Weeks of Work in an Hour with Agents

Speaker A: I am going to show you how to use multiple agents at the same time without needing to know how to use any automation tools like Zapier Nan or make. And the beautiful thing is you could be a complete noob with those capabilities and do weeks of work literally in less than an hour. For those of you who don't know me, my name is Ryan Staley. I have helped companies with AI skill transformation for the past two years and I've worked with companies ranging from 15 million to over a billion and even publicly traded companies. So a excited to share this with you today. I'm going to walk through a couple examples of the lease conceptually, how you can start wrapping your head around this because this is something new that I haven't seen anywhere else. And I was blown away when I was sitting there literally having three different capabilities at my fingertips. One was a strategist, the other was a product manager, and the third was coding. I don't know how to code. I wasn't a product manager before and this was way beyond my skillset. And all I was doing is orchestrating these different agents in unison. Now, I'm not going to get into that exact work through or walkthrough of that, but what I am going to show you is how you can map this and start thinking through the lens of agent orchestration, even if it's manual agent orchestration. Okay, so let me start by sharing a simple concept that I call multi tabling. Okay, so if you those who don't know, I, uh, used to love playing online poker back in the day. And one of the things that was absolutely amazing about it, you could literally multi table and work anywhere from 8, 12, 16, 24 different tables. And it's so funny, uh, once I did this, uh, I had and I'm going to show you screenshots of like what I did. But once I did this, it reminded me of those days. And what you're seeing here is this is an example of a world record that a player called Elky won where he multitabled 64 tables at a time, had a Guinness World Record for it. And so that got me thinking of like, okay, with the future of work happening and the fact that this is the last group of executives that will ever manage a complete human workforce. It's like, how is that going to transition? And it got me through this concept and I looked up this article. I'm m like, oh, this is really good. To show you like a bigger view of what this looks like. He had all these different tables that he was managing and monitoring at the same time, making decisions and winning big amounts of money doing it. Now, I don't think it's going to be this complex where you would have this many tables, 64 different screens within those. However, one of the things that really hit home is like I was just working across three screens and had these different agents operating at the same time. And the reason why I did that was because they were all finishing at different times, but they were working together. Um, obviously the ultimate nirvana would be to have different agents that work in automation, where you just identify the outcome and the work is completed. However, from what I've seen with testing and talking to other folks, there's a lot of complexities behind that. And so this is a way that I know people can get immediate value right now with tools like ChatGPT, Deep Research, Google Deep Research, uh, Perplexity Labs, even Manus. Right. And to further illustrate my point, what you're going to see is there's another player called Nanoko Nanako or whatever. Hope I produce his name, pronounced his name properly. His actual real name is Randy Liu. And this goes through what he used to do. He was like a massive multi tabler as well in, um, poker, where on one day he won 76,000, but he rose from nothing to 2 million in like two and a half years. So what I'm about to show you is the process or the concept. I stopped and recorded it live. So I was like, ah, uh, I gotta do this while I have this pulling up and working through these different agents so I could show you a glimpse of it. This model of what we're doing is think of this as I have multiple different AI agents doing the same job. And then, um, I'm comparing results, identifying the winner and then picking that. Right. The more complex method is when we have different roles assigned to each individual agent, if you will, and they take on the role of people or Personas or jobs. And so I'm going to do, I think, a future video on this. But this was literally something that, that I was blown away with because it was weeks of worth of work that literally happened in hours. So check it out. All right, so what you're seeing right here is something that I'm working on. I am multi, um, tabling agents over here. Okay. So just to give you context, I have genspark, I have Manus, I have Claude with the new artifacts capability, and then in addition I have Perplexity Labs all running in sync at the same time. So this was one of the moments that I wanted to share with you because this was literally a, um, kind of like my chat TBT moment with agents that I experience. And I did this the other day. Uh, but this is a situation where I'm running all four in conjunction with cloud class I'm running up on. I did research, I sketched out ideas and created a monster prompt. And as you can see, this is, uh, genspark. It created an amazing presentation that's very clean and solid looking. Uh, at the same time I did the same thing with Manus. Manus did a really good job as well and was impressed with that, uh, artifacts. This just got released where you could effectively make apps. This is not even asking for an app. This is really just talking about the prompt and what I used. And what you're seeing here is at first it started off with a really comprehensive document or almost brief, if you could see of what I should cover when I'm conducting this training. But at the same time then, um, I'm looking potentially even generate a dashboard or a map. The other thing that you'll see too is with Perplexity Labs, this is agentic in nature, but it's wild how many results this has. So what you're seeing here is it provides all these different artifacts that are associated with it, from examples to curriculum to implementation timelines to visuals to even code and app. And so this is one of the examples that I just like as I was pulling this up, I wasn't even planning on making this content right now, but I was like, I gotta share this with you because this was transformational for me. The other day when I was creating an app on Lovable and I was doing three core things, right? Number one, I was doing effectively product design with one agent, right? So more of a product manager I was. And that was, um, trying to think what I was using for that. I think I was using Gemini for that, right? Which was really, really good for that, being a product manager. Then the other side of it, I was using ChatGPT03 for more of an executive reason. So that was more going back and forth. And then last but not least, I was using Lovable in the other screen, uh, while I was using all three of those at the same time. And so it was pretty crazy because I had three people stacked. I had really an executive thought leader, uh, who could operate at the same level that I could. But specialization was beyond my skill set. So that was more on the product side. There's more on the coding side. And then when I was Working in the product manager side, I was literally building prototypes within Gemini and then I would go over to lovable, paste that in there, also iterate back and forth, make connections. And what I was seeing is because all the agents operate at different speeds, they weren't all finishing at the same time. So one of the things I had to kind of look at was I had to look at like, all right, that's why I multi screened it. Now what you just saw was four in one screen, which is crazy, right? But I see this being the future because like literally executives now are the last. Executives are only going to have human employees. You're going to start to have employees like that where you have multiple people doing different components of a job. And just so you know, context wise those are like, if I were to have done that manually and had people do that manually and had to work with three different areas, three different people with the exact same task structure that I had and workloads that probably would have taken weeks at the same time. We've been really hard to find those people. And on top of it too. It was one of those areas where even if I had that embedded within what I was doing in my network and I knew there was still a lot of RAM time with like conversations, meetings, docs that needed to be trained back and forth. Whereas I did all that in an hour. And like I said that would have taken weeks with three different people with very high skill sets that I did not have. And so that was one of the things that blew me away was like, like I said my secondary chatgpt moment where I was like, holy shit, this is going to change everything. And it's really operating agents, um, in a multi tabling format, which, you know, I really didn't talk about this, but um, I don't know if you've heard of what's called, um, a person. His name is Elkie. Right. So he was a multi table or poker player who this was, I don't know, probably about maybe 2013, 2014. And he would mass multi table. So he would play like he would have tons of screens on top of each other like I just showed you, with multiple monitors, maybe play 24 tables at once and would be basically winning millions of dollars per hour doing this. And it was one of the most like interesting examples that I've ever seen. Um, I actually multi tabled as well. I didn't multitable to that extreme and at that highest stakes. But within doing that, what I saw was that, uh, yeah, there's massive amounts of opportunity to compound leverage that I had. Instead of just sitting there waiting and playing, I could basically use a heads up display and operate across 12 to 16 tables and really increase my profit per hour. So I think even that's like plain poker, online poker. I think that foundational element is going to translate over to work with what we're doing. And like I said, I had to share this to you. I stopped, uh, what I was doing. I'm like, I got to record this, I got to share it with the world, because I literally think this is one of the directions that we are going to head into, at least until things get more massively organized. But literally, I had, I don't know, probably hundreds of thousands of dollars of work done in an hour across three skill sets I didn't have. I probably paid, I think, a total of $80 a month or $100 a month for that capacity. So that was wild. Um, had to share it with you. Transformational. For me, um, I was going through the lovable ship program and just to build out like a prototype, something that I was doing as a hobby for an AI infographic creator. And it was one of the things where, as I was going through, I'm like, oh, this would be awesome to share because I think this is where the future is going. So happy to see you on today. Hope this was helpful, and I will see you all on the next video.