Replace Yourself With AI (The Complete Guide)

0:00I just saw the future of AI agents and I'm not even overselling it. I had the founder of Lindy AI show us new stuff around how to use plain English to do vibe marketing, to build out AI agents that make you money and make you more productive. A lot of people have promised this. A lot of people have promised AI agent platforms that do this, But it is finally here, and this opens the door for fully autonomous companies that are run by agents. And that was science fiction, you know, literally a few weeks ago. It's not anymore. I can't wait for you to see how the new Lindy AI works and how it uses agent swarms, something called computer use.

0:50And it's going to change the game. So tune in.

1:01When it comes to AI agents, Flo, you're probably one of my first calls that I make. And today's an extremely special episode because, Flo, what are we going to learn today? We are going to talk about the two major things we're announcing today, which are the agent builder and computer use. so the agent builder makes it super easy to build the agents and computer use makes the agents basically able to do pretty much anything that you can do on a computer so I think we've been talking to you and I, Greg, about the AI agents for a while now and they've been sort of immature these two things are a big, big, big step forward with AI agents Okay, because there's a lot of episodes on AI agents on YouTube and X, including some of mine where me and people are like, this is insane This is insane.

1:50Flo, is this actually insane? If people stick to the end of this episode, will they be like, my mind is blown? Look, I don't mean to sound too grandiloquent. The tech is new, right? That's the reality of it. I think we're like, we are driving as an industry towards what we're talking, what we're calling the Macintosh of AI agents, right? So we've been stuck in the terminal days of personal computers. It's like, yes, it's insane. Yes, it's really cool. But it's really hard to use. And I think that's one of the main concerns people have about AI agents. It's just super hard to use and to create and leverage this new technology.

2:25So yes, this is a really, really, really big step forward because now you're going to be able to create really complex AI agents really simply. It's like you just talk to it. It's like, hey, I want you to do X moving forward and this and that, and you just have a conversation. And it's effectively an AI agent creating an AI agent for you. The two concerns people have about AI agents are, number one, too hard, can't figure it out, I'm not an engineer, I don't have the time for that. Number two, it doesn't integrate with my tools. We're basically solving 90 % of both problems today. So look, we don't have AGI yet, but yes, it's a really, really big step forward.

3:05Okay, you have my attention. I'm intrigued. All right, let me show my screen then. So I'll talk about marketing, I can talk about sales, and I can talk about customer support. Those are like three really big use cases. Support is straightforward. It's like just yesterday I was catching up with a friend, and he's spending like$12 ,000 a month on customer support. And this is after optimization. He's got a bunch of like VAs in the Philippines, and he's in the process of replacing all of that by Lindy. and until now he was holding back because he was like yeah but they do so much that's like it's it's more than just answering a ticket like yes we've been doing the rag thing like the retrieval thing like yes you know if you ask a question about a refund policy or like a return policy we can answer that no problem but very often they check your order status on the shopify or like they issue a refund on stripe or like you know there's all sorts of things that that that it does um so now with computer use like you can't do it just like okay you receive a support ticket or they're asking for a refund, you insert a human into the loop, probably at that point.

4:10You're going to receive notifications every so often. It's like, boss, I'm about to issue this refund. Yeah or nay? And then say yay. And just goes on Stripe or like, hey, check the order status on Shopify. It goes on Shopify. It can do all of that stuff for you. So support is just such an easy one, especially for e-commerce businesses. If you have a little bit of seasonality, it's not just about the money saving. It's just easier to operate a business that's backed by AI agents than a business that's backed by humans. Because yes, AI agents are not perfect, but at least they're consistent. Like if you've gotten it to work once, it is going to work a thousand times.

4:43Well, as humans, you never know. And they don't scale. Like they quit on you, they start slacking off, they start like sometimes stealing from you. It's like AI agents, you can just put it on the pilot and forget about it and then move on to another part of your business to focus on. So support is just like a total no-brainer. sales. Ah, we have so many sales agents. So I'll start with like a huge caveat. Like I want to be real. Like, and I think that that's one thing I really love with your podcast, Greg, is like, I feel like there's so much, again, like grandiloquent promises out there that are like empty promises.

5:17And I feel like the AISDR, frankly, is one of them. Like, if you think you can just spin up an AISDR agent and click a button and then infinite pipeline is going to come through your or like you're out of your mind. Like this is just not how it works. Like it is still a lot of work. If you don't have an outbound motion, like even if you hire the human SDR and you don't have an outbound motion, you should expect like, I think 40 % chance that they never succeed. And even if they do succeed, you should expect a couple of months of like heavy iteration. And this is not because the human is dumb. It's just, it's hard.

5:49There's like a lot of iteration. But once you have figured it out, yes, like AI SDRs can be very effective. My recommendation is that I think an AI-SDR is basically supplementing a human SDR. So that's the whole ad-bound thing. I think the way of the future is you should hire a person full-time who is basically 10x more effective than they would be if they were alone, but you still need a person full-time to manage your AI-SDR agents. And so here with computer use, the things that we are unlocking with our AI-SDRs, man, I feel like I'm going to get banned from LinkedIn, but LinkedIn, LinkedIn DMs.

6:26so you've got to have a lot of touches so you know we send an email to people we send them a text message we can do that if they have opt-in you've got to collect opt-in that's like a legal thing but if they have opt-in we make them a phone call like the agents can do that and then we hit them on LinkedIn so it's just like all of these touches and it all happens inside a single workflow and LinkedIn actually turns out it's the most effective at least for now so outreach is a really big one nurturing is another really big one so you know we jump on these calls and like a good win rate if you're like if you've got a sales team is like 25 30 so it means like at best you're going to lose only 70 of your deals but those are actually really good leads like they jumped on the call with you they have like the beginning of a relationship and so forth.

7:16And so what we do is when a deal is lost, we log it in a spreadsheet. And then we have an AI agent that nurtures the lost deals. And so what it does is in that spreadsheet, we log the use case that this person had. And then this AI agent observes two categories of events. It observes, did we just win a deal in a similar use case or like in a similar industry? So like if we're in touch with like, I don't know, like a B2B SaaS finance company of 50 people, and then we close another company that's also B2B SaaS finance 50 people. Like the AI agent is going to observe that win. So like, ah, fuck, we won one.

7:57We're going to go back to that guy. So it looks at the spreadsheet. It's like, ah, there's one guy here. I'm going to go back to him. And like, Bob, how have you been? I was just thinking about you. We just closed another business. It's like, most likely they know about them because they might even be competitors, right? So now there's like the FOMO, right? So that's one. And the other kind of event it observes is the releases. So again, we basically talk to the agent, it observes our change logs and so forth. And it's like, hey, okay, we're releasing agent builders and we're releasing computer use.

8:25And so we also have that last reason in the thing. So it's like, ah, we couldn't integrate with, we've got a lot of customers in healthcare. That's one reason I'm so excited about computer use because these guys, they have this healthcare record management systems. And these systems do not offer APIs, like Epic and stuff. And if they do, it costs like$100 ,000. You have to go through a year-long review process. It's a nightmare. With computer use, you're basically going through the back door. And so right here, this nurturing agent looks like, aha. It's like, Bob, last time we spoke, you wanted to integrate with your Epic EMR.

8:59Computer use just came out. We can do it now. Do you want to book a call? Can we build from scratch a full-on agent showing computer use just from scratch? Yeah, let me think of a use case that we could go after. Let's just do a simple use case that's going to DM people on LinkedIn. I'm going to go here. and I'm going to be like, before you even do this, 99.9 % of people are not DMing people on LinkedIn. 99.9%, including myself. But I know that if I probably reached out to people on LinkedIn, DM, I would probably close more business. I'm just not doing it because in my mind it's cringe and I don't want to think about it.

9:55But if I could spin this up and it works, that's a huge unlock for me. So I just want to preface it with that. 100%. And I think that's one thing we hear very often. People are always like, AI agents are coming for our jobs. Sure, maybe over the long term, but in practice right now, what we're seeing is a lot of people who just do stuff they wouldn't do before. We know we should post on LinkedIn. We don't do it because it's really hard to automate and it's kind of cringe and we don't want to think about it. Okay, so for now, I'm just going to make it manual, but I could be like, hey, every time I ping you on Slack or every time someone submits a form or every time someone gets added to this spreadsheet, hit them up on LinkedIn.

10:39For now, I'm just going to be like, when I send you a message with a LinkedIn profile, I want you to send them a DM on LinkedIn asking if they would be interested in AI agent services.

11:04Tailor your DM to the person's profile. And I'm going to be like, I want you to use computer use to send a DM on LinkedIn asking if they would be interested in AI agent services. and the reason I'm doing that is because we also have LinkedIn integrations that, this is the ironic part by the way, like people think and I thought that API integrations would just be the bomb that's just like universally better actually computer use very often works better so it's like hey, okay, so when you send me a message it's confirming, it's like yeah, you want me to do that and start a computerization and do all of that stuff like yep So this is crazy dude you've been building this for a while so you probably are like numb to it but the fact that you can just literally talk to it and it's building it live.

11:50This is the dream. Oh, yeah. I agree. Thank you, Greg. You're right. I've become a little nub to it. But yeah, this has been what we've been working two wheels for the last three years. This has always been the vision. You tell it what you want to do and it just does it for you. You shouldn't have to be an engineer. It's just doing it. Dude, you're going to put all the N8N bros out of business. Look, we do have some computer details that I think are unnecessarily complex.

12:28All right, it's done. I've created your LinkedIn DM at create your agent. When you send a message with the LinkedIn profile URL, and if I inspect the agent here, it's like, all right, you're going to send me a message. If the message contains a LinkedIn profile URL, I'm going to start a computer session, and then you are helping to send a personalized LinkedIn DM to a prospect about AI agent services. We are going to redact here because what I need to do is I need to enter, and this is not going to be here in production, but I have a computer ID here that I need to use for it to have my logins.

12:58You can see it even named the agent. It's like LinkedIn DM outreach agent. I'm going to save this and let's do it. Greg, I'm going to spam you, man. Uh-oh. I liked it when I was DMing, not getting the DM. Wait a minute. You know the tweet is like, I didn't realize the leopard's eating people's faces would eat my faces. Exactly. Okay, so the LinkedIn, the condition passed. It's starting a computer. We should probably do something in the meanwhile because again, the big problem is like, it's not a big problem, but it's just slow. This is going to be a pain in the butt. Yeah, I mean, while it's doing that, we can, I mean, brainstorm other ideas to just give people a sense of what sort of things that they could be creating?

13:46Yeah. Actually, it's not that slow. Let me just open the browser and then we can tab away once it starts being boring. All right, we did it. Open phone is my shared phone number with my assistant. I still have a human assistant. All right, and so you can take control and when you've taken control, you can then release control and let the agent know, hey, I just did something. So here I'm going to be like, I just logged in. I feel like I'm watching the future, dude. This is crazy. Yes, it is. And again, it's early. I always want to be careful to be real with people. But it's working. Yeah, it's interesting because I was so excited about ChatGPT operator when it came out because to me that was a glimpse of the future.

14:38but what it was missing was the agent builder, the workflow. That's right. There was only so far it could go. Yeah, 100%. I think being able to plug it to your applications, also via APIs, and being able to give it different triggers is really powerful. And then being able to have this state transition. In the case of my ex to LinkedIn, it's the same agent, but it moves from stage to stage, and that makes it a lot more reliable. Because otherwise, operator is just surprising. It's not good enough to do a lot of this stuff, even simple tasks like this. But here, you're holding its hand ever so slightly.

15:19You can see I'm not telling it click by click what to do, but I'm still like, all right, step one, you're going to check my Twitter. Step two, you're going to check on LinkedIn. And if any of these steps is screwing up, I can really pinpoint where it's doing that, like what step of this workflow, and I can update the workflow. And from a prompt perspective, Do you have any advice on how to create optimized prompts for Lindy? None. The agent builder takes care of all of that for you. I mean, you've seen me create this agent. It's not rocket science. It's like I just talk to it like I talk to an intern and just figures it out.

15:52And again, that's the beauty of it. It's like, oh, okay, it's found your profile. And now it's going to... Ah, fuck, you don't have DMs. you're like in the photo mode. Let's see if you can figure this out. But this is a good example of what I mean by like, that's the advantage. It's like, you have this double mode of like this double loop of like, you can edit the agent and the agent's instructions and you can see the agent operate. And it's sort of ping pong between these two modes. Because if the agent screws up when it operates, you can just go in these instructions and you're like, okay, like keep this in mind moving forward.

16:30Okay, so now it's looking at your like profile to know how to pitch you. Yeah, I disabled messages from random people. I think that's going to become smarter and smarter. Yeah, it's looking for the message button. I think it's just going to give up. But it's interesting to see. I want to see what happens. And then we can always bug someone else after this. Ah, it's not dumb. Message Greg is right here. Oh, you know why? Because I have LinkedIn recruiter. It's kind of messed up how LinkedIn does that. Like you've disabled DMs, but with LinkedIn recruiter, it's fine because I'm paying for it. So it's probably going to ask me to log into like a LinkedIn recruiter account.

17:10Oh, oh my God. All right, Greg, are you interested in the AI services?

17:19I might be after this DM, man. And so again, I mean, you saw me create this agent. Like it took me literally like, I mean, we can look at the recording, but like two minutes, if that, like two to three minutes or something like that. it's not going to be perfect first shot. It's working, so that's always something. But you're going to want to iterate on the copy that it writes the DMs for and so forth. So I think, and this is what you said earlier, I introduced a human in the loop, not just because it's imperfect, but also because there's a dose of subjectivity. And so I think that's where we are with AI agents now.

17:52It's like we're sort of graduating from the phase of like, hey, it screws up, and we're moving towards the phase of like, now it's just like subjective. And sometimes it does lack common sense. Wait, dude, this is crazy. Hi, Greg. Just listen to your Startup Ideas podcast. Love how you're always spotting opportunities to, quote unquote, get the juices flowing in the entrepreneurial space. As someone managing a portfolio of internet companies at Late Checkout, I imagine you're consistently looking for ways to scale operations efficiently across your ventures. As a matter of fact, I am. I've been working with portfolio CEOs who are using AI agents to automate repetitive tasks like lead qualification, customer support, and content creation, freeing up their teams to focus on the high-impact work that actually moves the needles.

18:37Given your background scaling companies from islands to advising TikTok, you probably see the potential for AI to handle operational heavy lifting while founders focus on strategy and growth. this true would you be interested in a quick chat about how other portfolio companies are leveraging ai agents oh i'd love that i'd love to share some specific use cases that might be relevant for your portfolio that's actually really smart dude are you kidding me feel shot are you kidding me this is this is this is when it's all will sit craig like you know like being a founder sucks. This is the highlight of like, it's like you build cool less products and you're grinding on it for three years and at some point it clicks and like, look, it's more like 1 % of the way there.

19:27It's in your inbox. Did you hear that? Someone just messaged me on LinkedIn. I wonder who it is. And so again, now I can like chain it with like, I could find your phone number and I could be like, hey send him a text message to be like Greg I just hit you up on LinkedIn and if you opted in I could also make you a phone call right and now it could I'm in there you go so I can I could now iterate on this agent to go like hey if they say they're in look at my Google calendar offer them times right send them an invite and so forth so if you wanted to do that you would go back to flow editor and just give prompted?

20:11Is that what you do? Basically, yeah. I would be like, okay, after that you're going to wait for like an hour or something like that. And then you're going to wait for 12 hours and then 48 hours and something like that. And every time you wake up after waiting, you check if there was a reply. If there was a reply and if they say they're in, you check my availabilities on my calendar and you send the availabilities and you go back and forth until you found an availability that works. So this is why you start really small, and then you iterate. And that's why I'm saying, look, it's not like in five minutes, one click, you're going to have infinite pipeline.

20:51But you sit down for half a day or so, and it's not complicated anymore. It's just a matter of iterating. And in the end, I can show you, in the end, you have, I'll show you this example of an agent or this example of an agent. What else do I have? This example is really good. As you iterate, And again, you build your way towards it, but your agents end up becoming really complex and really, really, really powerful. So you start small, it's really simple to get started. And this is an agent that they use for recruiting because that's how I spend half my time. And that's what it does. And this is actually not even that complex of an agent, but little by little, you just keep iterating and iterating and iterating and you land here.

21:32This is one of my favorite agents, like my chief of staff agent that just live in this thing all day. This is one of my more complex ones. This is my CRM manager agent. So this one I just talk to all day and it logs stuff in my CRM, it retrieves stuff from my CRM. So that's where you end up after you've reiterated on your agents. Incredible. Dude, you've done it. You've done it again. I don't think I've ever had someone on, actually no, I've never had anyone on the podcast where I'm like, this is the future, I need to invest somehow and I need to get involved. You know, so that's, I think, the reason I say that is I've been playing with a lot of these tools and they've been close.

22:22But this is the closest thing I have seen to what I had in my mind, which is prompt it to workflows and agent flows and then having, you know, a computer go and actually go and fulfill that task. so for me what's going through my mind flow just to be frank is like how do I take stock of we have a bunch of companies that we're running all the tasks that we're doing it, how we can productize it and where is there an unfair advantage and where there's our opportunity to actually be more productive and make more money I always use the factory image I don't know if your listeners are familiar with Factorio, but it's like this factory simulation video game.

23:10But I really do think, and I've been using this image for years, I really do think the business of the future looks like Factorio. So you end up thinking of your business as like, and open a Figma, like a FigJam, just whiteboard it out. Like, okay, my business is basically this pipeline. Every business is basically a pipeline. And then you just take stock of like, where am I spending most money? Where am I spending most time? What is the current bottleneck of the business? And let me just overwhelm the bottleneck with AI agents. I have a top of funnel problem. I don't struggle to close people once they're in the funnel, but I struggle to get top of funnel.

23:44Okay, marketing agents. I'm going to spin up a bunch of agents that create a ton of content. We have a VO3 integration that's coming. So you could totally have an agent that's like, hey, I want you to post 100 videos on TikTok and Instagram every day. And then I'm going to give you feedback about the videos. And then you should learn. You can very much prompt your agent to be like, hey, also every day, You could have another agent do that. Like, I want you to look back at your videos, views history, and see what clicks. And then I want you to maintain a Google Doc with, like, your learnings so far that you just keep iterating on.

24:16And then the other agent that creates the videos consults this Google Doc every day. So you could totally do that. I was like, okay, I've solved my top of funnel problem. Now I have a bottom of funnel problem. Like, people are a pain in the ass to support. I'm just going to overwhelm the bottleneck with the AI agents, and I'm going to solve that. And I'm never going to touch a support ticket again. and just keep doing that. And I look, people don't understand, like, and I have been careful during this entire conversation to like not be overly grandiloquent. Like, so I hope people recognize that.

24:45Like I have been saying for years, like the fully autonomous company is coming. And I don't mean that as like a grandiloquent, like this is coming in 20 years. I'm like, no, no, no, no, no. This is coming like now, like in the next two years, perhaps. I think in the next, as early as like 12 months, I do think we're going to see people create fully autonomous agentic companies? I mean, when I see something like this, it makes sense, right?

25:16So, of course, there's going to be kinks in the product as you're rolling it out. This is the first day that it's live. But I think that if you have an idea and you have distribution and you have a plan to get more distribution You create these vibe marketing agents and LinkedIn DMs. What is a business, if you think about it? It's customer acquisition and fulfillment of the product or service. Of course, it's going to be autonomous at some point. Because if you could figure out how to create AI agents that are automating the distribution, like we've just seen right now, and you can figure out how you can create AI agents and automations to do the fulfillment, then why wouldn't there be an autonomous company?