Making $$$ with Loop Engineering

I sit down with Elie Steinbock to unpack loop engineering and how to run a business on loops. We start with the roots of the idea in the lean startup and Toyota's manufacturing, then move into practical, copy-ready workflows for SEO, Facebook ads, and product feedback. Elie walks through a live Google Search Console example on Draft Fantasy and shows how to set up an SEO loop that runs once a month for years. The core promise for listeners: hand repeatable business work to an AI agent that measures an objective metric and improves over time. By the end, you know how loops work and how to launch your first one today. Timestamps 00:00 – Intro and episode promise 02:54 – What is Loop Engineering 06:51 – Loops with AI agents: build and verify 11:17 – Example of Loop: SEO as an objective-metric loop 15:29 – Setting up the SEO loop and tools 25:27 – Cost and token economics 29:05 – The Paid ads loop 33:10 – The product feedback loop 36:25 – A minimal viable loop for every channel 39:21 – Closing Thoughts Key Points Loop engineering means giving an agent a task, an objective metric, and a stop condition so it improves on a schedule. The lean startup and Toyota's build-measure-learn cycle map directly onto AI agents. An SEO loop connects to Google Search Console and Data for SEO, then pushes rankings up month over month. These loops run cheaply — often a few dollars per monthly run — which beats the cost of an agency. The same pattern extends to Facebook ads, and a product feedback loop stands as the ultimate version. Start small with a minimal viable loop tied to a clear metric like impressions or ten likes. Numbered Section Summaries The Promise of Running a Business on Loops I open by asking Elie what listeners will walk away with, and he frames the whole episode: use loops to automate SEO, ads, and more. We agree the aim is clear, copyable workflows people can launch today. Where Loop Engineering Comes From Elie traces the recent buzz to Boris from Claude Code and Peter Steinberger, plus a joking tweet from his friend Dimitro about software that builds itself. He grounds it in the lean startup's build-measure-learn cycle, which itself grew from Toyota's lean manufacturing. Loops With AI Agents: Build and Verify Elie explains the agent version: a build step paired with a verify step and a clear stop condition. He uses Inbox Zero's evals as an example, where the agent keeps adjusting the prompt or model until accuracy passes 90%. The SEO Loop We dig into SEO as the flagship example, where Google ranking serves as a clean, objective metric. Elie describes a loop that runs once a month, learns from the last run via a markdown memory file, and steadily climbs the rankings. Setting It Up on Real Data Elie shows his Draft Fantasy Search Console, connects the agent to Google Search Console and Data for SEO, and runs the loop live in Codex. He shares the Atom Eve prompt as a deeper template people can copy. Cost and Token Economics I raise Ross Mike's skepticism about loop buzz and token spend, and Elie makes the case that an SEO loop stays cheap — often under five dollars per monthly run. He adds that Max-plan users have plenty of headroom, while tight budgets suit cheaper open models like GLM 5.2. Ads, Product Feedback, and the Ultimate Loop We move to a Facebook ads loop that tests copy and creative variants, favoring a mix of human hooks and AI optimization. Then Elie describes the product feedback loop — reading customer feedback, analytics, and logs to prioritize and ship — as the closest thing to a business that builds itself. Starting Small We close on the minimal viable loop: begin with one channel and a modest, verifiable metric like impressions or ten likes, then let it compound. Elie and I agree that every part of a business could sit on a loop, and starting one today makes for a low-risk experiment. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND ELIE ON SOCIAL Youtube: https://www.youtube.com/elie2222 X/Twitter: https://x.com/elie2222

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Greg Isenberg?

  You might have heard of engineering loops. They've been going viral on Twitter and everything like that. And I think they're really interesting, but they're way more interesting to use to actually run your business. There's a way to use loops to actually get customers, get SEO, be seen by LLMs, and actually improve your product 24/7. Now, I haven't seen anyone cover how to actually implement these loops. So I created a tutorial, how loops work, how you can use it to run your business, and how you can use Claude Code or Codex to actually implement it. In this episode, I share everything with my friend Ellie, and you'll see and understand completely how to do it yourself

• 0:41Greg Isenberg?

  so that you can get traffic, get customers, build a startup today. My favorite loop is actually the last loop that we share. Enjoy the episode, and I'll see you at the end.

• 1:01Greg Isenberg?

  Ellie, welcome to the show. By the end of this episode, what are people gonna learn?

• 1:06Speaker 01

  Yeah, so you're gonna learn how to use loops to better automate your business. Loops have been really popular over the last few weeks. People are using loop engineering to better develop products. But it can go a lot further than that. You can use it for SEO, for Facebook ads, really to automate almost every part of your business. So that's what we're gonna talk about today.

• 1:26Greg Isenberg?

  Okay, cool. So yeah, people are using loops to basically build products. But you're basically saying there's a way to use loops that could, you know, you could run your business on it, basically. And that's gonna help you get customers. That's gonna help you build a more efficient business. And what I'm asking for you, Ellie, is if you can clearly explain how to actually do this thing, and then show some examples so that people can actually just copy some of these workflows. And then by the end of the episode, they're gonna understand loops for, you know, how to use loops to run your business, but also how they can get started today. Can you make that commitment, Ellie?

• 2:06Speaker 01

  Yeah, yeah, sure.

• 2:10Speaker 01

  I'm going to show you how to use loops to run your business. We're going to talk about it at a high level, like sort of what the concept is, where you can potentially use it. But then I'm also going to show you how it actually runs in practice. So it's not just theoretical. I'll show you how you can actually improve your SEO massively using loops. It's the sort of thing a lot of you might be doing today. If you have anything running on a schedule, that's a form of loop. But we're gonna sort of really push it far. And I think the state of AI today, you can really do quite a lot with a loop over a long period of time. Most of the time, we're talking about loops. Maybe, you know, they run in half an hour, an hour here. We're talking about loops that might last for months or even years.

• 2:52Greg Isenberg?

  Let's do it. All right, let's get into it.

• 2:54Speaker 01

  Cool. So yeah, around a month ago, loop engineering got really popular. Boris from

• 3:02Speaker 01

  Boris from Claude Code started tweeting about it. Also, Peter Steinberger from Open Claw started tweeting about loop engineering and everyone sort of was like, wow, what is this loop engineering thing? Overall, it's quite a simple concept, but it's really blown up. And I guess it's nice that sort of it's got a term now, loop engineering, before someone could have described this concept. And it didn't have sort of a one word explanation. Now it does. Shortly after this whole hype cycle started, a friend of mine, Dimitro, he went and tweeted this, "In 2026, you don't prompt anymore. Your software should be able to build itself and achieve product market fit on its own. Your only job should be to

• 3:42Speaker 01

  find money to pay for tokens and take care of yourself." So he was definitely joking when he wrote this. I think he was making fun of this whole idea of loop engineering, how we had like, you know, prompt engineering, context engineering, harness engineering. Every month, we've got another hype cycle. But if you read the tweet, I found it funny. I thought it was a great tweet. But then the question is, wait, could you actually do this? What would it look like to actually have everything running on a loop in your business? So that's what we're going to speak about today. And the idea of loops, honestly, it's not that new. Maybe even like 10, 15 years. Ago, the Lean Startup book was pretty popular and a big part of that book was this loop where you

• 4:26Speaker 01

  build something, you'd measure how it does, then you'd learn from it, then you'd build a bit more. But basically, if you break down a business or you think about Dimitro's question, how could an entire business run as a loop? It's basically, let's go build something, let's get feedback, let's improve it and just keep that cycle going of like build and learn, build and learn, and I guess measure as part of that as well. And you can do the exact same thing with AI and it's not just sort of high level for like the business to build and get feedback that might be on the product, but you can do this for so many parts of your business and it's actually what you do already. If you're improving your SEO, you're seeing, okay, where do I rank today? Where do I want to rank? What are

• 5:08Speaker 01

  the things I can do to improve it? Who is ranking above me? You do all these experiments and then you try and rank higher and you have accurate measurements from Google coming back to you. And so that would be an example of a great loop that you can run. It's a loop that I'm running today in production. If you're like sort of familiar with like lean manufacturing where or the sort of the Toyota story where a lot of this stuff became popular as well, that's also a loop where basically you're just constantly iterating and trying to make things better. And so these aren't new concepts. I think we're all familiar with them. When it got paired with loop and loop engineering, it was like, wow, what is this? But I think it's something we all understand quite

• 5:50Speaker 01

  well and it's just how do we take these ideas and get our agent to do the same thing?

• 5:56Greg Isenberg?

  Right, yeah. And the Toyota example, I think that was the basis of the Lean Startup book, right? I think Eric Rees looked at the Toyota example and basically said like, hey, there's this Japanese company and the way they manufacture, how are they able to create such reliable, consistent cars? And it was through the the loop mechanism that they had this assembly line that was just highly efficient. And because of that, they were able to just create incredible products at a good price. What Eric looked at, he said, okay, well, you can actually build a startup That same way, you know, before that, people weren't building startups in that loop way. They would sort of, it was more artistic. They would kind of like just put out a product and change it, you know, as they go.

• 6:41Greg Isenberg?

  But I think the, you know, Toyota slash lean manufacturing process, applying that to startups was one of the reasons why we had such successful startups post, you know, 2005. So what, what are we talking about when we're talking about loops with AI agents?

• 6:58Speaker 01

  Yeah, so I think maybe the best way to explain it is to jump into that first example I spoke about. Well, I guess let's talk about a sort of a loop, loop engineering first and then jump into specific examples. But I would say if the loop for the lean startup is build, measure, learn, we have very similar steps here with an agent. We have this build step, which is like telling an AI, hey, go build me my new SaaS, for example. Then we have this verify step where, you know, if you're building product, the verify step might be that all tests work or the agent has used a browser to make sure it can click through everything. Or there's some other agent that's running. If you're doing this in Claude code and you use slash goal.

• 7:41Speaker 01

  So that's basically running this loop and it's got this other agent checking, has it actually finished or not? Is it working? And if it's not working, it's just going to tell the sort of the main builder agent to just keep looping and looping and looping till it's fully working. Some other examples of this within engineering. So you always have this stop condition. You don't want the AI just to loop infinitely. There needs to be some sort of result that you converge on. So it's some stop condition examples. One is like the feature works in the browser. I want signup, like the goal is to have signup working. You know, you slash goal make signup work and then once it's working in the browser, it's what, you know, it's passed and that's sort of the end of the loop.

• 8:25Speaker 01

  Another one for anyone building AI products, I run a product called Inbox Zero. So this like it manages, it's an AI that manages your inbox. And this one is super important for me. Basically, we have evals, the evals are sort of tests for AI, like. How well does it do? In the case of Inbox Zero, it would be how well does this model categorize emails? So for example, I just got a newsletter email that came in. Does it get categorized as newsletter? So evals are basically like the tests, the evaluations to check how well the AI is doing. Different models will perform better or worse, depending on what prompt you have, it will perform better or worse. So your goal is to sort of get your evals really high. It might be choosing the right model

• 9:10Speaker 01

  or adjusting your prompt. And so you can run this as a loop as well. And what that would look like is tell your agent, hey, I want our tests or evals to pass, like get a score of ninety percent and above. And so it can keep running the prompt over and over and it can keep adjusting it. And if it sees, oh, I'm only passing eighty-eight percent of the time, it can try again. And each time it will try and do a bit better till eventually it gets past ninety percent accuracy. And so if we take this, that's sort of on the engineering side, how you're always sort of building and verifying. But it's verify step. It doesn't just have to be related to product. It could really be anything.

• 9:53Speaker 01

  And really what you want is some sort of input back into the system, some sort of objective metric. And so in the case of SEO, which is the first example I mentioned, the objective metric is where do you rank in Google search? So right now, if you search for the term Inbox Zero on Google, Inbox Zero ranks first, but some other term, AI email assistant, we really want to rank high for that as our business, but we're ranked, I don't know, position thirty or so. So what we can do is run a loop that runs every month, for example, and tries to push us further and further up until basically we're on that first page. And honestly, this is a loop that never really has to end. Maybe this loop ends when we're in position one.

• 10:37Speaker 01

  But this isn't a loop that's running, let's say, for half an hour straight. It's running once, it's taking its step and then a month later, it will continue its process and try and push us further up. And so we can go. Into detail like what this actually looks like and what is needed to make a loop like this work. Because this example, I think like it's a good example because it applies to a lot of other things in the business. Facebook ads, for example, you know, you're spending a hundred dollars a month on the ads or a hundred dollars a day. You know, you want it to get to profitability. So it's all the same ideas. So how can you get an AI agent to get there? It is basically the ideas, the idea here that we're trying to understand.

• 11:17Greg Isenberg?

  Yeah. And with with SEO, I think, you know, the way you would typically do this is you would hire an agency or you'd hire a freelancer to essentially do this loop, right? So what you're suggesting is you kind of don't need to hire that person, at least to start. You can, you know, hire or slash build a loop that has a KPI, in this case, Google ranking, which is, you know, isn't gray. It's black or white. Either you moved up this month or you moved down or you stayed the same, right? And you're able to basically say, okay, am I doing a good job? Am I not doing a good job? And then based on that, actually, you know, perform actions.

• 12:00Greg Isenberg?

  So the only question mark is can agents, at the time of recording, can agents, are they smart enough to actually work as good, if not better, than hiring an agency or a freelancer? Because, you know, ultimately, as a business owner, you care about the, you know, moving up in the rankings, right? So you don't want to like have a loop just for the loop's sake.

• 12:25Speaker 01

  Yeah, exactly. And I would say also, even if you do try this experiment and it doesn't work, you haven't necessarily lost anything. A lot of us aren't necessarily going to be hiring the SEO expert anyway. So it's just like, you know, you could run this experiment and worst case scenario, you see, oh, it's actually had negative impact. What a loop like this would do would be like, let's say we move from position 20 to position 30 in like sort of Google rankings. You could just undo the change, basically. So none of this is really set in stone. And it's sort of just experiments that we're running and hopefully like sort of long term will push us up. If anything goes wrong, we can always revert. Nothing is set.

• 13:05Greg Isenberg?

  Right. I mean, so I guess, do you think that agents are good enough today such that they can actually impact Google ranking and and get you more traffic?

• 13:18Speaker 01

  So having run it myself, it's definitely having positive results. It's going to take a few months to sort of really have the impact that I want. But yeah, for sure, like I, before we did this recording, I took a look at the numbers and I can see a whole bunch of numbers are going in the right direction. Some of them, you know, I might be moving from page three on Google to page two for a certain term. So it's, I guess it's valuable, it's getting there, but obviously the ultimate goal is to get to a first page ranking. I do think it depends on lots of different factors, like, you know, inbox zero domain rating might be like 63 or so. Last I checked, 64, something like that for a new business that sort of has a super low domain rating.

• 14:02Speaker 01

  Maybe, you know, it would work out differently. But yeah, to me, I'd happily run this, whether it's like an established business or, you know, a new business that you're starting to set up, basically.

• 14:15Greg Isenberg?

  Well, that's the thing with SEO is don't expect to do SEO and it works in 24 hours, you know?

• 14:22Speaker 01

  Yeah.

• 14:22Greg Isenberg?

  SEO is something that takes months, not days, that's just in general. So this is the type of loop that you kind of want to have, working in the background while you're doing other things too, right?

• 14:32Speaker 01

  Yeah, exactly.

• 14:34Greg Isenberg?

  So that way, you know, you might wake up on month, on month four, like nothing's really happening. Then month four, all of a sudden bam, bam, bam, you know, you're on page one. And that's happened to me in the past where it's just like SEO wasn't really working for, you know, some amount of time. But you know, you're still, you're doing the things necessary to rank well. And then all of a sudden that compounds and it starts to really, you know, bear fruit. So yeah, let's, let's go deeper into this and see some examples.

• 15:05Speaker 01

  Yeah, exactly. And it's definitely something that compounds over time. And I think everything you do marketing wise is all going to have an impact. Also, you know, we've been speaking about SEO here, but all of these things obviously benefit your, your EEO or GEO for ranking in search, in LLMs as well. So it's still super valuable, even if you're not someone using Google search that much anymore. Like going sort of deeper into this, like how would you actually set this up? So.

• 15:37Speaker 01

  The example you brought of having an agency that's sort of running your SEO. I'm not an SEO expert, but what they would likely do is run certain experiments. They do an audit of your website. This is something I think you should get AI to do for you regardless. Just get an audit done. It will say like, oh, we should improve these meta tags. Or, you know, you've got these JSON LDs which could like give you a small boost. So go and do all of that. Maybe you don't have a sitemap. There are a lot of things AI can just get fixed immediately and a quick win for most websites, I would say. But after that, what sort of that agency might do is start to experiment with certain terms. It's seeing, okay, you're ranking quite well for AI email assistant, but you're not on the first page yet.

• 16:23Speaker 01

  What is, you know, what, what is happening there? What, what can we fix? And so this whole thought process, you don't even need to worry about it too much. The AI will go into it. You're like, okay, you might be cannibalizing your own links because you're sharing, you know, the, the link power between two different links on your website. But like whatever the AI comes out with, or the SEO agency, what they're going to do is make those improvements. And they're not going to see results immediately. They're going to come back a month later and see, okay, we have moved up, we have moved down. And so the exact same thing that the SEO agency is doing, that's what we want our own agent to do for us. And so the first thing we need to do is give it access to all the tools it needs. The main ones, I would say, one is Google Search Console.

• 17:07Speaker 01

  That, where you can basically see all your data. And Google Search Console has an API. So it will show you exactly where you're ranking for Google rankings. I'm going to go to that.

• 17:21Speaker 01

  So here we're looking at my Google Search Console for draftfantasy.com. This is a business I started around 12 years ago. It still runs today. It's not my main focus, but because of the World Cup, it's had quite a lot of activity recently. And here you can sort of see how it's ranking. It's had 10 million impressions over the last three months on Google Search. Down here, we can see sort of some of the queries. That it's ranking for for the thirty eight zero search term right now, it's had one hundred and twenty thousand clicks, which is actually quite insane. Um. You can see it's got a million impressions. This is actually not a business that I've been running. There's sort of this loop agent on. I didn't want to go into the numbers behind Inbox Zero.

• 18:06Speaker 01

  But I'm happy to sort of share what's happening with drawfantasy.com right now. And you can see it's ranking well for a bunch of terms. But like what I did around two days ago is basically tell my, you know, my Claude code. Go and do the same loop engineering thing we're doing for SEO for Inbox Zero. Let's just have it run for draw fantasy as well, because why not? It will run in the background. I don't really need to think about it. It will make, you know, good updates over time. And it will remember what it's done and then go and make more improvements. And so here you can sort of see like lots of data around like, you know, where your search terms are ranking. Um, um, where is it? Let's say average position. This is like a big one.

• 18:47Speaker 01

  So for example, over here, you can see I'm ranked fourth to the term thirty eight zero. But let's say I want to push that up to one, like the AI can basically look at all of this data that I have here on screen. It can connect via the Google API and all this data will come into it and it can make a really smart decision. Honestly, a lot better than me even and decide, okay, these are the terms. I'd like a bringing a ton of traffic right now. How can we change things so we can rank even higher? So this is four point four right now. If I can get this up to three or two, imagine this wouldn't be a hundred and twenty thousand clicks. This is might be a half a million clicks. So it can drive just a ton of value. And there might be some really low hanging fruit that it can go and sort of fix up and make it work.

• 19:32Speaker 01

  Um. So yeah, the first thing to do and just across your business, whether you're doing loops or not. I think one of the easiest tricks is just connect your AI to your different tools, your real data. And the tools here would be Google Search Console. Another one would be Data for SEO. That's like an SEO API similar to Ahrefs and Semrush, I believe. And it will show you how you're ranking against competitors. So Google Search Console will just show you, okay, your. Or ranking fifth over here, but like what are the four articles that are ranking higher than yours for this term that you're really after? And so the more information you can give to your AI, obviously, the better it can do. And so what this loop actually then looks like is it makes improvements, it can check an objective metric, which is your Google ranking.

• 20:16Speaker 01

  Where you're ranked, it can learn from that, which you know, you can do immediately. And it can continuously iterate and the idea is every month or maybe every two weeks. It looks back at what it's done, it's noted everything down. This is another important part of it, like have it remember, have let's say a markdown file with everything that's happened. Then the last time it made improvements and then it can basically check its experiment, did it do well or not? I decided to change the description of the page. Did it, you know, did that description change? Did it rank our article higher or lower? And so it can look back at what was tried, what wasn't tried and it can iterate on that the same way as an SEO agency would do for you.

• 20:58Greg Isenberg?

  So if someone wants to actually create this SEO loop today is the easiest way to do it. Basically screenshot this, paste it into your, you know, Claude code or Codex. And be like, I want to create an SEO loop. I want to give you access to my Google search console slash data for SEO. And I want you to be judged on the objective metric of the Google ranking. So like check, check the metrics. Is that what people should be doing or how would you optimize that?

• 21:38Speaker 01

  Yeah, I think if you did that honestly, you could go quite far with it. I can show you an example, if you go to atom eve dev, this is another website I put out not so long ago. But here there's actually a real example of this SEO improver or just improve. This, people don't need to use this if, and if people are familiar with Eve, which is a Vercel project that just came out. Or Flu framework by the Astro team. So this is sort of like. You you don't need to use these to build agents, but this is one way of building agents. Um. But either way, even if you don't use this, you could honestly copy and paste this URL into your Claude code or codex and just say, hey, I want you to go and sort of copy the ideas here.

• 22:21Speaker 01

  But here you'll see basically a prompt um that does the same thing, which is like, you know, this is my Google Search Console. This is, you know, the the data for you to get into, the the API key for you to get into data for SEO. And then here's sort of a photo prompt that you can go and copy if you want.

• 22:39Greg Isenberg?

  Oh, wow. This is great. This is awesome. So this is, yeah, this is basically more, this is a expanded upon version of basically what I just said. So this is basically like you're the SEO improver. You're, you know, you're going to be judged upon these three metrics and and it's, yeah, and instructions on MD file for the specific uh job, right?

• 23:00Speaker 01

  Yeah, exactly. So you you can see, for example, it's saying when you apply changes, select the subset of this week's recommendations and clean needs of files and the blog repo. You you can read through it if you want. But the basic idea is exactly what we said. And, you know, if you're, if you want to play with the CLI, you can even run this command or even copy this prompt, honestly, into Claude code. This is a prompt and it will set that up for you. You don't need to use this. It it might actually complicate things for some people like using Eve or Flow. And if, like, I might just show you this in my own Claude code quickly.

• 23:33Greg Isenberg?

  Yeah.

• 23:34Speaker 01

  Cool. So here's my own codex, just running it in a terminal on my machine. I've actually gone and like taken the idea we had here and just taken a screenshot and of the chart we had before, and that's the loop we basically want to have running. Um. But yeah, if I say, hey, I I want to set this up

• 23:55Speaker 01

  for myself, I want to create an SEO loop.

• 24:00Speaker 01

  Basically, honestly, even with that, we should be able to get quite far. Maybe like if you're doing this yourself, speak to the AI a little bit more about it. In terms of what actually needs to happen, maybe you can use plan mode. But like it literally is as easy as that. It will guide you through like how you have to connect Google Search Console. If you're running it on your own computer, that's the easiest. There's a CLI you need to install or use the Google API. So there's like a few steps you need to go through like to give access to your data. But once you've done that, honestly, it should be quite easy.

• 24:38Speaker 01

  And you know, say something like, we want to improve our SEO. That would sort of be the main thing, maybe even do it on your own repo. Depends where your blog is, how this is done exactly. If you have a WordPress blog, maybe you want to give access to WordPress. If it's, you know, on some other system, if it's GitHub, then you could do that differently. But you give AI access to your blog, everything you're doing, all your data. And then honestly, from there, it should be able to run on its own. The one step afterwards, what you really want is to have some sort of automation set up. So like if you're, if you're a Claude user, they have, I think, are they called routines on Claude right now?

• 25:11Greg Isenberg?

  Yes.

• 25:11Speaker 01

  And Cursor has automation, so, and I think Codex, it's also called automations. So you can run one of those and the idea is just every few weeks, it should pick up where it left off, basically. And yeah, if you want a much deeper example, then use what we showed for Atom Eve, basically.

• 25:27Greg Isenberg?

  Cool.

• 25:29Greg Isenberg?

  So I had my friend Ross Mike on the pod recently and we talked a lot about loops. And his, his perception about loops is, you know, he's an engineer, he's a front end engineer. So he's looking at it from an engineering perspective. He basically was like, I don't really believe the hype around loops. I think the people that are going to get rich from loops are the token providers. Cause people are just going to be burning tokens. Now, we didn't talk about any business use cases. We were talking specifically around engineering. If I were to implement an SEO loop, would it be smart to basically say? A click to me is worth three cents or a customer to me is worth a hundred dollars.

• 26:13Greg Isenberg?

  You know, stop like, you know, stop.

• 26:17Greg Isenberg?

  Basically, stop the loop if these things happen, right? Because you basically, what's gonna happen with these loops is it's gonna cost money. And it might be fifty dollars a month, hundred dollars a month, two hundred dollars a month, depending on what you're actually doing. And you might just decide like, it's not worth it. So I'm curious how you think about cost benefit analysis for loops.

• 26:41Speaker 01

  Yeah, so I watched Mike's video, your guys' video together, and it was great. And I like, I definitely agree with a lot of what he's saying. That's like, you know, the unnecessary hype around these terms.

• 26:55Speaker 01

  Also, in terms of cost, for sure, like he mentioned that Peter Steinberger works for OpenAI now, spending one point three million dollars a month on AI credits. You know, it might even be more at this point. So I fully agree with that. For this loop, I would actually say it's quite cheap. So you should very much do it. You really shouldn't worry about cost, especially if you compare it to what this would cost if you hired an SEO agency. The reason I say it's so cheap is like, it's not each run in this loop. It's happening once a month, for example. I wouldn't be shocked if this like, cost you less than five dollars in tokens to basically go and run this one time right now. Like, well, I just ran it in the background. So each of these runs, they're not that deep.

• 27:38Speaker 01

  It's not that it's in like, sort of an AI getting itself into an infinite loop. It sort of is, but like, it's infinite over time. Meaning it will run once every month for the next two years or five years. Honestly, for me, I'd be happy for it to just keep going, do that once a month thing. You might even want to sort of,

• 27:59Speaker 01

  you might want to have the AI update you in between. This is something else I do myself. Every time one of these runs, I need to know it's running. So I'll get it to ping me on Slack, basically, whenever it's done a run. And then I can look over things and I can sort of give a quick approval if I like it or don't like it. And so I'm very happy to get these like, once a month updates for things we can improve in our SEO. And yeah, the overall cost is gonna be small. The other thing I mentioned that Mike didn't is that If you're on a max plan, you are getting tens of thousands of dollars per month in your like your $100 or $200 per month subscription. If you're really tight on budget and on a $20 plan, then yeah, you like you need to be much more wary of tokens.

• 28:44Speaker 01

  And I think about like using open source models that are cheaper for this sort of thing, like GLM 5.2 type thing. But if you're lucky enough to be on sort of $100 or $200 per month max plan, you really you've got thousands and thousands of tokens there. And so I wouldn't be worrying about cost for something like this. It should be fairly cheap, honestly.

• 29:04Greg Isenberg?

  Cool. All right. So we looked at SEO loops. What are other loops that people could be thinking about?

• 29:11Speaker 01

  Yeah. So another really good one would be a Facebook ad loop. So you're running you're running ads on Facebook, maybe even the AI is generating its own ads. And it's just it's looking at the data. It's put out like an experiment with three different variants. It sees, you know, variant A is doing super well, and so it pushes more in that direction. And so this is exactly what you'd be doing if you're hiring an ads agency as well. They're going to be experimenting with lots of different copy, lots of different, you know, graphics and, you know, images or videos and so on. And so you could run the same thing basically with an AI. Where this might get a little bit challenging is that

• 29:51Speaker 01

  the content that gets created by the AI, it's not always going to be amazing. If you're doing video content generation with AI or graphics being generated with AI, it won't necessarily, you know, be as good as what a human can put together. I'm sure there are some very good AI generated ads running by right now, but I if I had to guess, the human generated ads are running better. But things like changing the line of copy, for example, that is very easy for an AI to go and change. And then, yeah, see how it's performed and then improve on it. Or if we're talking about Google Ads where, you know, you don't have images necessarily, you're just trying to rank on Google search ads. The AI can very easily change the copy, basically.

• 30:37Greg Isenberg?

  Yeah, or, you know, it's funny because like the humans are becoming the API layer in the sense of like, create a folder and every day have like, create a new ad where you're yapping for 30 seconds and then let AI kind of edit it. And let AI go into that folder and edit it from there versus going and creating a fully AI ad. Less context, less human layer, you know, I think. My belief is the best ads are actually, I mean, if you have millions of dollars to spend, yes, the best ads are hiring the best humans on the planet to go and do that. But not everyone has millions of dollars to spend or hundreds of thousands of dollars to spend on the best agent, you know, ad agencies on the planet.

• 31:22Greg Isenberg?

  We're not making Super Bowl ads here. So the way to do it is a mix of humans plus AI to get you to a really, really quality level. And I just think that, yeah, if you just integrate this into your ads loop, you kind of get the best of both worlds. You're getting the human feeling of an ad, but you're getting the AI optimization around it. And the game around Facebook ads in general is a game of volume, you know, people forgot this, but you know, it's really this game around a bunch of different narratives and hooks. And seeing which one works.

• 32:05Greg Isenberg?

  So it's basically taking your one product, but trying different angles and hooks and different types of, you know, people, a female, a male, an older person, a younger person. And then seeing how the algorithm reacts to it and then cutting the losers, doubling down on the winners. And I could see how this loop could optimize this.

• 32:26Speaker 01

  Yeah, exactly. And frankly, like we are, we are doing this loop regardless, whether you're doing it yourself or the AI is doing it. Like you might even have like a thing in to do it. It's like, I often put schedules in to do it. It's like, every three days, remind me to look at this thing. You're basically doing that exact same thing with AI. Like go look at Facebook ads in three days from now. You don't need to be on top. Of it every hour of the day, you know, every day or two, you do you need to look back at what just happened and try different angles. And so, you know, if you want to try a thousand angles as a human, that's difficult. As an AI, it's pretty easy to do to just, you know, try as many variants as possible. Obviously, budget plays an impact, plays a part of it as well. You need to give enough budget to each variant to sort of make a like a decision as to whether it worked or not.

• 33:11Greg Isenberg?

  Ellie, do you have time to show one more loop?

• 33:13Speaker 01

  Yeah, um, like the ultimate loop, which is sort of interesting, like product feedback loop, like, like if you actually wanted to have like your entire like business run on AI, like just like, you know, an AI that builds itself and also gets feedback from users and then builds itself, that would be something like that. Yeah, maybe.

• 33:31Greg Isenberg?

  That's really cool. So what you're saying here, I'm just looking at this. So this is really cool. This is basically, you have an AI agent that's reading customer feedback, that's looking at your analytics, like your post hog, looking at your logs, your sentry. And based on that, it's prioritizing, it's finding out the biggest pain points, it's learning, and it's prototyping, features, fixing bugs. And then it looks at the actual, you know, I don't know if it's DAU or revenue, like I guess.

• 34:02Speaker 01

  I mean, you could decide, yeah.

• 34:04Greg Isenberg?

  You can decide. Um, you know, sometimes it's NPS, sometimes it's, um, you know, retention. So sometimes it's virality. So you can decide, or you can even let the agent decide. Basically say like, for each feature, pick the best, uh, possible KPI, and maybe you have to approve it. But, um, you know, I think that could also make sense because there's certain features. Um, actually, the way I would think about this, Ellie, and, and tell me if I'm wrong here, I would actually do a bug loop separate from a feature loop. So the bug loop would be around.

• 34:47Speaker 01

  Yeah.

• 34:49Greg Isenberg?

  Like uptime, you know, like the, the, the objective metric would be more around uptime and, and things like that. But the product feedback loop might be around core metrics like DAU over MAU or retention or virality, stuff like that.

• 35:05Speaker 01

  Yeah, for sure. Yeah, I think that would be a great way to look at things. Um, yeah, there, this, this loop is sort of, I, it's almost like sort of the ultimate loop. It's the, yeah, the loop, maybe the, the lean startup loop, but everything you would do to run a business is like, how can we give as much information back to the AI to sort of build itself? I think this would be like sort of a true Pulsar, like a, a true company builder, where it's like the idea and everything is like on the agent itself. I think this would be risky to do on a real business, but I'm sure we're going to see a lot of companies come out which try and do something along these lines. You just throw in a line like, hey, go build me a business in, you know, that helps real estate agents. It starts building something and, you know,

• 35:47Speaker 01

  if, if it had access to enough tools to market itself to get feedback from users, you know, and that feedback might just be in the analytics or in the database or, um, you know, whatever it has access to, that, that would sort of be, be the ultimate loop. And I'm sure we'll start to see some really good businesses built like this in the next year. I've, I've even seen like early experiments of it happening right now. I assume none are doing incredibly well, but yeah, like this does feel like the future, like anything that can be done at a computer and AI can do so, you know, why can't it like even, why can't it decide on its own features and, you know, experiment? And yeah, adjust its product over time, the same way humans do.

• 36:25Greg Isenberg?

  Okay. So we've done, you know, product feedback loop, the holy grail loop. We've done the ads loop. We've done the SEO loop, you know, just take us home, Ellie, you know, what are other types of loops that we can, we can use this for? Um, is the sky the limit?

• 36:43Speaker 01

  Yeah, I think so. I mean, there are limitations to AI, but it does feel like every part of your business you could potentially set on a loop. You as sort of the founder of your business, you wake up every day. You know, you've got your schedule, the alarm clock goes off. You are that agent starting your loop. You're thinking today, how can I improve my business? It's the same for the AI. How can we get it to sort of be in that same mode? You might be doing social media, video content, cold outreach, whatever it's support. All of these things that you're doing and you know, checking every few hours or improving it and looking at some objective metric, for example, on social media. How many likes did I get? How many impressions did I get? You know, how many conversions did I get?

• 37:24Speaker 01

  You that all of that could theoretically be fed into the AI to help it improve and iterate on itself, learn from it and do better next time. You know, there are definitely things here which it won't do incredibly well. I'd be skeptical that you could get an AI to get to like a hundred thousand Twitter followers. But you know, there are a lot of parts of the business where I'm certain it can have massive impact. And you know, you don't really lose anything for trying.

• 37:49Greg Isenberg?

  Well, yeah, I think to me like,

• 37:53Greg Isenberg?

  you know, I wouldn't give it a loop around go find a hundred thousand X followers. You know, you kind of want to start with a smaller loop, right? Like the minimal viable loop, the MVL in the sense of first start by just creating incredible posts.

• 38:11Speaker 01

  Yeah.

• 38:12Greg Isenberg?

  And and just optimize around the posts. And and maybe the verifiable outcome isn't a hundred thousand followers, but it's 10 likes.

• 38:29Speaker 01

  Yeah, no, I agree a hundred percent. The outcome should not be a hundred thousand followers. I think even for me, it would be.

• 38:37Speaker 01

  I mean, impressions you're getting on a post, for example, would be what like likes, impressions, something like that, like, yeah, every piece of content you put out, how well is it performing? Obviously, the number of followers should go up over time. It's difficult to go backwards. But like, how many views are we getting on average per week? That's sort of the metric I'd be trying to push up. And it's the same thing I do for myself. You know, I put out 10 tweets this week. Nine of them didn't do very well. One did do well. Why did that one do well? How can I do it better next time? And you're obviously great at this. You have a much larger social following. And you know, you must be doing the exact same thing. There's like, could we get an AI to sort of run that same process itself?

• 39:21Greg Isenberg?

  Ellie, thank you for coming on for explaining loops, for opening our eyes, for sharing examples. I'll include links for where to follow Ellie on social media in the description, in the show notes. And Ellie, thanks again for coming on, being generous with their sauce, and I'll see you see you next time.

• 39:41Speaker 01

  Yeah, it's been great speaking. Thank you.