7 INSANE loops you need to try right now

Loops are emerging as the single biggest unlock for people building software with artificial intelligence right now. But most people don't even know what loops are. And so today, I'm going to tell you what loops are. I'm going to show you why they're valuable. And then I'm actually going to give you many specific use cases that you can use loops for today. So what is a loop? A loop is a way to allow your AI coding agent to work autonomously towards a specified goal. The most important thing about loops is that it removes humans that allows the agent to work much more quickly towards this defined goal. And if it sounds very theoretical, I am going to break it down. So what is a loop more specifically? Well, you need two things. You need a trigger and you need a goal. With those two things, you can complete the loop. A trigger is what kicks off the loop. And there are three ways to kick off a loop. One, you can do so manually. You literally tell the agent, go do this loop. Two is schedule. You can schedule a loop to happen at a certain time of day or on a repeating schedule. And then three, you have actions. You can have the loop kick off based on some kind of action like opening a PR. Now to fully remove the human, we wouldn't want to kick everything off manually, but sometimes it is required. All right? And for the goal, the goal can be basically one of two things. It can be verifiable or we can use LLM as a judge. So if it's verifiable, it is something concrete, some specific number or some way to test it deterministically. If it is LLM as a judge, that means we're giving the model the ability to determine when it has reached the goal. Let me give you two examples. So for verifiable 100% test coverage in our codebase as an example, that is something that we know for sure and we have a nice way to test against when it is true. And for LLM as a judge, one example would be refactor until satisfied. And the satisfaction just means you as the LLM get to determine when we are satisfactorily refactored enough. All right, enough of the theoretical. Let me actually show you some examples. So, a lot of people talk about loops, but they don't actually give concrete use cases. And I wanted to fix this. That is why I am launching the loop library. It is a free library. I'm basically taking all the loops that I use and the ones that I see other people use and putting them in a single place so you can see them. You can be inspired by them to create your own loops or you can simply copy them straight from here. It's free. I'm going to drop the link down below. So, let's go over it. This is definitely my favorite loop and it's going to show you exactly how loops work. This is the sub50ms page load loop. Let me click into it. And here we are. So the objective of this loop is to get every single page load in my app under 50 milliseconds. And so that is the goal. It is a very concrete well-defined goal which really makes building a loop easier. So what I tell it is continue optimizing the code for speed. After each significant change, measure page load performance across every page under the same repeatable test conditions. continue until that's the loop continue until every page loads in under 50 milliseconds. So it is literally going to go through my entire application, every window, every page, every modal, load it. If it's above 50 milliseconds, it's going to continuously optimize it until it gets it under 50 milliseconds. Once it's done with one, it moves on to the next. That's the loop. That's the goal. But how do I actually do that? How do I actually kick it off? Well, the trigger in this case is me. I am the human and I'm going to manually kick off this loop. You can certainly set it on a schedule and you can even trigger it on, let's say, a PR open. So, every time you open a new PR, you also want to make sure that that new PR doesn't make the page load over 50 milliseconds. So, let's kick it off. So, we're going to click copy right here. All you have to do is paste it in. So I have the prompt right there. And then at the end or at the beginning, it doesn't matter. Type slashgoal. And this is a feature in codeex. Claude code also has a /goal feature. But as soon as you have this slashgoal, it's telling codeex to continue working until the condition is met. The condition of every page loads under 50 milliseconds. That's it. You just hit go. And it might run for 10 minutes. It might run for 10 hours. it will just continue to run until it meets the goal. And so you do have to keep a close eye on it if you're under a token budget constraint. So here it is in action. I sent this as a goal. Look for more optimizations to make sure every page loads in under 50 milliseconds on production. It worked for nearly 50 minutes. So I'm treating this as a production performance goal. I'll first measure the real team's page request path. And it basically, as you can see here, went through every single page and optimized it to load under 50 milliseconds. Loops are the frontier of AI workloads. And if you want to power them reliably and at production scale, use the sponsor of today's video, Digital Ocean. If you're running production inference, you're probably running into some of these problems. Your inference stack is too complex to operate. costs are unpredictable and I'm spending more time managing the infrastructure than actually building the things to be on the infrastructure. And most teams find out the hard way that the hard part of building AI applications is not using the model. It's actually everything around the model. The operational overhead, the fine-tuning inference complexity, the costs that become harder to predict as you scale. And that's why I want to tell you about Digital Ocean, the partner of this video. Digital Ocean is designed to minimize the total cost of ownership by giving teams a simpler path to production AI. They provide infrastructure that is optimized for inference and a vertically integrated core cloud that provides efficiency at scale. Vertically integrated is the key word. And with transparent usage based pricing that makes costs easy to predict. So, if you want to spend less time managing your infrastructure and actually building the thing you're excited about, Digital Ocean is the way to go. So, go check it out. They've been a fantastic partner. I've actually been using Digital Ocean for well over a decade at previous companies, so I can vouch for them. Go check them out. Link down below. Now, back to the video. Here's another loop that I really like. This is called the overnight docs sweep. Each night, review the codebase in full and make sure all documentation reflects the latest changes from the previous day. update the documentation as needed, then open a poll request with those changes. So, what I am doing is I'm making sure we have complete documentation based on any changes we may have made. This is an example of LLM as a judge. There's no verifiable way to know if we have complete documentation coverage. There may be some ways that we can say, okay, as long as a piece of documentation covers this section of the code, but ultimately what we're doing is saying, okay, LLM, you decide. So, how do we actually use this? Well, once again, just hit the copy button. We're going to come into codeex. We're going to click this automations tab. We're going to create via chat. We're going to delete this portion. I don't know why they put that in there, but I want to set up an automation. Then, we paste in what we just copied, and then each night review the codebase in full. hit go and let it run and hopefully it will set up an automation just like this. So there we go. I'll set this up as a recurring automation. So first I'm loading the automation tool rather than writing a one-off note. Perfect. So this is a way to keep your documentation always up to date. It is awesome. And by the way, I created this website with here.now. So shout out to here.now the partner on the loop library. I created it and I simply said deploy to here. Now and it was done. It's so easy. Next is the architecture satisfaction loop. This is one that Peter Steinberger himself says he uses often. Here we go. Refactor until you are happy with the architecture. Here is the trigger and the goal all in one sentence. Refactor, which is what the loop is going to do, until you are happy with the architecture. Happy with the architecture is the goal. This is another example of LLM as a judge. We can even give it more guidance on what happy with the architecture means. We can say be very strict about simplicity or make sure every single line of code is dry. Then after each significant step, live test the system, run auto review and commit. Track progress in and then we give it a markdown file to track the progress. This is fantastic. So it's tracking its loop as it's actually looping. Now you can kick this off manually or you can run it every night. So let's say during the day you're deploying a bunch of code and then every night you're just making sure that it's refactored, it's dry, and it looks really solid. So very good way to keep your codebase very clean. Next, another one of my favorites, the logging coverage loop. So let's click into it. Basically, what this loop is going to do is make sure that we have thorough logging throughout our app. And there's another loop that builds off of this that I'm going to show you in a minute, which these two loops together, you can start to see how loops can become so powerful. So, this says, "Review the systems logging and add missing coverage until every important path produces useful tested logs." And again, this just makes sure that we have logging for everything. And this is going to be manually kicked off. And this is going to be LLM as a judge because it says every important path and important is non-deterministic. It just means the LLM gets to decide what's important and what isn't. And by the way, if you want hands-on help with loops and other AI topics at your company, my team is offering free consulting sessions. I'm going to drop a link down below. We're only doing a few of these, so go apply if you're interested. Would love to talk to you. All right, so now imagine this. You have full logging coverage, but what do you actually do with those logs? Well, I have another loop for you. This is called the production error sweep. Every single night, we're going to review our production logs for errors. If you find an actionable issue, trace it to its root cause, fix it, verify the fix, and open a pull request. Then, ping me in Slack with the findings and PR link. If no actionable errors are present, ping me with that result instead. So we are kicking off a loop every night and the loop is looking for every error in the logs and we'll fix them one by one with the end goal being no more unressed errors in the logs. So that is a very concrete goal for this loop. All right, here's another loop. Something incredibly important to any website owner, any app owner is SEO. And not only SEO, now GEO. So, here's the SEO GEO visibility loop. Run an SEO GEO audit across crawlability, indexation, page intent, titles, internal links, structured data, source citations, and answer first content. Rank the gaps. I'm not going to read the whole thing. Fix the highest leverage issues. Rerun the same crawl. And here's the loop. Repeat until no critical technical issues remain. Again, you might have one issue. you might have 50 issues. The point is we've now kicked off a loop that fixes all of them until no more issues are present. So, this is a really cool one to run, let's say, once a week. All right, here's one of my favorite and one of the most handwavy loops that I have, but listen to this. This is called the full product evaluation loop. Create n realistic scenarios covering every major capability. Before testing, define clear success criteria and choose a consistent evaluation method such as past fail checks or a scoring rubric. Run every scenario under the same conditions and record evidence for each outcome. Fix the underlying cause of anything that that does not meet the criteria. Rerun the affected scenarios and then rerun the complete test. Continue until every scenario meets the original quality bar. Now, a lot of you might be thinking, "Wow, that just sounds like tests, right? It's just like a test suite. Well, kind of. But this is actually non-deterministic. This is allowing the model to go through every single use case in your application, in your product, figure out if it's good enough, determined by the LLM, and update it if necessary. This one really does work. It takes like 12 hours at times or more, but it really does come up with very good optimizations. Now, you can also customize this for your specific app. So, for example, I'm building something right now that requires me asking a question of an LLM and it providing a really accurate response with sources. So, I tell it, come up with 100 different use cases, wide ranging use cases for asking the LLM questions and judge whether the response is good enough. If it's not, iterate and improve it. So, I could keep going, but if you want to find all of the loops and any new ones that I discover, go check out the loop library. I'm going to drop a link down below. And once again, shout out to here. Now for hosting the loop library. Okay, so there are two major caveats with loops that I have to tell you about. Number one is it's not for every problem yet. Designing a loop isn't always easy. Specifically, coming up with the goal for the loop is not easy. If something can be verified like every page loads under 50 seconds, that is perfect for a loop. When we have to have the AI judge, LLM is a judge whether a goal is met or not. That's when it becomes a little more brittle because we are leaving taste and judgment up to the model. This becomes even more difficult when we're talking about building features. I have not really found a way to build features with loops. You cannot say loop until we build a full permissioning system. I mean, you technically can, but I'm not doing it because I don't know which direction the AI is going to go. I don't know what features it's going to build. I don't know when or how it's going to decide which features are worthwhile versus which are not. So, that makes it not great from day zero feature building. Now, one example of building a product from scratch using a loop is something I did where I told the model as a goal to clone Excel feature parody and it was running for days and days and days until I finally stopped it. It actually opened up Excel on my computer, used computer use, and literally clicked through and made sure that it had feature par. And yes, it was running for days before I finally stopped it. So, I do not recommend doing that. And that brings me to the second big caveat. Loops are very expensive. They are churning through tokens autonomously until they hit the goal. Some of these agents might run for 10 minutes. Some of them can run for days. So, for you token maxers out there, loops are fantastic. But for those of you who don't have an unlimited token budget, this might not work for you today. And by the way, if you like coding with loops, you might also like these four open- source projects that I reviewed that you can use right