I need. I can show you a slightly shorter way to do this. So without navigating to anything, if you're just on the home screen of the, of the project, you just set on the very top, there's a search. It's like a general search for everything. Google Cloud. So if you search here for computer engine API, which again I copied from the instructions from Chachi pt, you can see it finds different things. One of them is the API component, and you will take him to the same exact place. So even if you don't know how to navigate and where to navigate, you can just copy and paste to the top search and activate those things. Then it's telling me to configure identity and access management. The short for this is IAM. And again, it tells me exactly what to do. Go to IAM admin. So I'm again, good monkey, go here, go to IAM and admin, and then click on that. And then just add users. So it tells me how to do that. create an instance, add the users and tell me what to do and what permissions to give. And I just follow the instruction step by step. The next step tells me to set up the virtual machine. Same thing, go to Compute Engine. So I go back to the menu, I go to compute engine. And I go to a virtual machine, which is VM instances, and that's exactly what the instruction says. So I click on that and you can see right now I have no instances there. What this will basically allow me to do is to create a computer in this Google Cloud environment that 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 complex and scary options on the screen. Those of, you're not seeing, there's like multiple things and buttons to press and drop down menus, but you be a good monkey. give it a name. And so the name is gonna be whatever. and then, choose a region. So you can see here it says region 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's closest to me, which in this case is in South Carolina because I'm in Florida. and that's it. Then the next thing it says, the machine configuration choose E two, which is the default, which is the low cost day to day, thing. So that's the cheapest version that I can run. And then it says, what boot disc do I need to run? So it tells me what operating system. So in the next side, left menu, it says operating system and storage. And here I actually started with this initial recommendation of running a Linux distribution. And then after a long conversation with it where things didn't work for me, I asked it to start from the beginning. And we actually, ended up using a different operating system, which is called Ubuntu. and again, I don't even know what that means. I don't know what the differences are. I just know that it worked after I had all this long conversation that didn't work. Let me scroll down to those, to that 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 different operating system? You go here in the OS segment and you click on change. I. And then you pick what operating system you want. So instead of Damian, I'm gonna choose Ubuntu. and that's it. And now you can choose whichever version, which doesn't really matter. You just keep on updating the versions 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 the cloud that I can run. 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 the instructions that it's giving me and that's it. And you hit create and it's gonna create. A new computer for you in the cloud. Now that computer still doesn't have anything in it, so later on it will take me through the steps of installing two things. One, it will show me how to install. And again, the instructions are right 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 stop running, 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 I click on it and then it will run its thing and ask me to confirm different steps. And once all the steps are confirmed, and you can see authorized SSH, and I can, I will tell it which Google account to use and then I will. Establish a few things and I get a terminal window. Terminal window. Looks like all dos, right? It's just like the ugliest thing in the world, but you don't need to know anything. I've got the code. All I have to do is copy the code. From here, there's even a copy button and I click copy and I paste the code in here and I later it run and it will do its thing. That's it. It's that simple. So I go through all these steps. The first step will install, the updates that I need. The second step will install the desktop environment, and the third step will install Google Chrome and then remote desktop. So I literally, I'm gonna stop here by showing you all the different steps, because the next steps are exactly like this is copying the code from the instructions in Chachi pt. And I'm gonna share with you a link in the show notes to these instructions. So any one of you can literally copy. Everything that I've done, step by step and use it as your own. And you can see it's running a lot of code now in the terminal, which I don't have a clue what it's doing, but it's not on my computer, so I don't really care. It's running in this virtual machine in the cloud. And so what it ends up being, after I'm installing all these different things, I'm gonna install remote desktop on micro chrome browser, the one on my computer. And you can see here that's in step six, configure Chrome browser, remote desktop. So it tells me exactly how to set it up. very simple. And once I'm done, what I'm getting is I'm getting this and I'm gonna make this full screen. So what I'm getting now is you can see I have a browser within the browser. In my regular browser here on top, you can see I have the chat that we had before and I have this AI agent sandbox instance, and it's a remote desktop into this remote machine. In here, I have my new Google account with emails that I can send back and forth from my real universe or my real computer I can send emails to here with different things that I need and tools that I need and prompts that I created and so on. Because remember, this is not my computer. This is another computer. And then I have Spar, and I have Manus and I have a lot of other things running. So this is basically how this thing runs. I now have. A new machine that you literally can follow the same exact steps that I'm gonna share with you to have a separate machine that is not my machine logged in with a different Google user that I've created, and now I can do whatever I want without risking anything that I have while still running on my own computer. So let's, I promised you a few examples, and I'm gonna show you two separate examples. one of them, I'm gonna show you the comparison between the two different tools. I used the same exact prompt on both tools. By the way, the prompt was created by Claude. So I explained to Claude what I'm trying to do, and I asked Kate to create the prompt, and then I copied the prompt here. Now again, you cannot copy and paste from your computer to this because it's not the same computer. So what I do is I. Email this from my regular email account to this new Gmail account, and then it shows up in the email tab that I have here in the new machine. I copy it from this. Gmail in my virtual machine into spar or so on. So in this particular case, my kids go to the local Scouts chapter and we are now finishing the year and planning for next year. And both my wife and I are volunteering there since the kids started going there about nine years ago. And We are every year we are looking for ways to raise money, so we have the funds to run the scouts in the most efficient way. And one of the things that I'm doing is I'm looking for grants. And previously, in previous years I did it manually. I would go through dozens of websites, looking for different grants and where they're from and other applicable and so on. I said, Hey, wait a minute. I have these agents, maybe they can help me look for grants. So I explain what I'm trying to do to Claude. And Claude wrote this prompt, objective, automate the i, the identification and initial vetting of grant opportunities for a nonprofit in Maitland, Florida. background local scouts, no profit, blah, blah, blah. Serving one, first through 12 grades, youth run troops with parent volunteers, activities. What all the stuff basically that I told it is in there. And then the scope. Search scan. Federal websites, county local sources, plus private sectors, prioritize opportunities, blah, blah, blah, blah, blah. There's a whole explanation of what I would've done manually. And then you hit go and you leave for 20, 30 minutes and it does its thing. So what do I mean by does its thing you can see? The first respond is I'll help you identify and vet grant opportunities for your scout nonprofit in Maitland, Florida. Let me break this down into steps and search the relevant grants based on the requirements. By the way, the last thing that I ask for you to do is to create a user interface for me to track the different grant opportunities, what's the status with each and every one of them, and to basically see all the information, which those of you who are watching the screen can see it on the right, but what you can see is that it's. It's now gonna use different tools. The first tool, it's using search. It says Grants for youth in Orange County, Florida, or Scouts. And if I click on view. I can see all the websites that he was searching, I don't know, about 15, 20 websites. And then it started loose searching more and more things each and every step. It's learning more stuff and it's updating the plan on how it's gonna execute on that. So it's gonna do. Deeper and deeper dives into different things. So if I dive into this one, you can already see the grant description, application submission information, so it's diving deeper into each of the things that it found previously, and it goes on and on. And it's creating tables and it's then summarizing the tables and it's writing more stuff and it's doing additional research. So you can see it's doing all these things and finding different stuff. And in the end. I ask it, like I said, to create a tool for me to track all the information. So if I keep on scrolling down through this very long process and in the middle, I jumped in and gave it additional comments when it was done with, different steps. And at the end it created this for me, which is a website that, again, those of you're not watching, I apologize, but you're missing out. But it has a. Color coded. Website that has all the different opportunities in a table where I can search and filter by anything that I want. So I can filter by, either is it a federal, state, county, city, private, Jewish community or international fund. I can look by, statuses. So I have a status dropped on menu that I can update on my own. I can see the amounts. I can see the deadlines. I have a link straight to the opportunities that I can go straight into there. But the cool thing is, in this process, what I asked you to do, I said, I want you to help me also write the request for grants. I want you to actually write the proposals. And what I did in order to do this, I created a whole task section. When I say I, I didn't do anything. I ask it to create a task section, and this task section allows me to give the. AI agent additional tasks. So you can see, I can choose a specific grant. It picks it automatically because I'm in that grant. And then I can select the type, research, Eligibility and requirements, write submission documents. I can go to write submission documents. I can then write it a detailed prompt. I can give it a priority, I can give it a due date. I can assign the task and then it's going to execute on that. It's gonna read everything in that website and it's gonna write a draft for me, and it's gonna put it in the documents of this particular opportunity. This is pure gold. I invested. 10 minutes. It invested 45 minutes, and I now have a extremely effective way to go after grants across federal, local, county, city, private, and so on that are relevant to what I need to do with a website in which I can track the status of each and every one of the activities and filter and see progress and so on. This is nothing short of magic. This process would've taken a team of several people, several different days to create, and you need a web developer and you need a researcher, and you need an analyst, and you need all these things, or you yourself spending hours to do this. I did, like I said, the same exact thing I. On Manus. Manus came out with something a little different, by the way, on both of them, both on Manus and on, spar. You can publish this thing, so when you see this really cool website up here, there's a publish button that I can, click and then I can open it as a browser window that then I can share with people. Then they can run it in a real environment, not in a virtual environment, because this is just a website that it created. So this website is publicly act available. I can send it to people and I can collaborate on this process with additional people because I can very easily share that website. That is a tool to track our process. I did the same thing in Manus. So let's look at the Manus example. you can see Manus took a slightly different approach. Again, I didn't tell it exactly what to do. I said I want an application that will allow me to filter and see, the different applic, the different opportunities. So it took a slightly different approach, but very similar in concept, each and every one of them in a different box. What's really cool here, going back to the autonomy part of this, and it's taking initiative, it gave a score to each and every one of the opportunities based on how. Applicable it is, what's the deadline and what are the funds that are available? And you can see scores in the sixties, in the fifties, in the thirties, and then some of them are zero because it found them, but it doesn't think it's applicable to us. And so it actually helps me prioritize what's to go after first, which is really awesome. And again, it has a filtering capabilities and, search capabilities. Just like we've seen on gens spark. I like the gens spark, user interface better, but from a practicality perspective, they're both highly practical for my needs. The last thing that I wanna show you is something that is more business oriented, because most of you are in businesses and not in, Not in nonprofit, but you can, you hopefully get the point even from the nonprofit thing. What I've done here is actually something that one of my clients has done initially and I just use and follow their same concept, is they are in the smart home automation world and they wanted to find. Ways to look for additional partnerships in that world. So if you're in the smart home automation universe, you cannot do projects on your own. You need an architect that will work with you to implement all the stuff that you're planning. You need a builder. A GC that will actually do the work. You need an interior designer, so you need all these different things. And if you find more of them in the area in which you work, you have more chances of getting work. And the way we've done this is we've actually giving it names and websites of existing partners, one of each, one architect, one interior designer, and one GC in order to start. And we basically told it to play. Six degrees of Kevin Bacon. Basically go and look for people these companies have done projects with, and then look for people they've done projects with, and then go and look for people they have done projects with. And then give me a user interface in which I can see each and every one of these companies, what projects they've done. Where are they in the world, and what's their website? It did all of that and it created a user interface, which again, now I have a search where I can search for specific, and you can see here it says architects and I have a list of architects, and then I have interior designers, and I have a list of interior designers, and I have builders and construction companies, and I have them, but I can filter the list very easily. Let's say this is all in Southern California because this is what it's searching for. So let's look for Orange County. So if I type orange, you can see it filters it out. It found no architects and no interior designers, but it found several different builders that have done relevant projects that I can go and look at the actual projects. I can click on the links and so on. You can build any tool for any business purpose that you want with this. Now again, it doesn't always work 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 the present, like both this and the other thing that I showed you is things that are in use. They're actually providing immediate 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 versus Manus, and which one do I like better? I'm on the fence. Like I, what happens is, in some cases I see better, success with Spar and in some cases see better success with, Manus. And so it's, it just depends. And in, in general, I think Manus does better research. And Gen Spar creates better user interfaces, but that's on, five or six projects. I don't think that's like necessarily the case a hundred percent of the time. that's why I'm always trying both, like literally everything that I have, I'm dropping into both of them and I'm letting them run. And if one of them has a better, start, then I will continue with that one. If they both have a decent start. I will continue with both until I get to a situation where I know what to do next. Jonathan said it would make it much easier if you could build an agent to set up the secure agent. I think we'll get there. I think we'll get there where the 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 about an hour to figure this out, right? I went back and forth and what I demoed to you now in 20 minutes of the setup. Actually took me about an hour to set up because a lot of things didn't work in the beginning, but after an hour it did work, and now I'm using it all the time and I'm using it safely and so on. So the, it's as much as it sounds complicated, it's worth investing one hour of your time to having a solution like this that is completely, disconnected with a very serious Chinese wall between that and your real universe. And then you can do whatever you want. Okay, so quick recap and summary. The. AI agent world is the present and it's definitely the future. There are many companies who provide agents that are very specific to specific things, like you can build voice agents to take phone calls or to do outbound. You can build agents to manage your emails. You can build agents to do customer service. You can build multiple types of agents, but then you have this new universe of general agents like Spar and Manus, and with those, they. Can do more or less anything you want because they can browse, research, summarize, connect to different systems and tools, write code, deploy websites, and so on. And I think that right now it's more geeky like it's people like me and more advanced users that are actually playing with these tools to do these different things. But two things I think will happen. One is I think these will become more and more. Mainstream as time goes by. But the other thing that I'm pretty certain of is that Cha GPT has something like this, and the only reason they didn't share it yet, and they have. Shared a version of this, right? So they have their solution that is currently available only to the upper tier. And it's the same, but not exactly, doesn't have the same freedom and capabilities as Manus and Spar. But there's zero doubt in my mind that in-house they have it. They're just thinking of how and when to release it. A, so that the public knows how to use it. B, that it's safe, and C, that it doesn't completely destroy the bandwidth of their servers that are already running very heavily doing everything that everybody's doing. But once they figure out a way and the right timing to release something like this, it's game over, right? Because right now there's 700 million or 800 million chat PT users. If you give them this capability to basically say, Hey, I want you to do this. Go do this on your own, and it will. You will jump from, I don't know, tens of thousands of people are doing it right now to hundreds of millions of people doing what I just showed you. And because it'll be Chachi Piti, I think people will feel a lot more comfortable than I'm feeling with Gens, spark, and Manus. And then. Just everybody will start using solutions like that and creating their own applications and doing their own research and summary and so on. And because Chachi PT is building more and more connectors, whether through MCP servers or just native connectors to, Google and Microsoft environments and, other big solutions out there like ERP systems and CRMs and so on, these tools will be. The ultimate power extender of every single person, right? You'll be able to ask it to do any research across any data, internal and external, either one or the other, or a combination, and get results in whatever format and report it to any other third party system that you would want just by asking in simple English. And so the ability to do things that today takes teams weeks. Be able to set it up in minutes and then enjoy them from that moment forward are. Coming and they're coming very fast. So my suggestion, go experiment with what I just showed you. Follow the instructions step by step as I did, and as I showed you right now. And learn what these tools are good at, what they fail at, how to prompt them better so when it does become available, or just start enjoying it right now. But if it becomes available in your work environment, you are more ready than everybody else. Thank you so much. Hopefully you found this, valuable. And, as I mentioned, there's a course coming up in August. Go sign up for that. The courses fill up pretty fast. We already have a few people signed up even though it's a few months away. So if you're interested in detailed AI training that can really accelerate your learning on how to implement AI in a business in an effective way, go check out the course. And thank you everybody for joining us. Live and thank you all of you for listening. If you're listening to this after the fact of watching this on YouTube, I appreciate all of you. Have an awesome rest of your day.

People on this episode

Head Shot

Isar Meitis

Host