AI Software Factories Are the Next Big Thing (And I'm Building You One)

0:00 The AI software factory or what I've been calling the dark factory on my channel this year is the ultimate evolution of AI coding. A PRD goes into the system and you get shipped code out.

0:11 Right? You create your higher level planning document. You give that to the system to split into individual tasks. It goes through building all of them, reviewing the poll requests, merging

0:20 things, and getting everything deployed straight to production without a human looking at the code. Now, you might be thinking, there is no way that could ever be reliable enough, especially if

0:29 you're more of a skeptic for coding agents in general. And I get that, but I've been hearing about companies left and right now that are legitimately implementing this kind of system for at

0:38 least part of the development in their organization. I've even helped a few businesses build out an AI factory system. Cuz here's the thing, coding agents as our harness, large language

0:49 models, and our larger workflows are all getting better in parallel. And so having this kind of system, it is becoming realistic. I know that might seem like a hot take for some of you,

0:59 but I think it is legitimately productive now for any business to incorporate some kind of AI software factory, at least for prototyping things quickly and spiking product ideas. And

1:09 let me tell you, I am betting big on this. The next big thing that I'm going to be pouring a ton of time into and focusing on with my YouTube channel is building out an open-source AI software

1:20 factory. something that you can download and use immediately to start building anything. And I know this is a big goal. I'm just getting started on this here. But I truly believe that the future of

1:31 building software in general is getting to this level of autonomy. And so that's what I want to cover in this video. I want to talk about what a software factory really is, how I've gotten here,

1:40 my own experimentation I've done this year, and I want to talk about what's next for this project. And hey, if you've never really followed my channel before, you've just checked out a couple

1:48 of videos, this might be the time to jump in. It is going to be a fun journey. I'm going to go on here with the software factory. And don't worry, I'm not some delusional freak that

1:57 thinks that AI is going to replace all engineering in a year. I just think that the software factory is legitimately going to become a big tool in the tool belt of most companies within the next

2:07 few years, and we get to lead the charge together. And just one more piece of food for thought here. Another reason I really want to get invested into building a software factory is this

2:17 forces me to make AI coding assistants as reliable as possible. If I take myself out of the loop, I can't catch the small mistakes my agent is making. And so I'm just making myself a better

2:29 agentic engineer when I push things to the limits like this. So if you follow along with me, you're going to be taking all the lessons I get from doing this as well. So, an AI software factory can

2:39 also be called a dark factory. They're pretty much the same thing. In fact, I used to call it more the dark factory just because that's what Dan Shapiro calls it in the blog post he put out at

2:48 the start of the year. This is what really got me interested in the idea. He covers the five levels of AI coding. Basically, the different levels of autonomy we give our coding agent. I've

2:58 covered this on my channel a couple times before. I'll probably keep referencing it a lot as well. You could turn this into a drinking game. like take a shot every time Cole shows Dan

3:06 Shapiro's blog post. But I love this because it uses the analogy of driving a vehicle to help us understand the different levels of AI coding autonomy. So starting with you pretty much still

3:15 all write all the code yourself. You're using AI for a little bit of assistance down to level three which is mostly what I teach where you want the most reliability possible. You have the

3:25 coding agent writing all the code but you're very involved in the planning and validation for every individual issue or ticket. But [snorts] then we get down to level five. So we have a console here.

3:36 We still get to drive the vehicle with the higher level directions, but there's no steering wheel anymore. All of the smaller decisions are made completely by the agent at this point. We send in our

3:46 planning document and we get shipped code out. And that is the dream for anybody as long as it's reliable enough. Now, this big question, is the dark factory reliable enough? Is something I

3:56 started an experiment on earlier this year to figure out. So, I built a full dark factory that I documented building on my YouTube channel through live streams like this one and a lot of

4:06 YouTube videos. And I created a full application with it. I call this Dino Chat, my AI tutor. It's an agentic chat application that has full access to my YouTube channel. And then if you're in

4:16 the Dynamis community, you can also search through my course and workshop content as well. So, you ask it any question and then it's grounded in everything that I teach on the internet.

4:25 It's pretty cool. So, it's not the most complicated application, but the important thing is I built this end to end with my dark factory. I never wrote or even looked at a single line of code

4:35 for this application. I'll have a link to this in the description. You can literally try this out right now. It's a live production application that I didn't build a single piece of myself.

4:43 So, I would say overall that this experiment was a success. But the thing is, this isn't a very critical application. It's not extremely complicated. I would say I didn't really

4:53 truly test the reliability of Dark Factories. And that is what I'm going to be doing next. And this initial experiment that I did, I even gave you a skill to help you build your own version

5:03 of it. So I'll link to a video right here where I covered that within my main skills GitHub repository. I have build dark factory. So it'll walk you through creating from scratch the exact system

5:14 that I used myself. And so that's a cool starting point. But this is where I have to kind of just be transparent with you and share a little bit of a change in my philosophy for how I teach and bring

5:25 tools to you. The sponsor of today's video is Data Impulse, the platform for pay as you go proxies for all your scraping needs for your agents and beyond. I'm building agents that involve

5:35 scraping all the time. In fact, I have one Midflight right now that's e-commerce related. I have a very simplified example of that scraper right here. So, I'm pulling product

5:44 information, but the problem is I'm using a single IP address. I'm not using a proxy. And so what happens is you start to get rate limited or outright blocked. This is the first wall you'll

5:55 hit with any scraping you do beyond just a handful of requests. And Data Impulse is the solution to that problem. They have their own residential network with 90 million plus IPs for you to use for

6:07 your proxy. And it's across 195 countries. Plus, there's no reselling. So all the IP addresses that you use here are going to be fast and reliable. So going back to my simplified demo

6:18 here, I'm running the same scraper, but this time routing all my traffic through data impulse. And so instead of it just going through the same IP address every single time, you can see that now we are

6:28 using different IPs and I'm not getting rate limited at all. And all the traffic that I'm generating with my scraper, I have the dashboard here where I can see the individual requests and all the

6:36 metrics over time. And I promise I won't get too in the weeds, but just to show you the code really quickly, all I have to do is use the same scraper with their proxy URL. There are no other changes to

6:46 the code and now all the requests come back from a different residential IP. So it just seems like a bunch of different people are interacting with the site from their homes. The whole thing runs

6:55 on $1 for every 1 GBTE. Pay as you go and nothing expires. And I can even hold a sticky session if I have to use the same IP address across a couple different requests. Data Impulse is the

7:05 proxy solution for any kind of scraping solution that you're building like rag agents, price tracking apps, whatever it is. I'll have a link to them in the description. So, I hope you don't mind.

7:15 I'm just going to get vulnerable for a little bit here. So, for the lifetime of my YouTube channel, I've always had the philosophy, I want to teach you how to build something yourself instead of just

7:24 giving it to you, right? Like teaching someone how to fish instead of just giving them the fish. And I know a lot of you appreciate that with my content. So, I'm not going to ditch that. But

7:33 now, I'm rethinking things. I I want at least some of my content to be I'm actually going to just give you the tool to run right out of the box. It's like before it was always like here I'll give

7:41 you the skill to help you build your dark factory or I'll teach you how to build your own second brain from scratch. But I got to be honest, I've always wanted to have an open source

7:50 project like OpenClaw with almost 400,000 stars or Hermes Agent with 240,000 stars, Deep Sea Carnis that's already at 209,000 stars. Like, I've never had something go viral like this.

8:01 I mean, the closest I've gotten is with Archon, which fantastic tool. I'm still pouring a lot into this and it's it's great, but it's not a 200,000 star, 300,000 star project. And I think the

8:13 reason why none of my stuff has gone sort of viral like these other tools is because it's not something incredible out of the box. It requires you to build out your own process or to really create

8:22 something from scratch because it's always been my philosophy, like I said. But now [snorts] I I think it's my turn to build something that you can just use right away super easily and get a ton of

8:33 value with it. So, trust me, Archon is not going anywhere. My philosophy still stands most of the time, but I also get it. Like, sometimes you just want something that you can just download and

8:42 start using right away with barely any setup. And so, that is what I'm doing now with the new AI software factory. I'm taking everything I've learned from helping companies implement systems like

8:52 this, from my public experiment I've been covering on my channel, all the lessons that I've learned the hard way, and I'm building that now into a solution that you can just download and

9:01 use right away. So obviously it's quite opinionated how I like to build software what I've ingrained into this and I actually even have this running Archon workflows under the hood. So when you

9:11 install it, it installs Archon to drive all the processes that take your plans, turn it into written code that's deployed. And of course there'll be dials you can tweak to really customize

9:21 things and make it your own if you want if you subscribe to my usual philosophy. But the point is there is now the option where you can take this prompt at the top of the readme, send it into your

9:31 coding agent, it'll ask you a few questions and then it'll install everything and be immediately ready to accept any PRD and just build things end to end for you. Just working right out

9:42 of the box. That's not my usual thing, but that's what I've got here. And like I said earlier, I just started building this. And so the point of this video is not to give you a tutorial to set this

9:52 up and run it. It's not necessarily ready for that. I mean, if you want to start the alpha of the software factory, you can go ahead and try it right now. Send this prompt into your coding agent.

10:01 But more why I wanted to make this video is to show you what I'm working on and invite you on a journey to build a software factory. So, come along with me as I build this out as a better and

10:12 better resource for you. And we'll see together how reliable we can make this kind of system. I'm decently skeptical that we can use a factory to build anything. In fact, you might even be a

10:22 little bit more skeptical or less. I don't really know. The point is, we're going to try to find that bar. And I think we really can. Like, if you need a certain level of reliability, you still

10:30 want to be in the loop a lot more. But for certain kinds of tasks or things you're working on, you can just give it over to a software factory as long as we put enough effort building out the

10:40 harness, which is exactly what I'm going to be doing. And like I said at the start of the video, there's certain things that I already know you can use this for, like proof of concepts and

10:49 spiking product ideas. Like literally using your coding agent to just build out entire things to test ideas is realistic now, especially because of how cheap certain large language models are.

11:00 So you can be very coste effective and building out a ton of code just to try things out. And trust me, I have been spending an insane amount of time testing this software factory as I'm

11:11 building it out. So, I create a ton of different software factories from scratch, like the one you're looking at right here. And I do that over and over again as I iterate and just continue to

11:20 refine the main open source project that I'm sharing with you, cuz it's been a lot of work to take all the lessons from the initial experiment I did and the companies I've worked with and turn that

11:30 into the single open-source project. And so, I've been spending a lot of tokens building this out and we're just getting started now. At this point, I don't have one of these test repositories to share

11:40 with you yet, but that's one of the next big things I'm going to be working on. Obviously, as I build out the software factory as the main repo for you, I also need real applications I build alongside

11:51 it to prove the factory is working well. So, I'm going to be putting a lot of effort into that. I've been thinking a lot about the kinds of applications I want to build, too. So, the AIT tutor

12:00 application that you're looking at right here, what I built for the last experiment, this is great. It's practical. It's deployed right now. It's a great resource for you to use, but

12:08 when I really push the limit of software factories coming up here, I need something a lot more complicated. And so, honestly, this might sound kind of silly, but what I want to build is video

12:19 games. Video games are fantastic for testing complicated buildouts because applications like this, there's only so much you can do before it just becomes a feature-bated mess. But with video

12:31 games, it feels like there's always an opportunity to build in more features, do something more elaborate and more fun. I think it's going to be fantastic. So, I'm not going to do anything web-

12:42 based like this. I know that these might be a bit more practical for, you know, resources for my channel, but video games are fun for me. Like, I grew up playing video games. I still play them.

12:50 And I think it's just going to be a great way to push the limits of software factories. And so all that to say, I've got a lot of cool things coming up on my YouTube channel where I'll be building

12:59 out the software factory, making it better and better for you, showing you the different projects that I've been building with it, and of course teaching you all the lessons and best practices I

13:09 learned as I'm building out the harness underneath, talking about how I use Archon and those workflows to drive everything, best practices to make things more reliable. I do also already

13:18 have content on my channel for how to build a dark factory. So, I'll link to a video right here where I cover all of the concepts in this diagram. So, a lot of golden nuggets that I've covered

13:28 already, but I just want to keep hitting on this as I work harder and harder on the project here. And honestly, the most important thing to mention here is that everything that goes into building this

13:38 software factory is also going to teach me and you how to just use coding agents better in general. Because if we are taking the autonomy to this level, we better make things reliable. But that's

13:48 also going to help even if you're more in the loop. And so there is just a lot to get out of this journey and following along with me. And so if you appreciated this video and you're looking forward to

13:58 following along as I build the software factory and all the AI coding lessons from that, I would really appreciate a like and a subscribe. And with that, I will see you in the next