How Loops Will Make You Way More Money

**Eric Siu** (0:00)
Everybody is talking about how loops are the next big thing when it comes to AI. For example, you have the founder of Claude Code saying it.

**SPEAKER_2** (0:06)
The thing that I've been finding myself using more and more is loop, just like the coolest thing. It's like the simplest thing that works.

**Eric Siu** (0:12)
And you also have the founder of OpenClaude saying it. So let's go into what that is exactly. And more specifically, let's go into how this will make more money for you, how this will make more money for your business. So let's take a look. First and foremost, the receipts are here. If you look at Boris here, he's the founder or creator of Claude Code, and he has said, I don't prompt Claude anymore. What I mostly use now is loops. There's that word loops. I create loops, they do the rest of the job. In 24 minutes, Boris reveals his real daily Claude Code setup, and then Claude plus loops plus routines plus dynamic workflows. So that's one proof point, okay? And then you have Peter Steinberger, who said this recently, by the way, this has 7.6 million views on it, okay? So this exploded. And here's your monthly reminder that you shouldn't be prompting coding agents anymore. You should be designing loops that prompt your agent. So what the heck does this mean exactly? So what I did is, so I have this guy that I know, Matt Van Horn, he wrote a post that got 2.8 million views. And so between these, we're talking millions and millions of views, right? And Matt here, I'm actually, by the way, if you check my channel on YouTube, I'm actually doing a live stream with him. So you should check that out where we actually go into a little more detail. But I'm talking about this in the context of making more money and driving more revenue for your business because that's ultimately what I care about. And that's what my company does. So that's what we're talking about, right? So I think he wrote some really good things here around what is a loop actually. And so it's pretty detailed. But I think the thing to call out here is that when you think about a loop, there's a lot of different people responding as to what that is, right? Is it a Ralph loop? Is it just like a slash goal command? What is it exactly? And so what Mac did here was that he ran the last 30 days. That's a skill that you can run to see what everyone was fighting about because nobody has a clear definition right now. And I think he did a really good job with his article here. So here's the month of reminders that this one got the 7.6 million views and then nobody knows by him and Boris, right? Somebody, Matthew Berman, who's another creator, said this. What a loop actually is, okay, if you look at the plain version, a loop is a small program that you write that prompts the coding agent for you. It reads what it produced, decides whether it is done, and if not prompts it again. You stop being the thing inside the loop typing prompts. You become the author of the loop.
The model becomes a subroutine.
He says, in the last 30 days, this is December 2025, 100% of my contributions to Claude Code were written by Claude Code. I landed 259 PR. Then he said he deleted his IDE.
In November, he hasn't opened it since.
I think the thing to call out here is, people are just like, oh, it's just a rebranded version of a cron job, as to what this loop actually means. What Matt's saying here is that a loop is actually an evolution of a cron job. People are saying, oh, well, isn't this just an evolution of the Ralph loop or the slash goal command? And it is. And so maybe this is perhaps the step before recursive self-improvement, where the agent improves itself over time. And so the way I think about this is a loop is, like, for example, I run my Hermes agent and I have a bunch of different slack threads open with it. And oftentimes I have to come back and I have to prompt it, right? Or with my Codex, for example, my Claude Code, I have to prompt it.
I have to be the human in the loop that's constantly reviewing all the time. But the idea with the loop is that it's just going to keep working on it over and over. And people say that slash goal can do it, like slash goal to an extent can do it now that it's been updated. But the Ralph loop back then a couple of months ago couldn't exactly do that, like it could work for a little longer. But at least for me, I didn't see it working through the night, right? And so slash goal command can actually do that. And slash loop is kind of the evolution of that, right? And so Boris posted five tips for running Opus autonomously for hours or days. And so that's what we all want, right? We want this to continue to move for us. And so five tips, in his words, use auto mode for permission, so Claude doesn't ask for approval. This is if you're using Claude. Use dynamic workflows to have Claude orchestrate hundreds or thousands of agents to get a task done. I don't think you usually need to use dynamic workflows. Also, it's very token intensive as well. And then use slash goal or loop slash loop to nudge Claude to keep going until it's done. Use Claude code in the cloud so you can close your laptop and make sure Claude has a way to self-verify its work end to end, okay? So that's what we're looking for, right? Tip five is the one that hype skips and the practitioners obsess over. You want a loop that's trustworthy and it has the ability to check its own work. And so if we move on here, the loop is now the expensive part. So here's where the research turned from velocity to a finance problem. So the sharpest deflation of the whole agent's mythology came from a working engineer. So every AI agent I shipped this year is a for loop, an LLM call and a try catch around the JSON parsing. The only thing agentic about is the entropic bill at the end of the month. So again, this is very token intensive, right? And so when I start to think about this from a business standpoint, I'm going to give you a couple of examples here. Okay. By the way, if you want to grow faster, you need to have a single brain, unified intelligence sitting inside of your chat. So it could be inside of Slack or Teams, but you can see right here, this bot's working and it's creating ad creatives. It is doing data pulls from Meta, from Google. You can pull your SEO data. So imagine having all these data connectors. You can ask whatever question you want, get the data pulls a lot faster. If your team can see it as well, they can choose to execute and then you can run other specialist agents that you have inside. So we have ad creative agents. We have email infrastructure agents. There's all these agents that can do a bunch of things. And the whole idea is they're all playing together. They're playing with your team as well. That way you're going to be able to just move a lot faster and then grow a lot faster. So check it out. Just go to singlebrainwithab.com, singlebrain.com. We'll see you inside. So a couple of examples when it comes to business here is you think about, let's say you have a stale deal, for example, okay? So you might have a stale deal. Then you can summarize the context, right? This is talking about in the context of sales. So you have a stale deal, okay? It's not going anywhere right now.