This AI Finds the Idea, Customers, and Does the Work Transcript, AI Summary & Key Points

00:00 Anything that you do on your computer, your agent  could be doing and in many cases should be doing. This is someone on my quote unquote payroll that  never stops working and cost 99% less than an actual human. It's going to an actual browser and  browsing like a human. My hands are off the mouse keyboard here. You can hook up Telegram, WhatsApp.  Anytime anything's on your mind while you're just on your phone, you can put your agent to work.

00:20 We  have probably 20 agents running autonomously, like fully endto-end. I have an agent that is like my  visual designer and motion designer. This is crazy to me because it would take me hours. You set it  up, you go to sleep, you wake up, you have leads. You could do this for any niche. Your agent can  go and find these candidates and actually build them new digital properties to the point where  you could sell the implementation of that website specific to them.

00:47 That becomes your template  that you then stamp out across all your clients. You could start this for almost nothing. The guy  that I talked to actually did. I knew I asked it to do this, but I didn't think it actually would.  That's incredible. Boom. That was incredibly easy. I bet you can't find me one person that wouldn't  want AI to just go out there, an AI agent, and do stuff for it while they sleep.

01:09 Well, today  we're talking about how to do that. Cloud's cool. ChatGBT, awesome. Those are awesome. What if  it went a step further? What if Chat GBT was in a robot body and could go a step further and do  stuff for you? times a h 100red AI agents. That's what we're talking about today. How to make money  with them, how to build them, why they're cool, why they're important, why they're dangerous,  how to guard rail them.

01:28 And if you're the type of person that agrees it's better to show than  tell, stick around because at the end of this I'm actually going to build something with Hyper  Agent for myself. Super cool. Please enjoy. What is a practical realistic use case for an AI agent  today that you're seeing people use on a daily basis? Yeah, I'll jump right into one that's super  visual and easy to understand.

01:47 This will start off as kind of like a one-time task, like a project  for an agent, and then I want to show you how you can start to change your thinking and and consider  these agents as persistent 247 employees. Okay, so this is a run of an agent that has found  local businesses that have great reviews, but no website or outdated websites. finds their  contact information, learns about their brand, learns what customers love about them, and then  actually builds them an entirely new website.

02:19 So, let me walk you through what the agent actually  did here. So, what you're looking at basically is all of the thread with the agent here is  on the left. All of the thinking process, it spins up sub aents to delegate different uh  tasks to break things down, make them happen in parallel. And then on the right here are all  of the artifacts. So, you can see the agent has visited some websites, taken some screenshots.

02:41 It  actually literally opens and runs its own browser over here on the canvas. So while it's running,  you will see it actually navigating the web. And then the final deliverable here is in the form  of an all-encompassing web page which is meant to be for my consumption which contains all  of the business candidates that it found as well as the websites that it built for them.

03:02 So, for example, we've got CS Automotive here, 300 plus Google reviews, fantastic reviews, but  uh no real digital presence, no website. And so, it has actually based on its understanding of  what they do just from the customer reviews and the things that people love about it, built them  an entire website here that has a booking system as well. Oh, man.

03:25 So, you can come through here,  even get an estimate. These are all just based on best judgment, best guess of of pricing, right?  But if you were to actually get this in front of this business, you could make this specific  to them. So the idea here is from one prompt, if you're watching the video, pause it, screenshot  it. You can do this anywhere.

03:39 You could do this for any niche. Your agent can go and find these  candidates and actually build them new digital properties to the point where you could sell  the implementation of that website specific to them. So you could put this in an offer and  say, "Hey, we've learned about your business. We think people probably can't find you the way that  they should be based on all your amazing reviews."

04:01 here is an example of the type of website we'd be  able to stand up for you within days. Or there's even this notion that maybe that website is just  like a free giveaway because of just how easy it is and how fast it is to do this at scale. Hey,  this is yours. This is yours for for zero cost. So you see a few different things that I'll call out  there that agents are capable of.

04:18 One is extensive deep research all happening in parallel. This  whole run was about maybe 20 to 30 minutes from the research finding the candidates to actually  building all these unique websites. Browser use, like I mentioned, being able to actually judge  visual quality kind of qualitatively to say, "Hey, that that to me." That's right. Yeah. That  looks like kind of an outdated website that could be better.

04:43 That's going to be a candidate for the  outreach. Actually managing drafting that outreach per business. So tool use in there as well. So  it's going to be able to use your email and draft those messages. is you can approve them or you  can just trust the agent and say go for it. So, uh really good example of what pretty close to  a oneshot task that you can give an agent and this skill is on the marketplace for free  as well.

05:03 If anyone wants to try this for a certain domain of businesses or in their local,  you should uh you should give it a try. So, let's say three years ago, I have a an internet  agency that makes websites for local business owners. Yeah. I'm going to spend my downtime, you  know, browsing through Google Business Profile, finding businesses with no website, looking  into the reviews.

05:22 Do they have pictures? Are they optimized? Oh, here's one. Find their email,  scrape it, cross reference it, email them. I see you don't have a website. Can I build that for  you? Your response rate is going to be 0.5%, 1% maybe. And then you respond, you hop  on a call back and forth, days elapse, weeks elapse. Then it's like, "All right, what  kind of a website do you want?

05:42 Let me close it. Let me invoice you." And now you're saying  like you set this up, which you can just get the template from you. We don't need to start  from scratch. You set it up, you go to sleep, you wake up, theoretically you could have leads.  Yeah. So there's a Seinfeld episode where Kramer takes this car out and he tries to push it as far  as he can go that you know how far it can drive on empty.

06:05 Yeah. If you were to get really bold  with this and go further, like send the invoice, accept the payment, fulfill the service, hop on  a call with them with your product, how like how far could you push this agent if you really wanted  to be hands-off? And I'm not saying people should. I'm just curious. Anything that you do on your  computer, your agent could be doing and in many cases should be doing.

06:26 If it's more of a chore,  then your agent absolutely should be doing that. Like if you feel while you're doing some computer  task that your brain is like almost off, you should never be doing that task again. So actually  running the outreach and watching your inbox 247. This is another huge one, Chris, where I'll uh  if I go into one of my agents here, I'll just show you where we can set up tools.

06:48 So when you go  into tools and integrations, you know, if a lead comes in overnight, that needs to get a response  immediately, right? So there needs to be an inbox kind of night owl agent as well where anything  that comes in inbound or earns a reply from your outbound is immediately getting that that response  and that acknowledgement. We have agents running uh ads as well autonomously like fully endtoend  generating the creative strategy optimizing the spend uh doubling down on the winners killing  the losers.

07:18 So everything related to filling your pipeline, outbound ads, inbound sales coaching  is is another one. So get your notetaker on your call, have those notes automatically passed  back to your team of agents so they can give you feedback on your performance with that client.  How can you improve your close rates? How can you sharpen your own script and uh and your ability  to actually secure that business?

07:40 Daily marketing competitive intel and industry briefs. feed  that into your team of agents as well to to tune up the outreach that they're doing. Are there  things that are more timely or more relevant they could be including? I'm also just showing directly  through the web interacting with these agents. But another big shift is being able to just message  your agents as if they're teammates.

08:00 So Slack is a big one for us. You can hook up Telegram, you can  hook up WhatsApp, just like you would communicate with an employee anytime anything's on your mind  while you're just on your phone. You can put your agent to work. So, if I click in here to my team  of agents, each of these cards here is a different agent that has a different job. And that helps  me actually organize.

08:19 Okay, I only want to give my agent access to be able to post on X if it it  is the agent that knows my brand voice and that I'm explicitly told and granted that permission.  I want a separate agent that's actually touching customer data and financial data. Those two things  better not ever cross. And I can create hard guard rails by assigning those permissions to different  agents.

08:41 It looks like with our team internally, these aren't our literal agents, but we've got  four of us on the growth and marketing team here, and we have probably 20 agents, each with  fairly broad sets of responsibility. Like, I'm not talking like, oh, like one little workflow  or approval. You know, I have an agent that is like my visual designer and motion designer that  creates all the stuff that we post on website or on X.

09:08 We have like a CMO agent that orchestrates  to all the other ones, copywriter agent. you really start to think of these in terms of  full-time jobs. Okay. So, what's an example of a breadandbut agent like simple but helpful that you  see a ton of your users using and then could you show me how to build that live? Yes, sir. Okay.  So, the most popular agent on our marketplace, which is where we have all these different agent  and skill templates, is called Signal.

09:32 This is your always on 247 sales agent. So it works  end to end owning the full pipeline. I'll walk you through some of its key capabilities and then  I'll I'll show everyone how to actually grab this agent and start setting it up for themselves.  So it is responsible for growing pipeline, growing our business, getting us more customers.  So that's the explainer on Signal and then I'll jump into seeing it in action.

09:54 Yeah, let's do  it. Okay, so this is our thread with Signal. So the way this is structured is in what we call  live mode. So there's basically one thread that keeps getting the same prompt on a set cadence.  In this case, I have this set to every hour. And Signal wrote this prompt, this loop effectively  for itself based on everything that I loosely instructed it how to do.

10:19 So this is a good like  general point with our agents as well. I just describe a job description the same way I would  give an employee a job description. And the agent is the one that can actually scribe those detailed  instructions for itself to the point where, you know, there's been a lot of, I think, excitement  over the last several months about, you know, skills and we have our skills on our marketplace.

10:37 I'm excited when a skill does the job. You won't really find me diving into like the exact wording  in that skill or in the pieces of it because it's not really for me anymore. It's for the agents to  run themselves. So every hour in this same thread, this live mode prompt gets kind of reinserted into  that thread and then signal goes to work. So it does everything that was just in that explainer.

10:59 It goes and finds new prospects based on our ICP. It will build personalized landing pages for  them. So let's take a look at this one. I've switched my context here. This is a different  type of company that we're kind of representing the sales outbound function for. This is a real  company uh that I've been working with on their hyper agent setup.

11:17 It's called Swiss Solar and  they actually sell self self-cleaning solar panel technology. Very very cool tech. That's cool. And  so you can imagine the types of prospects they're looking to sell into are like industrial-grade  solar projects. They have found that their agent can go out and actually source real information  and run deep research for specific people that are the project leads on specific solar farms and  industrial projects.

11:40 And then the idea here is that this is a personalized landing page just for  that person. So you have you know what in the the CTA in their case is let's let's discuss a study  or a pilot program. We actually have videos here that the agent has created here as well. It's  got screenshots of the software. It's got real images of that project that's all incorporated  into this hero video.

12:04 Some animated explainers discussing how the technology works. more shots  of the product UI. So, you can imagine like you are receiving this very very personal and unique  proposal of a technology you're not familiar with but has clearly put in the work to understand your  business, the specifics of your project. You know, we think we have a much better chance getting  uh someone on the on the phone after receiving a proposal like that than just a plain uh text  kind of cold email.

12:32 I I feel like this is very egofriendly. I like to say like if you're if we  were Yeah, I like that. on a live sales call or a demo and I'm actually interested, but I don't want  to really show it, then I'm probably not gonna ask as many questions as I want to ask. I don't want  to lead you on. So, I'm like, I don't know. I'll check it out and then I might or I might not.

12:51 But  this is very async, right? He can do it on his own time. He could ask it a bunch of questions,  go through, take his time without the fear of anyone watching him or anyone pressuring him, you  know? 100%. Yeah. And think about I mean again the old school way to do this the I mean the classic  copout response from any buyer is like oh send me some materials.

13:10 Well now it's like I can send you  some materials. It is something hyper specific and personalized to you. And hopefully if we do that  actually earlier in the process we stay out of that trap of just needing to you know send someone  some materials. And so we're we're actually really earning that buyer's attention and respect by  putting in that deeper work for what is in this case especially a very high consideration type of  purchase.

13:30 We're really starting that relationship out on the right note. So, as I'm just scrolling  through here, you can see that Signal, this agent, as it's been running in live mode, just  working 247 has been building out these uh these contacts for real projects, been building  out all these pages, and then it's doing all of its other kind of routine chores in every run as  well.

13:49 CRM discipline. It's going to post an update over to Slack for me as well. So, if I switch  over to Slack, this is what that looks like. We're big fans of wherever possible, we think  agents should be prompting their humans rather than humans needing to prompt their agents.  Your agents should just be working. Like your agent should be working 24/7.

14:08 They should have  clear guard rails, tool access, and then when they need your attention or just to update you,  they will let you know, hey, in my 3pm loop, here's what I did. Added some new prospects, built  out their pages here in the command center. Here are some things I learned. That's the other really  powerful part. Once you get this wheel in motion is the constant learning.

14:30 So for the outreach that  does earn a reply, you're going to see more of that from Signal. For the tactics that don't work,  you're going to see less of that and is always going to be passing those learnings back to you.  Hey, here's the type of prospect that actually seems to be responding better to our offer and the  type of messaging that's earning that click and that call book.

14:47 Interesting. Do you have any like  anecdotal case studies of people using your agent for outbound sales that have like actual wins that  they've reported? Yeah, there's been a couple. Um, let me show visually what some of it looks like.  We had, for example, a landscaping company that has been using agents to actually build out their  proposals based on inbound leads in their case.

15:14 So, imagine you are looking to get some work done  on your yard. You send in a very short description of what you're looking done with a picture of your  current yard. Maybe you send that out to three or four different local companies. One of them gets  back to you, you know, very quickly and actually has a vision for you of what your backyard could  look like, your actual yard.

15:28 Like this is where you started and this is what it could look like.  Meanwhile, the other three companies are like, "Uh, well, we'll see when we can come on site."  Probably took them one or two days to get back to you anyways. like what a competitive advantage it  is to not only have an agent that's able to reply right away and kind of respect that that lead as  soon as it comes in, but actually potentially sell them a little bit of a vision and not have the  customer have to use their imagination for an offering like

15:56 that. That's destined to fail.  We're not creative beings, right? Like we we shouldn't have to expend brain power into how we  can give you more money. We need to do all that for you. Take away all that. We got to see Yeah.  People have to see it to believe it. even things that are, you know, a little bit less visual but  still uh kind of warrant this approach.

16:10 We have a paving company that is using satellite imagery of  uh large lots like parking lots that are clearly, you know, past their prime. Yeah. And showing with  that satellite imagery and AI image generation, here's exactly where we would repave estimates on  the cost based on what we can see from satellite. Interesting. and you know the the impact to  the value and kind of like street curb appeal of your of your business or your commercial  property whatever that might be.

16:39 So there's some really cool use cases like that. I'll share  one more was uh a company that does branded like company apparel essentially. So you know you might  get your your company polos or hats or whatever. Uh again you can see where this is going. Let's  build that prospect list. Let's actually take their branding put it on some of our products.

16:59 use AI image generation to show, hey, this is what your team could be looking like when they show up  to the site or show up to the trade show. Here's some different visual styles, you know, interested  in in understanding more about what we can do. So, those are some of the the fun ones that are a  little more on the visual side that people have been doing.

17:16 What about um this is just a personal  idea I have. So, I I just bought a ranch here in North Texas and it has this pond that needs to  be dredged. And so, I'm looking for like pond dredging companies, pond maintenance companies.  And and I had the thought and I prompted Claude like, are there any companies that's like the Zoom  info for ponds? Like, if I were a pond management company, could I buy a customer list?

17:38 Could I get  leads from somewhere? And then I asked Claude, "How many ponds are there on farms and ranches  in Texas?" 800,000. Okay, 800,000. And I said, is there a directory? Is there a place where I  could sort through that? It's like, no, that's not a thing. It's like, well, that that's very niche,  but certainly people would pay money for that.

17:54 So, could I use hyper agent to build an agent that  could go take I mean, all this stuff exists, just satellite data, GIS, mapping, spreadsheets,  and just take a measurement. All right, like this lake is one acre. The address is this based on the  PIN, and just put it all in like a Google sheet. I like where you're going. Yeah. Do you think any of  that data would come from like zoning applications or anything?

18:19 Or would would straight up satellite  image analysis be the best sour? It could come from tax records, zoning applications, like right,  let's try. Well, I'll I'll let Hyper Agent run and we can we can keep chatting and we'll we'll see  what it does in the background. Let me prompt it here. I just got an idea from my friend Chris  for uh our pond dredging company.

18:33 Uh we're in North Texas. you pick the the the town where this  might make sense, but what we want to do is build out a database of all of the ponds that might need  dredging in the area. Uh we're thinking you might be using satellite imagery to do that or maybe  zoning applications or other sources of data. Uh do a little proof of concept sprint. See what you  can find using different approaches to find leads for our pond dredging business.

19:02 Oh man, that's  so good. So, we'll let our agent run there and see what it comes up with. Yeah, it's not the  best use of time, but it is a little bit fun to just watch them run. Yeah, you get to see their  whole thought process. You get to see them lay out different approaches, rule them out, whether they  work or don't work. All of its actual um artifacts will pop up on the canvas here as we go.

19:24 It's like  Claude in a human form, right? It's like a robot whose brain is cla or chadypty or grock or all of  the above or whichever one it decides to use with the ability to go out and do the thing that you're  asking questions about. Yeah, exactly. Yeah. At a technical level, it's worth mentioning in every  single thread, every agent actually literally does have its own computer.

19:45 It has its own virtual  machine where it can do things like run commands and install libraries. And you're going to  watch it right here open up its own browser. So, my hands are off the the mouse and keyboard here.  It has spawned what we call sub aents. So, it's got a couple sub agents here where it's it's sort  of they're running like in parallel then.

19:59 Yeah, exactly. So, it's kind of got like the, you  know, it's got the gang together and said, "All right, here's the overall plan. Agent one, I  need you to check the satellite data. Agent two, I need you to check the zoning applications."  And they're going to go off and run in parallel and then report back to uh to the main agent  as they they complete their their work.

20:16 Okay, that's a good one. Yeah, we'll see how it does.  I'm curious, what else have you seen from your your audience when it comes to this concept of  having agents that you really start to treat more like uh like employees or co-workers? Are people  pretty early in that journey? Are you seeing some some cool experiments that people have started to  to get real value out of?

20:35 Very early. I know a lot of people that have AI implementation businesses,  they'll go into small to mediumsiz businesses and do an AI audit or just help them install AI  tools. So I am curious how agents could help them find more customers or help them fulfill  customers they already have. Yeah, this is a group that we're thinking a ton about and I would  speak to it on two levels.

20:57 So one is for the AI automation agency itself for your own internal  operations. use these agents, whether you use the pre-built templates or come in here and build  AI employees for yourself to find more customers and also to service your customers, run your own  operations, project management, things like that. But you could use that exact same flow that I  was sharing where that that same single agent is running outbound, inbound, nurture, finding  leads within your niche, whether that's kind of uh physical service

21:29 businesses or something more  upmarket, whatever that might be. The second thing is using this as a platform to actually deploy  the agents that you sell. So any agent here that you create like you might have an agent for your  niche that let's say we stick with this like pond dredging example that's like the pond dredging  project manager agent and we're going to go sell this to all the pond dredging companies that  becomes your template that you then stamp out across all your clients.

21:56 So we think that our  platform also has a really strong position as being the way that AI automation agencies actually  choose to sell, package, and deploy those agents to the end client. And I'll I'll come back to this  agent in a second, but essentially the way that's structured is we have this concept of teams.  They're kind of like different workspaces.

22:13 And so I could have a workspace for just one client  like Apex Landscaping. I could have workspace for another client. And then I my client can  be in there and actually be the one paying the bills for the ongoing AI costs, but I'm the one  actually managing and editing those agents that are inside this workspace just for them. So I  have that backend access.

22:32 The client can just use the agents. You could give them edit access  if you want, but for most of those AI agencies, we hear that they and their clients just want  the client to be an end user of the agent and any backend changes to that agent, any config  is going to happen by the agency. And so you can set up that exact model right in here. We  hear that AI implementation agencies are doing a lot of like very creative and I would say  often like hacky stuff to be able to set up, standardize and package their

23:02 offering, deploy  it for clients with like a lot of technical stuff with different private servers, everything like  that and then actually charging for it is uh is a bit of a hassle as well. We can simplify a lot of  that with uh with this setup. Yeah. Beautiful. How does Hyper Agent know what a good website looks  like? It's going to be looking both visually, and by visually, I just mean literally like it'll  take a screenshot and then process visually what it's saying.

23:27 It can also look at the code itself.  So things like the color choices, the layout choices, the use of negative space. I'm looking  at the landscaping one just because it's what I had handy, but this is a obviously a page that  that agent has built itself. Code has become the language of agents now. They're so good at looking  at code and understanding what they're seeing and understanding how it could be better and how that  code is going to visually present itself.

23:48 So it's twofold. It's one is straight up image recognition  like if you were just take a screenshot of this and say is this a clear layout? Is this good use  of color? Is this a modern you know font family? Things like that. The second is actually by  inspecting the code. Those are the two ways that that age can conclusion because they've seen all  the examples and all the references in the world of every website that's out there and how web  design trends have have changed over time as well.

24:15 I mean, put maybe overly simplistically, it could  just Google best looking websites of 2026 and just find random blogs and train itself on how that  looks. Like, all right, we're seeing a lot of SIF fonts. We're seeing a lot of pastel colors, choo  pattern matching, pattern matching. Cool. Yeah, exactly. If someone were total beginner to AI  agents, they've used Cloud, they've used Chad GBT, never agents, what do you suggest they do from day  one on on your platform?

24:35 Yeah, I would say pick a part of your work that you find very tedious that  you would like to not do anymore that is like a computer job and start with asking hyper agent to  build a dedicated agent for you to do that job. That should hopefully give you the first taste  of what these agents can do. You can put that agent into live mode as well like we talked about  with signal.

24:57 So just every hour it comes through, it runs its checklist, it does that job. From  there, you can start to get more ambitious. And the metaphor is less about, oh, what are like  chores and tedious things that I don't want to do? And it's more like, if I had all the money  and time in the world to make the dream higher and make that person really successful, who would  I hire right now?

25:16 And then what would they do 24/7 if they never had to sleep? So, for example,  with Signal, the sales agent, it's like, well, dream sales hire would be constantly sourcing new  outbound, constantly sharpening its messaging and its approach to our ICP definitions. It would go  super super deep in its research for every single prospect and build them something very personal  as a proposal or pilot or initial offer.

25:37 It would never let a warm lead go cold. And it would track  everything perfectly in CRM. it would find that you would get creative with where it finds contact  information. List those things out and then push your agent to do as many of them as possible and  hopefully we've given a taste today of how far you can go with that. What's something that you've  seen Hyper Agent do that genuinely surprised you?

26:03 Ooh, that's a good question. A lot of the  browser use stuff is really impressive because it's so humanlike. The way it will actually  just navigate through web interfaces that are not meant for agents. Like the web at large is  still pretty hostile to agents. You think about things like even like captas that are just in the  way. They're like trivial for agents to solve now, but they're still in the way from the era where we  were so concerned about bots.

26:22 Now the shift that's happening that's underway is people actually want  to make their websites very agent friendly so that agents can find them as opposed to only being for  humans. But seeing agents actually browse the web, visually process what they're seeing. We had our  agent do like a a landing page design tearown. So if I go back through here, yeah, this landing  page tear down.

26:43 So it was doing like this would be for like a web design analysis or something like  that using its browser look at web design trends and then come back with annotated markups the way  that like a really expert designer would. That was really impressive to me between the browser  use, the visual understanding and you use that that word taste which is becoming a hot topic  for sure with any kind of visual work or even copyrightiting.

27:09 In my experience, given the right  context and instruction, the models are getting pretty good. A lot of the video work as well,  Chris, has become really, really exciting. So, if I quickly go over to our X feed here, let me  show you some of the stuff that I've been able to do with these agents. So, so let me let this  play and then I'll tell you about why this was so exciting to me.

27:28 So, this video that you're looking  at was created by a motion design agent. So, it's very meta, but I have a motion design agent  creating videos about agents. Historically, for me to do these demo videos, I have to use the product  as if I'm the customer I'm trying to represent and then screen record the process, show the agent  generating its work, show a really good outcome, and then edit that video together.

27:51 It's very like  handcrafted and artisal. You got to get the timing right. You got to make sure everything that's  on the screen is right. What's happening here is this agent is actually using its own browser.  It logs into hyper agent and it says, "Hey, Alex has asked me to create a demo of an agent  monitoring its inbox. It will actually do that, understand how that would look as a real run  and then through code actually just create that whole visual experience and animate it and  get all the timing right.

28:16 It can also then take creative liberties where it has like these popup  messages from the agent, a popup message from the human user that are there because it helps  clarify the product story. This is crazy to me because it would take me hours to create a screen  recording of this quality and there's even things I wouldn't be able to do here where I'd have to  like awkwardly punch in on the text.

28:36 Now the agent can just have the whole storyboard of this whole  product animation exactly the way that it wants. The creative possibilities that this unlocked have  been pretty amazing for me as a marketer. Okay, first of all, that's wild. Second of all, how how  much babysitting is required? like with other vibe vibe coding tools or prompting like it's loading  it's loading you're checking in you're fixing you're fixing the last mile is really really hard  what would you say to that I would call it less about

29:04 babysitting it's not so much that I have to  watch it during runtime but there are definitely a lot of iteration cycles so to get this motion  design agent for each of its runs I expect to have to probably give it three or four rounds of  feedback so the the rhythm of that is I start the thread I let it run it usually takes about 30 to  40 minutes because again it's using its browser to actually study the product.

29:25 It's actually coding  up a recreation simulation of the product. It's thinking through the whole storyboard and then  rendering the video. It then pings me when it's ready. There's probably things related to the  timing or the visuals or the sequence that I want to see improved. Maybe some copy that is put  in the video is off. It runs again. That run's going to be much shorter.

29:42 Maybe 5 10 minutes. And  then maybe we have to do that a couple times. So it will get to a serviceable output every time. I  don't have to babysit it in order to get it to a decent output. But to get it to my standard is  usually going to take a couple tries. But that time keeps getting lower because during every  run it is learning as it goes. And so it says, "Okay, Alex has given me that feedback.

30:02 I'm not going to forget that." There's always that perr run feedback and learning that  you're going to have to be prepared for. Again, just like if you were onboarding an employee,  the difference here is that those learnings will stick in the form of literal updates to its skills  and its memories. Okay. Speaking of marketplace, can this browse Facebook marketplace and message  people?

30:19 It can do anything through the browser. It can do things more easily and faster when there's  an API. I haven't tried the marketplace example, but of course you could do that through through  the browser directly. So, it could actually literally open marketplace, scroll through based  on what you're looking for, try different search terms, and either buy or sell on your behalf.

30:37 For  sure. So, another example, you know, I bought this ranch, so there's a bunch of stuff I need to buy.  I need to buy a side by side, a Bobcat, a tractor, ton of stuff. So, I'm on Facebook Marketplace all  the time and sorting and talking when can I come see it? And I have my assistant helping me, but  it's still a pain. So, I'm wondering if I could go to my Claude project that I already have for  this.

30:56 It knows exactly the makes and models and prices that I'm looking for. Just say, "Claude,  give me a markdown file of everything of all this. Give that to Hyper Agent and say, "Hey, let me log  into my Facebook account. You know what I want? you know what I'm looking for. Every hour, every  two, if you see something that fits my criteria, reach out and ask questions.

31:15 Exactly. Right.  Yeah. I'll show you even step by step how you would do something like that. So, let's imagine we  had that markdown file. You would literally just attach it right here as you're getting set up.  And I would just say like create an agent that's going to watch Facebook Marketplace for sales that  I specify. And we'll just see how this agent gets spun up.

31:32 I'll just want you to see the uh the  create agent flow here, which is really, really simple. So, I've kept this one really general. If  you had like specific products, specific buying criteria, you would just give all that to the  agent. If you see this little card right here, we're now going to get what we would call a named  agent. So, a specific agent entity that's going to have its own name, its own avatar, like all  these ones we've been seeing, signal, funnel, red line.

31:55 These are all named agents. So, you can  always use hyper agent just for a general task, uh, kind of a one-time thing. But exactly what you  started describing there is where we're seeing all of our customers start to shift. And what they  want is these persistent employee like entities that actually perform a job on an ongoing basis.  So we've got this agent here called let's see what it chose to name itself marketplace scout.

32:17 So  as you see described here this is going to be a persistent agent browser access listings table.  So it's always going to be remembering what it's seeing what comes back around. So we can go ahead  and save this agent right here. It's suggesting that we put the agent into live mode, which is  that feature that I talked about where it's just gonna wake up every hour, run through its list,  run through its list, and if it sees something that fits your criteria, you can instruct it on  how to notify you, whether that's

32:39 through email, WhatsApp, Telegram, Slack, Discord, whatever.  We'll enable live mode. And then when we go see that agent, we can see it's given itself the  little shopping cart emoji as an avatar here for fun. We can uh we can generate one as well. Maybe  friendly robot in a uh noir style. Why not? Let's see what we get here. And then I'll show you  how we set up those integrations as well.

32:59 But that's cool. Yeah, our CEO actually has an agent  that will watch uh vintage sports car listings for him. Uh which is very similar to what you're  describing. That's a good idea. Beautiful. Well, how's our pond project doing? Let's see. The uh  the pond dredging lead genen analysis agent is still working away. Let's see what it's found  so far. You can always uh jump in and just ask your agent to summarize, but it's been working  hard.

33:24 you, as you can see, like these runs, they do get quite long with the more ambitious  tasks. And so, let me just see what it's learned so far. Just pause work for a second and update  me with a few key bullets on what you've learned so far. It gives you the whole thought process  here. So, a little out of my depths in terms of this like geographic data it's looking at, but we  can see what data sources it's been trying.

33:41 Yeah, with a little more runtime, what I would expect  to get back from this agent would be basically a single web page artifact that is kind of  like that command center that I had going for the solar panel tech company where it's here's  all the leads, here is the buying signal that I specifically identified, the data sources where  I got it from, and here's exactly the message I would send to them as a reach out.

34:06 So here's  what the agent found. Let's have a look here. Here it picked a specific town in North Texas  looks like based on some population figures. It's got imagery. It's got a pretty good start  there, it looks like. And then, like I mentioned, I would just have it keep running and then deliver  its findings basically as a a briefing to me that uses some of that design and formatting that  we saw from the other agents.

34:24 Amazing. Well, thank you, Alex, for your time. Where can we find  you? Where can we find this product? Follow us on X would be uh the best place to keep up with  what we're doing. Hyper Agent OnX and uh use uh the link that we'll provide for your audience to  get some initial free credits to get you started. Give your agents some ambitious jobs. The jobs you  would give, you know, really skilled people that you were hiring and see what they can do when you  you just let them run.

34:48 Yeah. Let them help you, you know, find customers, grow your business, run  operations. There's a ton of potential here. And we've got some other customer stories you can see  on our socials as well if you want to get inspired with with what people are doing. Beautiful. Thank  you, Alex. Awesome. Thanks, Chris. All right, as promised, I'm going to log into Hyper Agent and  build some pretty cool stuff so you can see for yourself hands-on how this actually works instead  of just talking about it theoretically.

35:11 Okay, this is Hyper Agent, which I am an active user  of, and it's built by the team at Air Table, which I've been an active user of for years. You  give it a job, it goes off, it uses a browser and real tools and comes back with something that is  actually finished. This thing can run a whole team of these agents at once. It builds real stuff.  We're talking like entire web pages, dashboards, not just text or images.

35:36 There's this one company  that had a single dude build a fleet of 14 agents that his whole team now uses every day. So,  today I'm going to use it for my favorite thing, which is finding boring businesses that quietly  make a killing and then actually building one out. We're going to start right here in the search box  and type in this prompt. Find me 10 boring local businesses that quietly make over $500,000 a year  and that almost no one talks about.

35:58 For each one, tell me what it costs to get started, the  typical profit margins, and why more people aren't doing it. Put it all on one clean page  that I can read fast. Cool. Okay, let's see what it does. I'm going to leave it on the model  that it shows by default, which is GPT 5.6. Okay, let's see what it's doing. Reasoning asking me  a couple questions here.

36:18 What should make over $500,000 a year mean? You know what? I'm going  to say owner profit. Which market should startup costs and economics reflect? United States. Do  you want business models or 10 specific operating companies? Both. So, if you give it a crappy  prompt, it improves it for you. Okay. I think it's really important that you actually watch what the  agent does as it's doing it because it's mimicking human behavior.

36:43 It's going to an actual browser  in a cloud computer session and browsing like a human. It's reading documents, searching the web,  portable sanitation. Oh, a little sneak preview right there. Now, it's suggesting a couple skills  that we can save. This is basically like a skill. It's a skill that Hyper agent just learned and it  wants to know if I want to save it and recall that skill at any given point.

37:05 Kind of like the Matrix,  right? They plug into his brain. He's like, I know karate now. That's a skill. He doesn't have to use  that skill when he's talking to his grandma, but if a bunch of bad dudes in suits approach him on  the street, he's going to access that skill that he had learned previously. Same thing here. We'll  go ahead and save that.

37:18 Let's go ahead and check in with it. How's it going? Okay, I went ahead and  approved the plan as presented right here and now it's cooking. Super cool. Research four boring  US local facility or assetbased business models capable of exceeding 500,000 and normalize  annual benefit to the owner at established scale. Multi-tore laundromats, laundry route, self  storage, express car wash, parking lots.

37:40 Cool. The initial screen is done. The threshold is genuinely  demanding. Most qualifying operators need several crews yada yada yada. Tightening the evidence row,  especially the named examples. searching the web. Bisby by sell. Bisby by sell. Cool. I like how  it's not just being a yes man and saying this one can and this one can. This one can. It's saying  a $500,000 owner profit threshold eliminates most easy side hustle examples and usually requires  multi-crew or multilocation scale.

38:07 Appreciate the honesty. So interesting watching it learn in real  time. It's an interesting route it's taking. It says broker reported examples. So it's referring  to a business broker. And it's doing this, I'm assuming, because I asked for specific examples of  500K SDE, sellers discretionary earnings, aka what the business owner actually makes, because profit  is not it.

38:30 You can make a million dollars profit, but the owner is only able to pay himself a  fraction of that because he's reinvesting the profit back into growth or he pays 38% in income  taxes or whatever. So, it decided to go look at business broker listings because that's where  owner reported net profit is super interesting. It says it's flagging unusually strong  earnings claims rather than treating them as verified facts.

38:56 So, it's checking itself. Elevator  maintenance, pest control, parking lot striping, towing company, commercial cleaning, tree service.  Very cool. Okay, here we go. It's publishing it on a web page for me. It didn't even ask it to  do that, but I'm down. Okay, research brief. 10 quiet businesses with the path to 500k in owner  earnings. Scale is mandatory.

39:11 Broker data is not audited. Okay. Parking lot and striping. I've  posted about this twice. Interviews like long form interviews. We'll link to them below. 8,000  to 90,000 to start, which is not fully accurate. You could start this for almost nothing. The  guy that I talked to actually did. You can buy a $5 paint roller, but regardless, 35 to 40% net  profit.

39:30 You would need $1.25 to $1.43 million in revenue to have 500,000 in net profit. It  works because paint fades every 18 to 48 months. People avoid it because it's night work, weather  windows, aggressive selling, bid accuracy, yada yada. Septic drainage. Cool. Portable restroom  rental routes, commercial janitorial contracts, pest control service routes.

39:54 Number five, elevator  maintenance number six. And it says the downside is license plus labor fortress, which I would  agree. Fire protection inspection. Number seven, tree care and arborist. Number eight,  towing recovery and impound. And number 10, pallet recovery, repair, and resale. Interesting.  And it shows how to verify these earnings claims.

40:15 Very cool. Now, I kind of want to know more  about the laundromat business. And I personally don't really like the elevator maintenance  business. So, I'm going to ask it to swap that. Swap number six with laundromats.  Okay, look at that. Number six, multi storere laundromat portfolio. There it  is. Now, let's have it go a step further. Take number six and build me a page I can actually  publish.

40:35 Put every laundromat within 30 mi on a map. I'll put a zip code. Here's the zip code  I grew up in. Put every laundromat within 30 mi of 32796 zip code on a map so I can see which  towns have a gap. Pull in real photos. Which neighborhoods? And I'm going to put 100 miles.  Have a gap. Pull in real photos. Then add what it cost to start. Simple pricing and how I land my  first customers.

40:55 Pull it all on one page. I can share. Okay. Centered the study on Titusville,  Florida. Building an overlapping search grid. Now because map indexes cap results per query  the page will describe. So it's scraping Google places which is awesome. Looking at census  data population buffalo mess. Yeah. Okay. Okay. Look at this. It's doing exactly what  I said.

41:16 There's where I grew up. Tisville, Florida 32796 within 100 miles. It's making a map.  Okay. I knew I asked it to do this, but I didn't think it actually would. That's incredible. It's  interactive. It's like based on what seems to be the Google Maps API. This is incredible. Okay.  Done. It built and published the Space Coast Laundry opportunity map.

41:36 Okay. Interactive map  with 78 laundromats and four screening gap areas, overlapping searches, and then it even has a  design here. Where should the next laundromat go? Amazing. Click on a couple pins. Pulls in the  reviews, the address, star. Beautiful. Remember, these agents actually learn as you use them.  They remember things like you remember things.

42:00 So each time it runs and builds stuff like this,  it's better than it was before. And guys, this is amazing. It's interactive. It's handing me the  actual page, not like some theory, not some mockup or wireframe. This is something I could hand over  to an investor right now. We want to publish it. We do. I'm just going to hit this drop down right  here.

42:16 Allow search engines to index this page. Yes, please. Publish. Done. Done. That's it. Okay.  Now, we want to be sure that this saves. So on the left sidebar here, we're going to click agents.  Cool. So, I told it that I wanted to save this as an agent because I want it to update and run every  day, every week, whatever. And it says click this save as agent.

42:38 It open this window right here.  We're going to name it uh deal scout. Then we're going to click invocations right here. And we're  going to create a schedule for it just in plain English. Run every morning at 7:00 a.m. Oh, got to  be more specific. Run searches for new laundromats in other Florida zip codes every morning at 7:00  a.m. Boom. Now it is on the team with the rest of my AI agents.

43:01 I've got another one that scouts a  Facebook marketplace for me personally every day looking for skid steers to buy because I'm on the  market for one right now. This is someone on my quote unquote payroll that never stops working and  costs, you know, 99% less than an actual human. Boom. That was incredibly easy. Just took four  or five steps. You can let it find an idea for you.

43:21 You can give it an idea. Either one. It'll  do the research, create videos, publish stuff, everything you need. Go try Hyper Agent. Use  the exact same prompt that I used or your own, whatever, and see what it digs up in your town.  Let me know in the comments what you find.