---
title: "Factory AI Can Build Any SaaS App in Minutes | Matan Grinberg Interview"
source_url: https://www.youtube.com/watch?v=8gKN29Ea-J8
captured_at: 2025-06-09
author: "The Next Wave - AI and the Future of Technology"
contributor: "ชิดชนก"
platform: youtube
---
# Factory AI Can Build Any SaaS App in Minutes | Matan Grinberg Interview

youtube video by **The Next Wave - AI and the Future of Technology**, 35m24s, uploaded 2025-05-28. URL: https://www.youtube.com/watch?v=8gKN29Ea-J8
Tags: Factory AI, Matan Grinberg AI, agentic software, AI SaaS builder, build SaaS with AI, The Next Wave podcast, Nathan Lands podcast, AI for software development, AI coding assistants, enterprise AI tools, AI agents for devs, DocuSign competitor AI, automated app development, AI for entrepreneurs, Factory AI demo, the next wave, tnw

## Shared in LINE Note+
- 2025-06-09 06:39 by ชิดชนก

## Description
*Want the ultimate guide to use Gemini's game-changing features? Get it here:* 🔗 

Episode 60: Can you really build an $8 billion SaaS startup by yourself using AI agents?

Nathan Lands ( sits down with Matan Grinberg ( a physicist, AI founder, and creator of Factory AI—one of Silicon Valley’s best-kept secrets. Matan has published papers alongside luminaries and built a company trusted by top VCs and tech insiders.
In this episode, Nathan and Matan dive deep into the power and practicality of Factory AI—an agentic software platform that allows anyone to build full-featured SaaS applications using only natural language. After years of focusing on large enterprise clients and remaining under the radar, Factory AI is now opening up to everyone and revealing what’s possible when state-of-the-art “droids” (purpose-built AI agents) collaborate to automate the entire software development lifecycle. Watch them attempt to build a DocuSign competitor in minutes live on the show, and explore how AI is changing the future of engineering, entrepreneurship, and creative problem-solving.

Check out The Next Wave Podcast if you’re on the go and want to listen to the show: 

—
Show Notes:
(00:00) 

## Transcript (captions:auto:en-orig)
Can you build an 8 billion startup by yourself using AI agents? Well, today we're going to find out. We have on Matan Grinberg, the founder of Factory.ai, one of the best kept secrets in Silicon Valley. With Factory.AI, you can actually build a real company just using natural language. Up until now, it's only been used by huge companies, but today they're releasing it to everyone and announcing it on this podcast. So, you guys are getting in on the ground floor. So, let's just jump right in. Matan, man. Thanks for uh coming on the show. Thank you for having me. I've been thinking for a while. I really wanted to get you on here because I've been hearing from friends in Silicon Valley for the last several months that, you know, basically factories like Devon but actually works. I mean, at least that's what they've been telling me, you know, and I've heard so much about Devon. You know, Devon like launched a little over a year ago. It was super hyped up in my opinion, overhyped. But then I was like wondering like, well, why haven't I heard about these guys? And then I saw this tweet yesterday. Okay, let me let me share this tweet real quick. Oh boy. Devon and friends are finally a product category. You know, we've been working on this problem for over a year now and many didn't believe it. Great to see that the world is realizing. And he kind of like lists out the category and he lists out two products that are brand new. Codeex from OpenAI and Jules from Google and Devon. And I thought it was kind of funny. He said Devon and friends. I would have thought, you know, Devon in factory, but he just left you guys out. And and then I looked into your website, you know, and you know, your approach seems more practical like instead of Devon seem to be kind of pitching, hey, we're going to replace all of your engineers, you seem to be more about like you're empowering, you know, engineering teams. So, I'm just you my question is, you know, why don't people know about you guys yet? We've been very heads down for kind of the first basically two years of our existence just working with enterprises um deploying factory to these enterprises improving the product from there and so that's why we've been a little less kind of outward but you know over over the next couple weeks we're at a point where it's pretty important for us to change that and you know be a lot more open get a lot more developers in the platform because we're at a point where we've found not only does the factory platform dramatically help enterprise engineers But we we kind of naturally see them start bringing factor to like their side projects or trying to sneak it into other avenues and it's really at the point where you know we feel the product is is mature enough to to start appealing to even more audiences than just the enterprise. That makes a lot of sense to me but maybe our listeners are like what's Devon cuz some people may not even know exactly what Devon is. Maybe like at a high level we should explain too like what is factory? Like what what do you guys do and why should people care? So we factory we are building droids. Okay. Robots. Robot. Yeah. Basically, so software robots that, you know, solve all the ugly tasks in the software development life cycle. And so, a lot of people, especially, you know, if they're not that familiar with engineering, might think engineering is just coding. But the reality is, especially at these large enterprises, developers don't just spend their time writing code, but they actually spend a majority of their time on all the stuff that goes in before the code and all the stuff that goes in after. And so that's like understanding and planning and PRDS and design docs. Um and then you get to the coding part and then after the code there's the review, the testing, the maintenance. Yeah. So we're kind of uh focused on the whole like end to end. So my understanding is you guys are doing general release now. So you've been you've been serving enterprise customers uh kind of silently building this for 2 years making great progress and a lot of head heads. I heard you guys even have been beating Devon often and so now that it's actually out there, maybe we can just like show people what it can do like so they'll actually, you know, we could talk forever, but if they actually just see it. Yeah, let's let's jump into it. Cool. So obviously, you know, the use cases that we do in the enterprise are, I guess, you know, obviously very valuable, but a little less visually pleasing. So I thought it could be fun to uh to build a little toy version of docyign within factory just to get a sense of how factory helps uh you know, agentically automate some development tasks. Cool. So, we're going to like build like a billion dollar company here today. Yeah. Yeah. Well, let's uh let's let's see what we can do. Who owns it? Do Am I like a 50-50 partner in this or like how does this how does this work? Yeah. Yeah. Fair enough. If you Hey, if you help guide the droids, then uh then then you get a stake. Um All right. So, here you can see uh we've landed on the factory dashboard. We have a chat interface. Um so, you know, pretty standard. Nothing too new here with LMS. We also have these four droids. And so, these are our agents. We call them droids because agent is kind of synonymous with poor quality, right? And for it's for, you know, different tasks that you might want to do. So, you know, the knowledge droid is maybe you're trying to create a design doc for some large engineering task that your org will be doing. Again, that's a little bit more enterprise angle. The code droid, this is really the kind of the one that everyone really wants to see, which is, you know, whether it's 0ero to one or end to plus one, having the ability to go into a codebase and kind of build endto-end features. There's the reliability droid which can integrate with tools like Sentry or Data Dog and if you have any outages, it can go in and you know create an RCA and even solve those issues. I like the approach with the droids because it seems like you have these like specialized droids that do a specific thing versus a lot of these you know AI agent companies whether you know I I'm friends with Yohay Nagima who did baby AGI and it was a great concept but a lot of these like that and and Devon they kind of promise they're going to do everything and then they kind of fail at almost everything. I I like that the fact that you guys have like specialized ones that do specific things. The name of the game with agents is you want them to be as reliable as possible. And so if you could have them focused on certain core competencies in their workflows, it makes that reliability a lot easier. And so I just hit enter on hey, let's build out a toy version of docyign from scratch. And so the code droid is now going in creating this plan. So you know here we have this general implementation plan project setup user user authentication document management potential challenges asking some clarifying questions. Now if I was going to be doing this a little more thoroughly and you know for production grade right now I might you know be a little more thoughtful in my responses but I defer to you let's just get a quick version up and running locally and then we can iterate from there. So, you know, it's asking me some very thorough questions like what tech sack, uh, which core features would you like this system to include authentication? These are good questions. I'm just saying, you know what, you you pick. Uh, I don't have time for this right now. So, uh, obviously in the enterprise setting, you're going to be much more picky about this when you're not going, you know, purely from scratch. But, you know, we can see its thinking process here as it's going in and starting. And so, now, uh, it's going to go and see here we have it running a command locally. So point here is that there are a lot of agents that run purely locally and so that's like a tool like claude code …