When robots recycle with Matanya Horowitz of AMP Robotics

Hello and welcome to how I built this lab. I'm Guy Raz. Right before the pandemic, I joined my son on a school field trip to a recycling center in the Bay Area here in California, and I was really surprised to see how it works. There was a giant conveyor belt of glass and plastic and paper all mixed up. And a row of people sorting it as fast as they could.

And while the workers were amazing and fast, There was a ton of stuff that was inevitably left behind. and not recycled. In the US, the EPA estimates that only a third of all waste actually gets recycled.

And one of the main reasons for this Well, most recycling facilities just aren't equipped to sort through all the materials they receive. My guest today, Matania Horowitz, launched Amp Robotics in 2014 to tackle this very problem. The company uses artificial intelligence and robots to sort through waste more efficiently, which means recycling facilities across the world are able to actually recycle more of the material they receive. Batania studied robotics at Caltech and it was there where he discovered deep learning. It's a method in artificial intelligence that enables computers to process data

Like the human brain. you could just start to see that machines were going to be able to see as well as a person for the first time in a very kind of fundamental and true way. And so even though that wasn't my focus area, I was like, Oh my gosh, this is gonna be massive. So I I started focusing on that. I started studying it. And after graduating, uh, I was looking for areas where I thought it could be useful'cause I was like, this might be the next mobile phone sort of uh wave. Um it could be the next internet. I don't know, but I just know it's gonna be a big deal.

Alright, so you're seeing um the the beginnings of what will and is already starting to revolutionize industry in the US and even consumer products. And You get your

your PhD from Caltech in twenty fourteen. And With obviously a lot of experience working in robotics um So you start to explore, hey, what could I do? What where can I actually make a contribution?

And of course we know you end up in in the sector of recycling, but but how did you come to that? So I I wish I had a story that was uh about me really being an expert in recycling, or maybe I saw a plastic bag blow across the road and it made me sad or something. But I um it was a very academic process. I I I said to myself, Okay You have a machine that could

C roughly as well as a person. What does that open up? Um There were different things in drones I was pretty interested in. I had an idea for a drone you'd kinda throw in the air and it would follow you and create kind of like a highlights reel you could throw it in the air or sniper. Yeah, you know, I I think somebody actually went ahead and did that, uh and I saw that you'd have to raise a lot of money.

For drones it seemed like it was getting very Crowded. Um, so this is around tw twenty thirteen, two thousand fourteen. Um I started researching a couple of different industries, but

I visited A recycling facility in Los Angeles. And If you've ever visited a recycling facility, you'll see that The main task is people standing around conveyor belts sorting through material by hand.

Yeah. You have people picking bottles, cans, cardboard, paper. It's a tough job. Uh doesn't smell great and the turnovers very high. People don't kinda put their their full heart into the job and so the material quality is lower than it needs to be.

And it was really clear that this is a An industry where Robotics. could really have an impact. I would talk to the recycling facility owners and managers.

And they would say, This industry absolutely needs robots. Um, I don't understand why we can't get robots and with a vision system and technology that could see roughly as well as a person now, you could bring that tool to this problem. Yeah. You know, I wanna just step back and and talk to you about

Recycling. Only about sixty percent of American households have access to like curbside recycling programs. Right. You know, for most of us. We just dump it all into one bin, you know, all recyclables. Or maybe you sort paper and then and then everything else. Cans, glass, bottles.

Um And then it gets dumped into a facility. I've been to one. I went to one in Berkeley, California a couple years ago, and was amazed because it is a conveyor belt and there are humans just sorting things out on the conveyor belt as it passes by and a lot of things just naturally don't get sort of or You know, like a a bottle gets

Tossed in with aluminum. I mean it's just gonna happen. And um these facilities are just super inefficient. And I was kinda surprised. Learning that Only about

thirty five percent of waste is recycled in the US. Even though much more of it is recyclable. Right. Right. Well

There's a couple of kind of core challenges to the industry that that you're hitting on. you know, one of the main one that we're making a big impact with is uh is technical. all this material you put in the recycling bin, it gets smashed, it gets folded, it's dirty, it's torn in different ways. And so you have this huge stream of material that is inconsistent. And that inconsistency makes it very hard to separate.

uh the core task of the industry is to separate out these different commodities. Yeah. You want to get all the number one plastics in one spot, the number two plastics. But if they're smashed up, if they're folded, they're m kind of mushed together. Exactly. And that core technical problem is what's made the industry so reliant on

On people. The second problem is really a a problem of incentives. If you can separate material out, is it gonna be worth separating out? Can you sell it for a profit? And because of the need for all of this manual labor, what you find is for a lot of materials.

uh it may not be profitable to actually recycle them. Which is unfortunate because what you find is the vast majority of materials can be reused or recycled in some way. But for many of them, you know, the two thirds of material that that isn't getting recycled today. that incentive isn't very strong. Uh and so you it's hard to build a business. In other words, it's not strong because the cost of the

particularly the labor cost All the stuff is sometimes higher than the price you get. Yes. For selling recycled materials, right? Yeah. Well and to give you a couple of figures that I think are helpful, um

Most of these materials they live in a commodity market. So you know, oil goes up and down, plastic goes up and down Um so sometimes you know, just by virtue of what the economy's doing, recycling becomes a better or worse business. Um

You know, setting aside any technology like like what we have. But Some rough figures here are that. the recyclables you put in your recycling bin, depending on that commodity market. are probably worth about a hundred dollars per ton. And that's real value. Like you can pull out that plastic and and sell it. Um

The trouble is is that the cost of running it through a recycling facility ends up being about a hundred dollars a ton. Depends on how modern the facility is and and these things, but you're kind of at this point where it's a little bit marginal. But what you can see is If with technology you can bring that cost of sorting down to fifty dollars a ton.

Or twenty dollars a ton. And also if you make it worthwhile to sort more materials, that a hundred dollars a ton of value can become more like one twenty or one forty. Uh either by purifying the material or being more specific about what you separate out. Yeah. And now recycling starts to become this phenomenal business. Wow. Now you've sort of incentivized

more recycling. So a significant amount of material is recycled, but but It's only about a third. Um and there's a lot that is thrown away. In particular

I think is problematic because not only as you mentioned, not only it does it it's it's price go up and down depending on the price of oil, sometimes it's just cheaper to make virgin plastic than it is to recycle it. But plastic also degrades after several uses like recycled plastic. over time becomes Toxic, essentially.

Well Yeah, there's a whole there's a whole bunch of different kind of issues around plastic, you know, the Um, you know, the one that I'm most focused on personally is uh sort of plastics of the ocean and how do you really keep all these plastics from getting there. Yeah. And it's an interesting story, but You know,

all of these challenges around plastic. The the real hard part about it is uh It's kinda matched with plastics being this wonderful material. Like it's it's so strong. It's uh weight. I can keep our food safe. And so You know As I see it.

The most important thing that you know, we can do is we make it so that the world tries to capture that plastic and get value out of it so that we can make sure it's properly handled and doesn't make it into our environment and into our you know food or you know whatever And what I get most excited about over the long term is If you make recycling this fundamentally better business.

you not only create a incentive to expand recycling in the US or in Europe, but If you can make it so that it There's a stronger incentive to recycle in the developing world. Now you really make a huge impact because uh It ends up a lot of these plastics in the ocean are kind of coming from developing nations where they don't have strong waste infrastructure.

That's the the depth we ultimately want to make. We're gonna take a short break, but when we come back, Matania explains how he got amp robotics off the ground. And why that involved some dumpster diving. Stay with us, I'm Guy Raz, and you're listening to How I Built This Lab. One more thing before we get back to the show, please make sure to click the follow button on your podcast app so you never miss a new episode of the show. It's usually just at the top of the app and it's totally free.

Welcome back to how I built this lab. I'm Guy Raz, and my guest today is Matania Horowitz, founder and CEO of AMP Robotics. Alright, so you are searching around for how you can be part of this new emerging Technology, AI combined with robotics and you land on recycling. You realize that

Part of the problem is just the human problem, just sorting this stuff. Accurate. And so you decide. to tackle this problem and see if you could launch a company that could

automate this. So tell me about the idea that you decided to come up with. Yeah, well. I was focused on where is a spot where this artificial intelligence technology was the the core linchpin. To building a new product. So I started focusing on recycling and I liked it because it seemed like you could use robots that had already been around for decades.

If you could pair them with this vision system. And I thought that was really good. You should have one hard technical problem. That was gonna be the vision system You didn't want to have to innovate on the robotic side, uh, at least not too much. That was at least the idea. Um So started

Kind of zeroing in on this idea of building a robot that could be bolted onto a conveyor belt and just pick stuff. Like that's really all we're trying to do is pick a bottle and pick a can. I applied for a grant from the National Science Foundation. Uh, there's a program called the SBIR, Small Business Innovations Research Program. That gave me some seed funding to get started and started building a little prototype. There was um You know, a lot of kind of good fortune on the way. Uh Initially I couldn't afford a conveyor belt.

And got a grant from Oscar Blues, the brewing company. They had for recycling stuff. And you know, I was applying for these grants, I was visiting recycling facilities. I didn't know the industry that well, and so I was honestly saying a lot of Dumb stuff. Asking a lot of dumb questions and

You know, I'm kind of amazed looking back that people would give me the time of day, but But yeah, started kind of building this robot, the first data sets for the vision system. Um so you you sort of need examples of bottles and cans to train this artificial intelligence stuff. Um I did dumpster diving for'em. Um, was uh going to recycling centers and pulling out bottles and cans and uh Yeah, just starting to hack it away at it.

I mean, this is a hardware and a software challenge, right? Because you've gotta build the hardware To be physically resilient. Right. Just grossness that it's gonna deal with and you know, there's probably gonna be

Rotten milk or rotten things, right. And then there's the software side, which is it's gotta identify the different plastics, what's glass, what's paper, what's right, and then pick it up quickly. Tell me how you started to work on building a machine that could identify What it's picking up. And sorting out.

So the interesting thing was The computer vision technology, this artificial intelligence, actually started to work really well almost from the beginning. Well, um you know, we had some insights really early on as to what would be important to these algorithms and and had uh a lot of success. Initially.

you know, we weren't at ninety nine percent accuracy. Um But one of the nice things about recycling is honestly the bar is a little low. Like it's hard. to consistently create pure material. And so As compared to automotive where you can't run over one out of a hundred people you see.

You know, for us it if you mess up on one bottle or can, you're still doing a lot better than the status quo. So it's a very forgiving environment. And we were able to kinda meet the standards of the industry pretty quickly. the part we thought would be easy which was using these off the shelf robots. That ended up being really tough.

Um so rotten milk sounds gross, but the real problem with it is that when it as it dries out, it starts to get really sticky. Uh sticky with a robot is not good. And these were and these robots had like Claws like you know, like you would see in like a How are they picking up the recycled material? So you know, we actually did start with claws and that was basically what my PhD was on, was having robots use claws in interesting ways. And it's really hard. It's just really hard to imitate what people do. There's so many sophisticated things you do.

Like when you're picking up something that's flat, like a a s a flattened carton. If you kind of do it slowly, you'll see you do things like you push down on a corner of it to get the opposite corner to lift up. And then you that lets you wrap your fingers around. It's very hard to get a robot to do this kind of um kind of sophisticated multi step planning.

And what I saw was it was gonna be tough. Uh and we ended up switching to a whole different technology that I I didn't even know much about in graduate school, which was uh using vacuum technology. So basically using something that's a industrialized system, but it's it's not that different from with your vacuum cleaner at home. You think about, okay, I can take my vacuum cleaner and I can kinda point it at an aluminum can, I'll probably be able to pick up the aluminum can That's kinda what we started to do, just point

a vacuum at the thing you want and pick it up. And we found uh we could get that to work really well. Um, so we we kinda hit the easy button on this. I mean, it's not that easy. I've spent like nine years of my life thinking about vacuums. I've seen a video of this. It's like

Tubes. Right. There's like a few tubes. over the conveyor belt and they'll just pop down And suck up. each piece of trash and they happens really fast, like in a millisecond. But but how did you make it so it it wouldn't just suck up like four things, right?

instead of just the actual thing it needs to suck up. Y you end up having this trade off exactly like you're describing. It can't be too big or it'll pick up too much. It can't be too small. Um We rely a lot on our vision system to look at the items even if they're overlapping and only target kind of promising areas to pick things up. And it's gotten pretty sophisticated. There's multiple layers. The thing self-cleans, it reverses the airflow after every uh pick.

Uh in case it Picked up some plastic bags or something. Right. It's a tough problem. We're still working at it. We're constantly trying to make it better. The hardest part out of all of it ended up being keeping it from getting gunked up with that rotten milk, pieces of glass debris.

There's so much stuff that can just kind of accumulate in a recycling facility and What we found was Even once we made something that worked. Most concepts for doing this will get gunked up with stuff within half an hour and we needed something that would last days. And that ended up being the hardest piece of it. So

Do do you have a sense of a of the accuracy? I mean how much so, for example, in a traditional Recycling. I have to imagine that oftentimes, you know, some glass gets into the aluminum cans, you know, and some paper gets into the plastic. How much more accurate are these machines and humans?

So There's kind of two ways to answer. So one is a person can actually be very good and produce above ninety nine percent purity. But they almost never do. Just'cause the the staff tends to not be motivated and uh it's a tough job and you start zoning out and things. Um, and so what you'll see is for most commodities, the recycling facilities will produce material that kind of bumps around ninety or ninety five percent pure. And so

Our facilities the biggest thing is besides being fully automated and having this lower cost structure as a result is they're just extremely consistent, like constantly producing material of the same purity. But yeah, we'll be ninety five to ninety nine percent. Interestingly what you find is, you know, there's this broader supply chain. We're selling the plastics to somebody. And they take these plastics and because the industry can't get to a high enough purity

Consistently. those buyers will actually have a whole sorting process where they sort it again. They they're cleaning up what they just bought. Uh, we sell those guys robots. Uh so our robots are helping clean the stuff up. And so the result though is is we can calibrate the purity to what the buyer uh will pay. So if they pay a premium, you know, we can hit a very high standard.

you know, if they're looking for kind of something that's middle of the road, more like ninety five percent, we'll just produce at ninety five percent. Let's talk about your customer who in the United States Who handles recycling? Is it'cause I think a lot of people assume it's like the government or municipal offices, but it's mostly not, right? It's private companies. Yeah, it it'll be companies like waste management or republic services. So those are Fortune five hundred companies.

You'll find some small family businesses. We have one customer that's uh Recycling and disposal services in Virginia, but The way the industry works is your city will have or your HOA will have a waste contract. And they'll have a contract with one of these groups.

Some municipalities decide to do it themselves. But um but for the most part it's a uh a company. Um and they'll take your trash and they'll take your recycling. Um they'll bring the trash to a landfill or or sometimes an incineration facility. they'll take the recycling and um sort it out and and run that business. And yeah, the municipalities typically aren't doing all of it themselves, but but in some cases uh they do. So when you started to I mean when you when you

began this journey, I'm and and you start to raise money for it. Presumably you had to sort of say, Hey, this is a big market opportunity, right? Because Look, let's be honest. nobody n um is I mean, as much as they say they are, is is investing just out of the goodness of their hearts. They they want to make a return. if presumably most of the the customers here are companies that are are already recycling. And if recycling isn't a big

driver of revenue, right, for some of these big companies like waste management, which makes its money from collecting garbage. How do you make the case that this is actually gonna be It's gonna make money. For them. Yeah, so fundraising was very hard for most of the life of the company.

For for exactly this reason. Um You know, we started with these sorting robots and we kinda described this one that uses a section cup. And really that That's actually not so much about the recycling business. It's really about kind of labor and automation. And so you look at the market and you say, Okay, there's tens of thousands of people doing this manual sorting task. There's a potential for tens of thousands of

Robots And you do the math on that and you find that that market's worth a couple billion dollars. And that that can be exciting for a certain class of investor, but When they look at it, they'll say, Okay, there's municipal contracts in this industry, there's a high degree of concentration into the biggest waste players. Um that makes it really hard to

sell lots of units. These things just slow it down. And so what we found was this kind of story around Automation. Didn't really

Attracts. A whole lot of investors. And we ended up getting the self selecting group of investors who believed in kind of a bigger picture, which was Why is it that the world is throwing away all of this good stuff? Like all of the stuff does have value. Um okay, it's because sorting it costs too much.

Okay, if you can solve that, what does that mean? And if you do some math, what you find is that Uh between the plastics, the metals, the paper and everything. The world is throwing away hundreds of billions of dollars worth of value. That's not counting some of the fundamental costs of disposal, like moving it to a landfill and throwing it away and the cost of doing all of that. And so if you can make a dent in the fundamental economics of recycling and make it a better business

You're unlocking hundreds of billions of dollars of value. Uh, and that is exciting. And so What you see for us is We started with this robot.

Um and that was kinda the the first um kind of beachhead. It let us build out the technology. We've sold hundreds of those robots now and it it's a very strong business. But really what we're trying to do is is make the recycling industry a better industry and unlock this latent value of of our garbage. Um, and if you can do that, then That becomes very interesting and you can build a massive business on that. We're gonna take another quick break, but when we come back, more from Matanya about how AMP Robotics is automating the recycling industry. Stay with us.

I'm Guy Raz and you're listening to How I Built This Lab. Welcome back to How I Built This Lab. I'm speaking with Matanya Horowitz, founder and CEO of AMP Robotics. It's a company that's using artificial intelligence and robotics to make recycling more efficient and economically viable. So when you were working on this and you got grants and you were starting to

What did you expect to happen that didn't happen? In other words, did w I mean I I think and this is the case with most entrepreneurs I interview, you think that it's going to be easier to solve faster than it actually is. Was that the case for you? Absolutely. The tough thing ended up not being the technology. Like it did take a while. I thought it would take Maybe six months it ended up taking more like two years to have something that was good. But The hardest problem ends up being

matching that technology to uh the business problem. And having something that people really love. Uh so When we got something working, I was like, Okay, great, hard work's done. And then I found out that the real hard work was beginning, which was to go sell a ton of these things, uh and go visit the recycling facilities.

understand how to price it, you know, and all of this sort of work. But I think It was surprising to me the extent to which um You know. even if you have great technology, you just really gotta make sure that um

You position it right to have it catch fire. So tell me a little bit about how this would work with existing recycling facilities. The idea is your equipment and technology would essentially Yeah, that's right. Yeah, so we'll go into an existing facility and we can deploy now

Several different types of robots. And we can get these recycling facilities to be almost fully automated. Uh so just a handful of people pulling out the stuff that's not supposed to be there, like bicycles and garden hoses. And What's really key there is we do it with very little change to their existing operations.

Most of that equipment gets installed over weekends when people aren't running anyway. And so you have this very like low friction path to automation. What you see is recycling facilities can use their lower cost structure to go after more material. They'll start running second shifts, they'll start expanding recycling programs. And those are a set of solutions we have for

the existing infrastructure. We've now gone on to start building recycling facilities around our technology, uh new greenfield sites. Built from the ground up around AI. what you find is you can do you can go a step further. Um you can have facilities that'll run twenty four seven.

um facilities that can have even higher rates of material capture, higher purities, be much more flexible. And crucially they can be fulmated. Um And so now you're starting to really kinda like see this cost per ton of sorting starting to drop significantly.

And really kind of changing what is profitable to recycle versus what's not. Has it been fairly easy to convince recycling facilities to adopt this technology, or is there still resistance? I'd say it's kinda middle of the road. It's Like the adoption of any new technology.

People want to make sure they're They understand the technology. they're going to be handing over a large fraction of their business to these robots. And so What we've done is we've tried to uh make it easy for the technology to be adopted.

You can get one or two robots. You know. Work with it for six months. start to trust the system and then get another four. And then once you've kind of got comfortable with that, you get another four. eventually your facility is almost fully automated. But you never had to to sort of take a huge leap and um

and you know, blindly believe in the technology, y you could sort of uh step your way into it. And we've seen that strategy to be successful. Um we have customers that still have one or two robots and they're kind of integrating it with their process. We have other customers who have almost their whole facility automated with these systems. The question we're going to do. constantly focused on internally is how do we make the rate of adoption even faster?

And that has A lot to do with technology, interesting pricing structures. Um, you know, what can we do to help insulate customers from commodity swings themselves because that'll affect the return of the robots. There's a real kind of like enterprise sales process. Um, you know, people are very deliberative. And it so it just takes time. And and you guys are also getting into the recycling

industry yourself. Servicing facilities you decided to build your own, right? That's right. We started with uh what's called secondary sorting, where we were actually buying from the existing facilities low quality materials.

But There was kind of two goals with this. One was There's this interesting kind of niche opportunity to take advantage of kind of inefficiencies in existing facilities, but we were really focused on showing what a recycling facility built around AI could

Do And now that we've done that, we're selling those facilities to the waste players, we're pushing those facilities into new domains and kind of sorting stuff that other people haven't in the past. But we really needed this kind of like um a facility we controlled so we could show what the technology was capable of. And those facilities are fulfilling.

fully functional, they've run twenty four seven, um, they run fulmated. You don't have people picking at stuff. Um you know, I've been doing this for about eight years and I feel like only now Are we getting sort of like the really, really cool stuff where you know, you walk inside these facilities, you have like literal tons of material, like tons of plastics and things flying around and everything is magically sorting itself and it's just the the absolute coolest thing. And um, you know, we've kind of been working towards this for so long. It's just great to see it in in reality.

So How long before you can see a full transition to a fully automated Recycling centers. You know, I would say you're already seeing this massive shift inside the industry. Um

You know, over the next five years, I think you're gonna see the vast majority of facilities be pretty close to fully automated. The technology doesn't take that long and it's not that difficult to deploy. And the economics. when you s have a really good recycling facility that's much more automated, they can be very strong. And so there's a strong incentive towards this uh adoption of the tech. So you know I know that for example China used to

plastic and materials and in I think in twenty seventeen they basically said we're not gonna take it anymore. What does that mean for your industry? I mean is that actually a good thing that that things m you know have to be dealt with Domestically now? From your perspective with AMP. Does that mean that um there are opportunities there for you?

Certainly, you know, one way of looking at this is In the US a lot of material was going to China or South East Asian countries. You know, one of the things I I point out to people is It really speaks to how valuable this stuff is. Like it was worthwhile to move this stuff across the Pacific Ocean. And

pull out these different plastics, like that whole thing was worthwhile. If people were doing that at a profit. But um but yeah, uh there were a lot of issues with it. One of the reasons it was worthwhile to do this in places like China was um Well, one of the main reasons is they have lower labor costs. So it would be Sorry. easier for them to pull out the specific materials uh over there.

By lowering the cost of sorting here in the United States, it's it's almost one of these manufacturing reshoring stories. Like we have lowered the cost of sorting so much, it's now worthwhile to do this domestically. And Us buying these low value plastic bales and separating the different materials out. That's basically what was happening in China. It was getting shipped over there and people were separating out these low value plastics. That shift in from China and Southeast Asian countries really happened uh a couple of years ago and the industry has adapted. So it has created this push for higher quality materials and that does serve as a tailwind to us.

But yeah, I I take it as kind of like an example of this reshoring that's happening more broadly. So If in fact most or all recycling facilities. become automated, what kind of impact will it have on recycling? I mean, right now in the US thirty five percent of materials are recycled.

Which means two thirds of things that can be recycled or not. What what kind of difference will it make if it's totally automated. Well, so for the existing facilities you'll see them Get hungrier for materials.

If you look at the recycling rate in the country, this kind of one third figure, what you see is that it's it increased rapidly in the nineties and then kind of flatlined. Um and really you were kind of seeing this Limited of the kind of economic viability of the system in its current form. So

You'll start to see that rate. again start to go up. Um what that looks like on the ground is you'll start to see recycling programs in more rural areas. Where the greater the volume of material you have, the easier it is to justify a facility. If you make facilities lower cost or the operating costs lower, now you can go after smaller and smaller areas. You can also go after dirtier materials.

Um this is something that Robotics and AI really open up for the industry is There's a number of different sources of garbage that often don't participate in recycling programs. Um, apartment buildings and other multifamily housing often aren't part of recycling programs, and that's a big reason why you don't have deeper penetration of the industry. And a lot of that has to do with where the garbage is kind of stored in those complexes and it just being harder to stand up a Well separated s streamer recyclables.

If you can just go through dirtier material, you can ask less of consumers and now you can expand access to those recycling programs. But um as you start to make the economics better, you start to see that this thirty-four, thirty five percent number can start to look more like fifty or seventy percent. And um we think that there's a real opportunity to do that in the next five years. Amazing. Tanya Horace, thanks so much. A real pleasure. Thanks for having me on Guy. That's Metania Horowitz, founder and CEO of Amp Robotics.

Hey, thanks so much for listening to How I Built This Lab. Please make sure to click the follow button on your podcast app so you never miss a new episode of the show, and it's totally free. This episode was produced by Sam Paulson editing by John Isabella. Our music was composed by Ramteen Arablui. Our audio engineer was Katherine Silva.

Our production team at How I Built This includes Alex Chung, Casey Herman, Chris Massini, JC Howard, Liz Metzger, Carrie Thomson, Carla Estevez, and Elaine Coates. Eva Grant is our supervising editor, Beth Donovan is our executive producer. I'm Guy Raz and you've been listening. How I built this.

What you see above is a preview of the first minutes. One unlock costs 3 credits and covers this episode forever: full segment and word-level timestamps on this page, plus .txt, .srt, .vtt and word-level JSON downloads, as many times as you like.