Inside Planet Labs (NYSE: $PL): Satellites, Planet AI & Area 51

1. 0:00 – 0:48

   Will Marshall, Co-Founder & CEO at Planet Labs

   1. WMWill Marshall0:00

      We've built about 700 satellites here in the last 15 years. That is more satellites than any other company on the Earth except for SpaceX. All 700 of our satellites cost less than a typical satellite at NASA. There's about 1,000X reduction in the cost. But this is our AI interface. We can ask it questions. We have tied an LLM to the back end, and it can search the entire Earth in under a second. Someone at NASA kept on saying when we were there, "Why are we spending a billion dollars on a satellite when a phone like this has most of what a satellite has, but it costs 500 bucks?"

   2. MOMolly O'Shea0:35

      So what was the answer to that? [upbeat music]

2. 0:48 – 2:44

   700 satellites for less than one NASA mission

   1. MOMolly O'Shea0:48

      All right, we are here at Planet Labs. Thank you for having us.

   2. WMWill Marshall0:51

      No problem. Welcome.

   3. MOMolly O'Shea0:51

      So what are we gonna see today?

   4. WMWill Marshall0:53

      We're gonna see some satellites.

   5. MOMolly O'Shea0:54

      [laughs] Okay.

   6. WMWill Marshall0:55

      Uh, also some AI stuff. You'll, you're gonna see some of our new AI interface to all of our satellite data. But let, we're starting down here in the satellite lab because, uh, it's cool.

   7. MOMolly O'Shea1:05

      I mean, we got a little peek, so you guys are in for a treat. There's some vibration plates and some, like, what is that one thing? You have a thunderstruck-

   8. WMWill Marshall1:14

      Yeah, that, that tests the-

   9. MOMolly O'Shea1:15

      ... testing table

   10. WMWill Marshall1:16

       ... the, the, the shock table. Yeah. Mm-hmm.

   11. MOMolly O'Shea1:17

       Yeah. Okay. So as we walk through, we'll start over here. I know you have some older satellites we can look through, but what are the different areas that we'll see today?

   12. WMWill Marshall1:27

       Yeah, I mean, basically this is our satellite manufacturing facility. So this is where we build loads of satellites. We just launched 20 more last week. We can pump them out.

   13. MOMolly O'Shea1:37

       [laughs]

   14. WMWill Marshall1:37

       In fact, we've built about 700 satellites here in the last 15 years. That is more satellites than any other, uh, company on the Earth except for SpaceX. So th- this is the manufacturing facility for satellites. We launch about five, four or five times a year. We've done it on 40, over 40 rockets. So what has really changed in satellite game has been just the sheer size and number of satellites.

   15. MOMolly O'Shea2:06

       Mm.

   16. WMWill Marshall2:07

       And Planet sort of pioneered miniaturization of satellites, taking satellites that are bigger than this room and shrinking them down to small size so that we can then launch loads of them, and with loads of them in space, we can do different kinds of missions. Before, each satellite was the size of a double-decker bus and cost a billion dollars minimum. I mean, some NASA missions cost up to 10. S- the really cheapest ones cost a couple of hundred million. We're talking about launching all 700 of our satellites cost less than a typical satellite at NASA. So it's about 1,000X reduction in the cost, and that's all to do with the miniaturization of electronics, and that's what we pioneered

3. 2:44 – 3:45

   Why Planet Labs is really a data business

   1. WMWill Marshall2:44

      here in this lab.

   2. MOMolly O'Shea2:45

      Something that I definitely wanna talk about during our sit-down is the use cases have kind of-

   3. WMWill Marshall2:51

      Yeah

   4. MOMolly O'Shea2:51

      ... pretty much changed substantially, especially with the new, uh, you guys just launched with Google.

   5. WMWill Marshall2:57

      Yes.

   6. MOMolly O'Shea2:57

      So you're, you're moving into the world of intelligence, which by the way I heard has great premiums on it, but-

   7. WMWill Marshall3:02

      Ha

   8. MOMolly O'Shea3:02

      [laughs] Can you talk through-

   9. WMWill Marshall3:03

      Yeah, it's a data business fundamentally. We're selling information services.

   10. MOMolly O'Shea3:07

       Yeah.

   11. WMWill Marshall3:07

       Exactly. So even though we have a satellite back end, we have s- uh, we, our data business is a very high margins business. Each sell of a picture or analytics from that picture is very, very high margins.

   12. MOMolly O'Shea3:20

       Mm.

   13. WMWill Marshall3:21

       I love that because, uh, uh, you know, as a business person, we ha- we do have some CapEx, but really it's re- very high barrier to entry. People launching satellites are few and far that come by. They're very complicated, yet so we have a high barrier to entry, but our margins look like a software business, and so it has the best of both worlds.

   14. MOMolly O'Shea3:44

       Amazing.

4. 3:45 – 6:22

   How a satellite sees trees from 500 km away

   1. MOMolly O'Shea3:45

      Okay. So what do we have behind us?

   2. WMWill Marshall3:46

      Yeah. So-

   3. MOMolly O'Shea3:46

      Let's talk through the lore of Planet Labs.

   4. WMWill Marshall3:49

      The lore. Exactly.

   5. MOMolly O'Shea3:49

      'Cause we have some right here.

   6. WMWill Marshall3:51

      Yeah, yeah, we do. This is actually this, uh, the, the, uh, whiteboard from our garage when we were playing around, um, where this is the garage where we first, uh, set. This is our initial team.

   7. MOMolly O'Shea4:04

      Mm.

   8. WMWill Marshall4:04

      Um, we were building our first satellite there in the lab. Um, this was, um, the... We were still working a little bit at NASA, and then we slowly left.

   9. MOMolly O'Shea4:14

      [laughs]

   10. WMWill Marshall4:15

       This is in our nights and weekends, and then we were like, "Okay, this is too cool." So we started building these satellites. I mean, you can see various bits of them, solar panels, the, the, the, the actual, um, boards that we make for the satellites. I can actually show, this is the optical, uh, telescope assembly. So this is the telescope and then the camera system. You can look down there, and you can see the actual telescope.

   11. MOMolly O'Shea4:37

       Oh, yeah. Oh.

   12. WMWill Marshall4:37

       You can see yourself in the mirror, so to speak. And that is looking down, taking pictures. Now, we're 500 kilometers away, so about the same distance as from here to Los Angeles.

   13. MOMolly O'Shea4:47

       Mm-hmm.

   14. WMWill Marshall4:48

       We are taking pictures that far away, but we can see individual trees. We can see houses. It's amazing that we can do that 500 kilometers away from a telescope this big. And this is what the satellite looks like all put together except for the solar panels. Now, this is one of our older ones, but it gives you a sense. As I said, this is the telescope. This is the, um, the motherboards. This is perking down, right? That's taking pictures up into the stars. It automatically recognizes the constellations and then goes, "Okay, well, that constellation's there. Therefore, I'm pointed exactly in this direction." Then it can turn itself around using these little wheels, so it can spin itself in any direction to take a picture that we want it to take.

   15. MOMolly O'Shea5:28

       Yeah.

   16. WMWill Marshall5:29

       Then it beams it down to the ground using these radios. Now, these radios, you might think, "What the heck are these bits of wire?" We can get two gigabits a second from our satellite down to the ground station th- over 1,000 kilometers aw- away. So we're talking about, about-

   17. MOMolly O'Shea5:45

       Phew

   18. WMWill Marshall5:46

       ... two gigabits a second down to the ground over 1,000 kilometers range. I mean, it's like sometimes our internet in this building is worse than that. I can't-

   19. MOMolly O'Shea5:53

       I understand.

   20. WMWill Marshall5:54

       [laughs]

   21. MOMolly O'Shea5:55

       I understand. [laughs]

   22. WMWill Marshall5:56

       Um, so, so basically all of this electronics tells you where the satellite is in space, that's the GPS, where it's pointing with a star camera, the sun sensors.

   23. MOMolly O'Shea6:05

       Mm-hmm.

   24. WMWill Marshall6:05

       And then we take a series of pictures, and then we embed that metadata on that picture so that we know where we're pointing. And then we stitch that to the Earth's surface. Now, we have about 200 of these in orbit. They image the entire Earth every day. It's the only system that does that,

5. 6:22 – 7:44

   4 million images of Earth, every day

   1. WMWill Marshall6:22

      that images the whole Earth every day.

   2. MOMolly O'Shea6:23

      And, and how many images do you do a day, and what is the file size of that? [laughs]

   3. WMWill Marshall6:27

      It's about 4 million 47 megapixel images, basically. So it's of order, I think, 100 terapixels.

   4. MOMolly O'Shea6:35

      Oh my God.

   5. WMWill Marshall6:36

      Yeah. And eight spectral bands for every pixel. So it's, actually, it's kind of eight pictures-

   6. MOMolly O'Shea6:41

      Mm-hmm

   7. WMWill Marshall6:41

      ... for every point on the Earth's surface with different colors. But not just the three that we have, RGB and our eye-

   8. MOMolly O'Shea6:46

      Mm-hmm

   9. WMWill Marshall6:46

      ... red, green, blue, but we have eight spectral bands that cover near-infrared into the optical wavelengths.

   10. MOMolly O'Shea6:52

       And so for people who might be newer to Planet Labs, why is image data so important maybe versus, like, radio occultation data?

   11. WMWill Marshall7:00

       Well, there's all sorts of data that you can get from space. Um, imagery is of course super useful because it is the kind of data that we can visually interpret. We're visual creatures, right? You name it, we can see it, we can understand it. Also, there's a huge amount of work in visual l- language models now. Um, so graduating from the machine learning things that we're doing, recognizing cats and, and dogs in videos online-

   12. MOMolly O'Shea7:27

       Yeah. [laughs]

   13. WMWill Marshall7:27

       ... can now recognize buildings and ships and planes and trains or whatever it is that you're trying to find. So AI is very ready for it, just like we're very ready to look at it. Of course, we can't look at 4 million images per day, so we're using machines to do most of the, the he- heavy lifting there.

6. 7:44 – 9:03

   What a satellite goes through to reach orbit

   1. MOMolly O'Shea7:44

      Mm-hmm. Okay, so-

   2. WMWill Marshall7:45

      Do you wanna h- do you wanna hold it?

   3. MOMolly O'Shea7:46

      Sure. Oh my God.

   4. WMWill Marshall7:48

      What do you think?

   5. MOMolly O'Shea7:48

      Oh, it's not that heavy.

   6. WMWill Marshall7:49

      No, don't drop it. [laughs]

   7. MOMolly O'Shea7:50

      It's really light. [laughs]

   8. WMWill Marshall7:50

      Actually, if you dropped it, it wouldn't be so bad because that is more or less dropping it from about this-

   9. MOMolly O'Shea7:54

      I heard one of your jobs is to throw this against the wall

   10. WMWill Marshall7:56

       Yeah, exactly. Yeah.

   11. MOMolly O'Shea7:57

       [laughs]

   12. WMWill Marshall7:58

       I'll demonstrate in a second. But actually dropping it from about this height onto a, a-

   13. MOMolly O'Shea8:02

       Ooh

   14. WMWill Marshall8:02

       ... a marble floor is about the equivalent of the shock loads that it, it, it takes on when it, it, it, when the two stages of a rocket separate.

   15. MOMolly O'Shea8:10

       Okay. Yeah.

   16. WMWill Marshall8:10

       It's kind of-

   17. MOMolly O'Shea8:11

       That's intense.

   18. WMWill Marshall8:12

       Yes. 200 Gs. Um, it's, it's extremely intense. So it- one of the hard things about designing these satellites is not just that it needs to work, but it needs to work through the launch, which is 15 Gs shaking-

   19. MOMolly O'Shea8:23

       Yeah

   20. WMWill Marshall8:23

       ... 200 Gs, bolt, uh, shock loads. And then in the thermal environment of space, so where we're going from minus 40 degrees C to plus 20 degrees C-

   21. MOMolly O'Shea8:34

       Yeah

   22. WMWill Marshall8:34

       ... every 45 minutes. I mean, that's much colder than your freezer and much hotter than the hottest day, a sort of like oscillation. And this telescope must stay in focus for that whole time. Even movement of a fraction of a wavelength would put this out of focus. So this thing has to survive those shocks, survive that thermal environment, and stay in focus. So the difficulty is not so much the fundamental optic design-

   23. MOMolly O'Shea8:59

       Mm-hmm

   24. WMWill Marshall8:59

       ... but how do you encase it in a system that will survive all of that, that

7. 9:03 – 12:05

   The $500 phone vs. the $1B satellite

   1. WMWill Marshall9:03

      load?

   2. MOMolly O'Shea9:03

      Right. And so the first version that you had, you put... I'll put this down.

   3. WMWill Marshall9:07

      Yeah, yeah, sure.

   4. MOMolly O'Shea9:09

      You, you put a phone up into space?

   5. WMWill Marshall9:10

      Yeah. This was a slightly catastrophic, uh, event [laughs] as you can see.

   6. MOMolly O'Shea9:14

      [laughs]

   7. WMWill Marshall9:15

      Um, basically we put this phone onto a suborbital rocket. We were trying to show... Well, basically, let me step back one sec.

   8. MOMolly O'Shea9:22

      Okay.

   9. WMWill Marshall9:23

      Someone at NASA kept on saying when we were there, "Why are we spending a billion dollars on a satellite when a phone like this has most of what a satellite has, but it costs 500 bucks?"

   10. MOMolly O'Shea9:35

       Right.

   11. WMWill Marshall9:36

       It has GPS-

   12. MOMolly O'Shea9:36

       So what was the answer to that?

   13. WMWill Marshall9:38

       Uh, it didn't need to cost a billion dollars. Phones work just fine in space. Now, this first test-

   14. MOMolly O'Shea9:43

       [laughs]

   15. WMWill Marshall9:43

       ... did not work, but amazingly, all of the, the phone electronics have survived and we managed to get all the data. And, and this just showed the case in point that even though this-

   16. MOMolly O'Shea9:54

       Yeah

   17. WMWill Marshall9:54

       ... was a failed launch, these things are incredibly robust. They're designed exactly for you to drop it on the floor and it not break because people do shit like that.

   18. MOMolly O'Shea10:03

       Mm-hmm.

   19. WMWill Marshall10:03

       And so, um, it actually was a surprising e- example of just how robust consumer electronics are. See, what happened back in the '60s and '70s and '80s, NASA was pioneering all this technology because it had to. To go to the moon, you had to put a capsule with humans in it, and you had to have a computer, so they had to sort of develop microprocessors in order to get a computer that's small enough, 'cause computers were the size of a building. They had to, you know, pioneer solar panels and various other technology in order to get it done. And so they're used to the idea of building everything themselves because they couldn't go down to, you know, Fry's or whatever and get the component. They didn't exist. You didn't buy batteries that they needed. You couldn't buy computers that they needed. They couldn't buy solar panels. So they invented it all. So NASA had a mentality of inventing everything. Now, it did incredible things as a result, but now the consumer electronics, the electronics that we have in our back pocket-

   20. MOMolly O'Shea11:01

       Yeah

   21. WMWill Marshall11:01

       ... are far superior to what they had. And the do- dom- dominant R&D is being spent by Apple and Google and whoever on developing these electronics to be better and better. So we took the attitude of instead of developing all of that, let's take the best stuff that's already being developed commercially and use that for space, learning to follow the consumer electronics industry rather than trying to pioneer everything. And that whole approach, use cheap electronics that we can buy online, and then, by the way, throw up a few more than we need, and if one or two of the satellites breaks, no big deal.

   22. MOMolly O'Shea11:40

       Mm.

   23. WMWill Marshall11:40

       Totally different risk attitude to what NASA did. And that also enabled us to just reduce the cost by about three orders of magnitude, which is, you know, a big deal for any sector.

   24. MOMolly O'Shea11:52

       A huge deal. [laughs]

   25. WMWill Marshall11:52

       You know? It's a bit like the mainframe computers to desktop computer revolution, and all the, you know, applications we have with desktops now are completely different than what we did with a few mainframes, one per country or whatever,

8. 12:05 – 14:47

   1,000x more data than the first satellites

   1. WMWill Marshall12:05

      you know?

   2. MOMolly O'Shea12:06

      So I have endless questions. I guess before I get to all of them, what is the biggest difference between, okay, V1, we're putting a phone up into space, to one of these-

   3. WMWill Marshall12:17

      Yeah

   4. MOMolly O'Shea12:17

      ... going up there, to what we're about to see right now?

   5. WMWill Marshall12:20

      Okay. So one way to think about it is how much data they're producing and getting down to the ground. Um, when we first launched the first satellites, some of which are here, various parts, they would produce- Uh, get data rates down about a megabit a second. So we take lots of pictures, we dump it down with a radio that's going at about a megabit a second. Well, if you're taking 47 megapixel images, you can't get very much data down at that rate. In fact, uh, the co- so now our data is about two gigabits a second, so about 1,000 times better. That means we're roughly getting 1,000 times more data than the first ones.

   6. MOMolly O'Shea12:55

      Mm.

   7. WMWill Marshall12:55

      Per satellite, per unit time. So huge increases in the amount of data. Um, and that's what enabled us to get to this first mission one, we called it-

   8. MOMolly O'Shea13:04

      [laughs]

   9. WMWill Marshall13:05

      ... of imaging the whole Earth every day.

   10. MOMolly O'Shea13:07

       This episode is brought to you by Brex, my favorite. You become what you spend on, and I refuse to spend my time on work that shouldn't exist. Expense reports, receipt chasing, and manual closes. The companies building what's next from Vercel, OpenAI, Anthropic, Granola, and Deepgram all made the same call. They all run on Brex. Brex is the intelligent finance platform that combines cards, expenses, and banking into a single stack with agentic finance built in. AI agents that handle expenses automatically, enforce policy before spend happens, and close your books in minutes. That's why Sourcery runs on Brex, so I can spend time on building and not busy work. It's time to get Brex AF. Learn more at brex.com/sourcery. That's B-R-E-X.com/S-O-U-R-C-E-R-Y. Bye. From handshake to signature faster, Harvey, the AI platform built for legal work, is trusted by 80% of the Am Law 100 and over 20% of the Fortune 500. Learn more today at harvey.ai. That's harvey.ai. AI needs more than chips. It needs power, land, and infrastructure. Zone develops next generation data center campuses, partnering with AI companies, site developers, and technology leaders to bring compute online faster and at scale. Zone is building the foundation of the AI frontier. Visit zonefrontier.com to learn more. That's zonefrontier.com to learn

9. 14:47 – 16:44

   Planet Labs' 48 ground stations that bring Earth’s data home

   1. MOMolly O'Shea14:47

      more. Let's, uh, let's go take a look inside.

   2. WMWill Marshall14:49

      Yeah.

   3. MOMolly O'Shea14:50

      Um, I know you and your team work very closely together between manufacturing, testing, production, all that. So how, how do they communicate with one another? What's the flow here?

   4. WMWill Marshall15:03

      Well, f- we build all the satellites here. You'll see some of it. Um, we're actually gonna first go into the place where we build the bigger satellites.

   5. MOMolly O'Shea15:11

      Okay.

   6. WMWill Marshall15:11

      Now, all of this is done on these sort of automated test stands. This gentleman here is working on them, these guys here. And they, they build all the subsystems. That all comes together into this main clean room area, which you see here, which we can actually put our hair nets on and go in-

   7. MOMolly O'Shea15:27

      Okay

   8. WMWill Marshall15:27

      ... um, so that we can actually see one of the satellites. They're a bit bigger than the, those first ones, 'cause these ones, as I was mentioning, trying to get to a much higher resolution on the ground.

   9. MOMolly O'Shea15:36

      Mm-hmm.

   10. WMWill Marshall15:37

       So... and I don't know if you were asking about how they communicate with each other, but we can talk about that, but basically each satellite dumps its data to the ground stations, but we've got 48 of those ground stations all around the world.

   11. MOMolly O'Shea15:48

       You have your own ground stations?

   12. WMWill Marshall15:49

       Yes. We built... Basically, no one had that either. You can't go to Fry's-

   13. MOMolly O'Shea15:53

       I understand. [laughs]

   14. WMWill Marshall15:53

       ... and get that either. So basically, we built about, I think it is 48 or so of these parabolic dish antennas-

   15. MOMolly O'Shea15:59

       Yeah

   16. WMWill Marshall15:59

       ... doing dual S and X band in, um, uh, uh, a few dozen locations. We often have four or eight of these ground stations at any one location, 'cause we have so many satellites, there's many to look at, at any one time, even from the same spot. And, uh, we're, uh, so we're... and they're in Alaska, northern Canada, uh, northern Norway, southern tip of New Zealand, southern tip of Australia. So basically, the highest latitude locations because our satellites are mainly in polar orbits, and so they get much more contact points than closer your station is to the pole. Um, so we put them as far north and south as possible with an internet connection, because we have to get all that data back-

   17. MOMolly O'Shea16:43

       Yeah. Yeah

   18. WMWill Marshall16:43

       ... obviously.

10. 16:44 – 18:19

    Why every Planet Labs satellite is named after a bird

    1. MOMolly O'Shea16:44

       Okay. So as we go and we look through these, I want to address one thing. All of these satellites are named after birds.

    2. WMWill Marshall16:52

       Yes.

    3. MOMolly O'Shea16:53

       Why? [laughs]

    4. WMWill Marshall16:53

       Okay. This is actually a space tradition that precedes us, and we were, um, uh, like, in NASA there was the Eagle that landed. Um, obviously a lot of military missions, uh, like Kestrel Eye or... And we wanted to name ours after birds that were a part of our mission. So Dove's trying to inspire how we're trying to help peace and security around the Earth. Um, Tanager is our hyperspectral satellite, and that's because these are looking out for biodiverse areas. Tanagers are some endangered birds with a lot of different colors in the tropics, so we can track ecosystems. Uh, Pelicans are highest resolution systems. That's because they fly really low.

    5. MOMolly O'Shea17:40

       Mm-hmm.

    6. WMWill Marshall17:40

       They so- fly so low. Pelicans fly really low 'cause they get a bit of lift off the water-

    7. MOMolly O'Shea17:45

       Yeah

    8. WMWill Marshall17:45

       ... when they fly really low. They get a little, like 10 or 20% more lift. Um, we can do the same, sort of, across the top of the atmosphere. So we fly these satellites really low so that we get better resolution on the ground, so we named them after Pelicans 'cause of that. So we'll continue to name them-

    9. MOMolly O'Shea18:01

       [laughs]

    10. WMWill Marshall18:01

        ... after cool birds. Oh, our next one is gonna be called Owl.

    11. MOMolly O'Shea18:04

        Oh, yeah. Mm-hmm.

    12. WMWill Marshall18:05

        Uh, so we're launching all these owls 'cause they've got bigger eyes, and they're wise 'cause they have a huge amount of compute onboard. So we're naming them after owls. So we'll keep on doing that just for fun.

    13. MOMolly O'Shea18:14

        Amazing. Okay. Let's get-

    14. WMWill Marshall18:16

        Okay. We'll put some hair nets on

    15. MOMolly O'Shea18:17

        ... suited up. [laughs]

    16. WMWill Marshall18:18

        Yeah. All right.

11. 18:19 – 20:17

    A look inside Planet Labs’ sharpest satellite

    1. WMWill Marshall18:19

       So we're going into the clean room to see some of the bigger satellites. Uh, you're all hair netted up.

    2. MOMolly O'Shea18:24

       [laughs]

    3. WMWill Marshall18:24

       You look cool. We look cool. Let's go. All right. So- Um, yeah, so in here we actually build the satellites, the bigger satellites. That's a stand for one of the satellites here. You can actually see these are the solar panels that will be attached to these bigger satellites. This is a bus of one of the bigger satellites, so that's the, um, core spacecraft components. That does the attitude determination and control, it does the propulsion, it does the radio communications. The propulsion, I think, is on the bottom. And so basically, all of that ha- harness hel- holds the payload-

    4. MOMolly O'Shea19:01

       Yeah

    5. WMWill Marshall19:01

       ... which is a huge telescope that looks down.

    6. MOMolly O'Shea19:03

       Mm-hmm.

    7. WMWill Marshall19:04

       So most of the volume is taken up with that. Now, somewhere around here we have one of the actual satellites. Oh, actually, this is a bit of fun.

    8. MOMolly O'Shea19:11

       [laughs]

    9. WMWill Marshall19:12

       You can see there the optics, the primary optics there.

    10. MOMolly O'Shea19:15

        Oh, yeah.

    11. WMWill Marshall19:16

        That is the big telescope looking down.

    12. MOMolly O'Shea19:18

        Yeah.

    13. WMWill Marshall19:18

        So that gives you a sense of the scale. But here's the spacecraft that we're gonna look at. Um, so this is, a, a Ta- a Pelican-10, um, so it's one of our highest resolution satellites. So this, this is now integrated. It has the telescope inside of it. So here you can see the back. This is the propulsion system. You can see this is the feeder. These are the two main tanks. This is the pressurant tank, uh, of that propulsion system, so that's the back end. The telescope is ac- This is the connection that goes to the rocket here, and then, and then these are star cameras that are actually hidden, uh, e- enclosed so that they, um, we don't get dust in them. And, uh, the telescope is inside of here. You can't really see it. Um, uh, so it's all wrapped up in this main section.

    14. MOMolly O'Shea20:13

        Wow.

    15. WMWill Marshall20:14

        Any questions?

    16. MOMolly O'Shea20:15

        Yeah. [laughs] A lot.

    17. WMWill Marshall20:16

        Go on then.

12. 20:17 – 21:14

    Why Planet Labs doesn’t make its own chips

    1. MOMolly O'Shea20:17

       Okay. So, uh, Planet Labs is vertically integrated, so how many of these components are you building in-house versus which parts are not as-

    2. WMWill Marshall20:26

       Yeah

    3. MOMolly O'Shea20:26

       ... kind of, uh-

    4. WMWill Marshall20:28

       It's a little bit nuanced because the, at the chip level we buy almost everything externally.

    5. MOMolly O'Shea20:33

       Yeah.

    6. WMWill Marshall20:33

       But at the system level, we build almost everything internally. So the telescope, we get the blanks from a, a, a company, but we integrate the telescope, as you saw over there, here. Um, and so we build up the framing and the, and the structure. Um, similar for almost everything else. The radios. We b- don't build our own chips. You know, we get the same chips from other people. WiMAX components, other things. But we integrate them into special circuits that, and with special antenna, that enable us to get the radio frequency sort of, uh, output that we need. Um, so it really depends. I would say the way to think about it, uh, simplistically is the, the chips we buy, the sy- systems we build.

13. 21:14 – 22:47

    Building a satellite in 8 hours, not 8 years

    1. MOMolly O'Shea21:14

       Mm-hmm. And so how many Pelicans do you produce a year? How many Doves? How many Tanagers?

    2. WMWill Marshall21:20

       Great question.

    3. MOMolly O'Shea21:21

       How do you think through all of these?

    4. WMWill Marshall21:22

       So we're ramping up on the Pelicans. The, the Doves, we build hundreds. We've built about over 650 of those Doves here in this lab. We can build up to, uh, 40 a week, so we can... We don't do that every week, but we can build really fast. So I think each satellite comes with, takes about eight hours to build.

    5. MOMolly O'Shea21:44

       Okay.

    6. WMWill Marshall21:45

       Um, to give you a sense.

    7. MOMolly O'Shea21:46

       Yeah.

    8. WMWill Marshall21:46

       And to give you a sense, when I was at NASA, it was, like, eight years.

    9. MOMolly O'Shea21:49

       [laughs]

    10. WMWill Marshall21:49

        Okay? Not eight days.

    11. MOMolly O'Shea21:50

        Yeah. [laughs]

    12. WMWill Marshall21:50

        So it was, like, completely changing. Um, these bigger ones take a bit longer, and we're ramping up the production, uh, so we can do many dozens of those. We, in fact, we just announced a new facility in Berlin where we're doubling again the manufacturing space that we have, that we announced could do up to 60 of those, these sort of per year.

    13. MOMolly O'Shea22:11

        Wow.

    14. WMWill Marshall22:11

        So that'll give you a sense of scale. And then the Tanagers is rather lower volume because they're sort of specialized instruments that we're working with NASA JPL to-

    15. MOMolly O'Shea22:19

        Yeah

    16. WMWill Marshall22:20

        ... uh, on. And, uh, we just launched our second one literally, uh, last week, and we've got another one that's actually, I think, behind there. Um, we can't go in because that one's more export-

    17. MOMolly O'Shea22:31

        Super secret

    18. WMWill Marshall22:32

        ... controlled. Yeah, so we can't go into that.

    19. MOMolly O'Shea22:34

        [laughs]

    20. WMWill Marshall22:35

        You can see it's black. [laughs]

    21. MOMolly O'Shea22:36

        [laughs]

    22. WMWill Marshall22:37

        Um, top secret. Uh, but that, uh, that, that payload is a little bit more specialized. It takes a little bit more work, and so we're, we're launching a couple more of those per year sort of rate.

14. 22:47 – 24:30

    Why fleet size isn't what matters

    1. MOMolly O'Shea22:47

       Is there a goal to how many you're gonna build in a constellation, or is some of this replenishing? Like, how do you think about it?

    2. WMWill Marshall22:54

       It is replenishing now, and in fact, it's more about what capability do you have on each satellite-

    3. MOMolly O'Shea22:59

       Mm

    4. WMWill Marshall22:59

       ... than the number of satellites. We have the largest Earth imaging s- fleet. It's about 10 times larger than anyone else, and most importantly, it images about 100 times more area than any other commercial actor. Uh, at least western one. Uh, the Chinese are trying to build similar systems. In fact, they even copy our names. They call theirs-

    5. MOMolly O'Shea23:17

       Oh, boy. [laughs]

    6. WMWill Marshall23:18

       What do they call it? Pigeon or something.

    7. MOMolly O'Shea23:19

       [laughs]

    8. WMWill Marshall23:19

       It was, like, a close to Dove. Uh, anyway.

    9. MOMolly O'Shea23:21

       [laughs]

    10. WMWill Marshall23:22

        It was like it looked eerily similar, and it, they even named it eerily similar. But, um, but no, roughly speaking, we're the only ones that cover the whole world every day. If you look at any of the other players, they might task to a few specific locations, but cover less than 1% of the land mass of the Earth per day, or maybe a couple of percent at most, whereas we cover the whole of it. So, you know, 100 times-ish area collection. So that's what we really care about. The Owls are the upgrade, um, to have the area, uh, collection the same, but 10 times more data per unit area because we're going from three-meter resolution to one-meter resolution daily scan of the planet. And that's roughly three by three times more data, so 10 times more data almost. And also, we're getting it back 10 times faster 'cause we're adding optical links and links to get that back really quickly. So basically, you can get it with- back within a few minutes. So we're getting 10 times faster back and 10 times more data. But actually, the number of satellites will stay about the same, if not go down a little bit because of the nature of how we're building those.

    11. MOMolly O'Shea24:25

        Mm.

    12. WMWill Marshall24:26

        So it's, it's not how many satellites you have, it's what you do with them or something.

15. 24:30 – 25:29

    The engine that’s 10x more efficient in space

    1. MOMolly O'Shea24:30

       [laughs] Okay. Is there anything else in here that we should see? Anything, any technical specs that we should know?

    2. WMWill Marshall24:35

       Um, well, we can see, see a few other things here.

    3. MOMolly O'Shea24:37

       Okay.

    4. WMWill Marshall24:37

       There's, uh, this is a, a propulsion system all laid out, and you can see that on a bench. That's kinda fun. As I said, this is our telescope assembly here. Um, so it's, it's about 50 centimeters, uh-

    5. MOMolly O'Shea24:52

       Yeah

    6. WMWill Marshall24:52

       ... uh, it's, um, in size, and that determines how small a object we can see on the ground-

    7. MOMolly O'Shea24:57

       Mm-hmm

    8. WMWill Marshall24:57

       ... together with the altitude of the satellite. So that's it. Um-

    9. MOMolly O'Shea25:01

       What kind of fuel are you guys using?

    10. WMWill Marshall25:02

        Uh, in this is z- xenon. So it's a, it's a, it's an ion engine, so they're very efficient in space. They, the, the gas comes out the back extremely fast. Much, much faster, like 10 times faster than a rocket engine-

    11. MOMolly O'Shea25:16

        Wow

    12. WMWill Marshall25:17

        ... a classical rocket engine. It doesn't have as much thrust, so you can't take off using these engines off the planet. It's not nearly enough. But once you're in space, they're much, much more efficient, like, as I said, almost 10 times more efficient than those big rocket

16. 25:29 – 26:56

    Why the 100 million pieces of space junk is the real collision risk

    1. WMWill Marshall25:29

       engines.

    2. MOMolly O'Shea25:30

       I think it was SpaceX Starlink that just put out, they wanna try to open source the data for anti-collision avoidance.

    3. WMWill Marshall25:37

       Yes. Satellite-

    4. MOMolly O'Shea25:38

       So-

    5. WMWill Marshall25:38

       ... uh, uh, space domain awareness data

    6. MOMolly O'Shea25:40

       Nice

    7. WMWill Marshall25:40

       ... SDA, yeah. Um, yeah, so I think that's really cool. Um, uh, early on, I mean, we, we have a lot more objects in space.

    8. MOMolly O'Shea25:48

       Yeah.

    9. WMWill Marshall25:49

       We wanna stop collisions. We work very collaboratively with the other players. The biggest challenge, though, is less the satellites. It's all the space debris. So we've got about, of order 10,000 satellites operating in space, but we've got of order 100 million space debris objects, so objects that were former satellites that blew apart, uh, satellites that crashed, uh, satellites that were deliberately taken out by anti-satellite weapons from the ground. Um, and those things cause one satellite to pop into tens of thousands of bits. Okay, let's carry on.

    10. MOMolly O'Shea26:22

        What a wild, wild problem. [laughs]

    11. WMWill Marshall26:25

        It is. It's wild, wild space.

    12. MOMolly O'Shea26:27

        Wild, wild space.

    13. WMWill Marshall26:28

        [laughs]

    14. MOMolly O'Shea26:28

        Great documentary by Ashley Vance, which you were in-

    15. WMWill Marshall26:31

        [laughs] I know

    16. MOMolly O'Shea26:31

        ... by the way.

    17. WMWill Marshall26:32

        Yeah, it is.

    18. MOMolly O'Shea26:32

        Small plug.

    19. WMWill Marshall26:33

        It's cool, right?

    20. MOMolly O'Shea26:33

        It's so good.

    21. WMWill Marshall26:34

        Have you seen it?

    22. MOMolly O'Shea26:35

        Yes, I have.

    23. WMWill Marshall26:35

        Yeah, yeah, yeah.

    24. MOMolly O'Shea26:36

        Before we went to Rocket Lab, I, I watched that, and, uh-

    25. WMWill Marshall26:39

        Yeah

    26. MOMolly O'Shea26:39

        ... their little fight between him and, I think, I, who was it?

    27. WMWill Marshall26:42

        A- A- A- Chris Kemp from NASA

    28. MOMolly O'Shea26:44

        Yeah, Chris Kemp.

    29. WMWill Marshall26:45

        Yeah.

    30. MOMolly O'Shea26:45

        It was just hilarious.
17. 26:56 – 27:40

    Spotting gas leaks from space

    1. WMWill Marshall26:56

       this is a post of, uh, methane tracking activities of the Tanager spacecraft.

    2. MOMolly O'Shea27:02

       Oh, wow.

    3. WMWill Marshall27:02

       So this is a plume of gas. By the way, when we enable them to be turned off-

    4. MOMolly O'Shea27:07

       Uh-huh

    5. WMWill Marshall27:07

       ... that because we just tell the gas company, "Hey, you got a big fricking great leak on your pipeline."

    6. MOMolly O'Shea27:13

       Uh-huh.

    7. WMWill Marshall27:14

       Turning this one off is the equivalent of taking a couple of hundred thousand cars off the road from a pollution standpoint.

    8. MOMolly O'Shea27:20

       Oh my gosh.

    9. WMWill Marshall27:21

       So one leak.

    10. MOMolly O'Shea27:22

        Ooh, when we go to the AI demo later, is it possible to see the difference of COVID versus non-COVID? You know, when-

    11. WMWill Marshall27:28

        Oh, yeah

    12. MOMolly O'Shea27:28

        ... everything was off the world.

    13. WMWill Marshall27:30

        We can have a look. We can have a look.

    14. MOMolly O'Shea27:31

        Okay.

    15. WMWill Marshall27:31

        We can ask the AIs.

    16. MOMolly O'Shea27:32

        Let's ask the AIs. [laughs]

    17. WMWill Marshall27:34

        Uh, you-

    18. MOMolly O'Shea27:34

        Is that named after a, a bird too? [laughs]

    19. WMWill Marshall27:36

        No. [laughs] It should do.

    20. MOMolly O'Shea27:38

        [laughs] Yeah.

    21. WMWill Marshall27:38

        That's a good idea. Okay,

18. 27:40 – 32:19

    Testing satellites to the breaking point

    1. WMWill Marshall27:40

       I'm gonna steal that.

    2. MOMolly O'Shea27:41

       Okay.

    3. WMWill Marshall27:41

       So here we have some of our testing facilities. So here, this is, this is, um, a, a system that tests this, um, the r- the shock when you, when two stages of the rocket separate. So basically we put our satellite here, and we bring this up, and we let this hammer smack down, and it's gives this 200G-ish shock load. And it's-

    4. MOMolly O'Shea28:05

       Why, why, [laughs] why isn't this in a sound barrier room? [laughs]

    5. WMWill Marshall28:08

       Well, I guess people put earplugs in.

    6. MOMolly O'Shea28:10

       Okay. [laughs]

    7. WMWill Marshall28:10

       The, the, the earplugs. You haven't got any, but [laughs] they're up there.

    8. MOMolly O'Shea28:13

       Great.

    9. WMWill Marshall28:14

       And then this is a vibration table. So this vibrates to simulate the launch environment.

    10. MOMolly O'Shea28:19

        Yeah.

    11. WMWill Marshall28:20

        Um, so we put our satellite on there, vibrate the shit out of it, and hopefully nothing falls apart.

    12. MOMolly O'Shea28:25

        What have been the biggest, uh, failures?

    13. WMWill Marshall28:28

        Well, we've had telescopes break.

    14. MOMolly O'Shea28:31

        Okay.

    15. WMWill Marshall28:31

        We have to redesign it. We've had-

    16. MOMolly O'Shea28:33

        What, like, what is the most delicate part of your satellite?

    17. WMWill Marshall28:36

        Well, it's probably the telescope.

    18. MOMolly O'Shea28:37

        Yeah.

    19. WMWill Marshall28:37

        Exactly.

    20. MOMolly O'Shea28:38

        Okay.

    21. WMWill Marshall28:38

        So it's, because they're, again, just think about this, like the optics of that mustn't move by more than a fraction of a wavelength. The wavelength is of order less than a micron, so a thousandth of a millimeter. So the telescope, two components, the main optics, mustn't move by more than a thousandth of a millimeter, otherwise it's out of focus. Well, that's really annoying, 'cause that's a s- very small distance.

    22. MOMolly O'Shea29:04

        Mm.

    23. WMWill Marshall29:05

        And again, even when it's in space, normally if you just made the telescope out of aluminum like this, it would expand and contract so much that the telescope wouldn't work when it's too hot or too cold because it would be totally out of focus. So we have to design it out of special materials that compensate for that expansion and contraction 'cause of the thermal loads. So that's the kind of thing that's really difficult. And now I can actually show you where we test that thermal loads.

    24. MOMolly O'Shea29:30

        How many satellites do go up end up having errors? Like, what has been the-

    25. WMWill Marshall29:35

        Error rate?

    26. MOMolly O'Shea29:36

        Yeah.

    27. WMWill Marshall29:37

        Um, so firstly, of all 700 satellites, if the launch worked and delivered us into orbit, our satellites have turned on and worked.

    28. MOMolly O'Shea29:47

        Okay.

    29. WMWill Marshall29:48

        We have had some that were out of focus. Um, we have had a few problems where a solar panel didn't deploy, a reaction wheel stopped working early, things like this. But generally, we've got utility out of 100% of our satellites, which I actually think is a problem, and I keep on telling folks that.

    30. MOMolly O'Shea30:04

        Why?
19. 32:19 – 37:31

    What changed at Area 51 in five years?

    1. WMWill Marshall32:19

       So let's go upstairs and, um-

    2. MOMolly O'Shea32:21

       Cool

    3. WMWill Marshall32:22

       ... uh, yeah. So we're gonna go up to the third floor. I guess I could take this at this point.

    4. MOMolly O'Shea32:26

       You ready? Well, he's ready. [laughs] Let's go.

    5. WMWill Marshall32:28

       Come on.

    6. MOMolly O'Shea32:29

       [laughs]

    7. WMWill Marshall32:29

       So here are some of our doves. There's a SkySat. Um, this is our new, um, Pelican spacecraft that you were just seeing downstairs, the model of it.

    8. MOMolly O'Shea32:38

       It's smaller.

    9. WMWill Marshall32:39

       Well, that's a, is, um, scaled down.

    10. MOMolly O'Shea32:41

        Oh, okay. [laughs]

    11. WMWill Marshall32:42

        [laughs] Um, but this is our AI interface. So basically, this is our imagery of the whole world.

    12. MOMolly O'Shea32:48

        Uh-huh.

    13. WMWill Marshall32:48

        You can zoom in any way you wanna zoom in on. You can go through time and see it as it changes over time. I mean, if we go up further north, if we go down to December, it's gonna be snowier. Um-

    14. MOMolly O'Shea33:01

        Wow

    15. WMWill Marshall33:01

        ... so you can see all the snow cover. And, um, but, but the coolest thing is that we have ... So we have 3,000 layers of images-

    16. MOMolly O'Shea33:10

        Mm-hmm

    17. WMWill Marshall33:10

        ... going back 10 years, so pretty much every day for 10 years. But-

    18. MOMolly O'Shea33:14

        Zoom in as far as you can. Let's see what-

    19. WMWill Marshall33:16

        Well-

    20. MOMolly O'Shea33:16

        ... what we got here

    21. WMWill Marshall33:16

        ... I mean, what do you wanna ... Uh, the, but the coolest thing before-

    22. MOMolly O'Shea33:18

        Okay

    23. WMWill Marshall33:18

        ... we do that is not only that we can zoom in, is that we can ask it questions-

    24. MOMolly O'Shea33:23

        Mm-hmm

    25. WMWill Marshall33:23

        ... and we have tied an LLM to the backend. So LLMs really only trained on the text of the internet, so they didn't know much of real, the real world.

    26. MOMolly O'Shea33:31

        Yeah.

    27. WMWill Marshall33:32

        We have all the real world-

    28. MOMolly O'Shea33:33

        Mm-hmm

    29. WMWill Marshall33:33

        ... and we mate them together, and then you have a system that can understand all of human knowledge and tap into real-world stuff. So what does that mean? It means if you're a farmer and you want to understand your crop yields, a normal LLM chat is gonna tell you about the theory of agriculture, but it doesn't know shit about your field, right?

    30. MOMolly O'Shea33:52

        [laughs] Yeah.
20. 37:31 – 39:49

    The room where satellite radios are tested

    1. WMWill Marshall37:31

       floor, so.

    2. MOMolly O'Shea37:31

       This is the first time anybody has seen this floor. [laughs]

    3. WMWill Marshall37:35

       It's true. You're the first one to come in.

    4. MOMolly O'Shea37:36

       [laughs]

    5. WMWill Marshall37:37

       Yeah. [laughs] All right. So actually, I can show you just a couple of things before we sit down. Um, but these, this is the so-called dove nest.

    6. MOMolly O'Shea37:50

       Oh.

    7. WMWill Marshall37:50

       So this is where we've built all the doves-

    8. MOMolly O'Shea37:52

       Mm

    9. WMWill Marshall37:52

       ... and they're sitting in their nest waiting for the launch. So you can see they're two by two in there.

    10. MOMolly O'Shea37:57

        Quite the difference from the garage you started in.

    11. WMWill Marshall38:01

        Yeah, it's a little bit more substantive. That's true. Oh, and there's one more fun thing-

    12. MOMolly O'Shea38:04

        You can go on over. [laughs]

    13. WMWill Marshall38:05

        Thank you. You can put it back. Um, one more fun thing for you to see in here.

    14. MOMolly O'Shea38:09

        Okay.

    15. WMWill Marshall38:09

        Um, so here. You have to go in there-

    16. MOMolly O'Shea38:13

        Oh

    17. WMWill Marshall38:13

        ... both of you.

    18. MOMolly O'Shea38:14

        Do you wanna go first? [laughs]

    19. WMWill Marshall38:19

        Um-

    20. MOMolly O'Shea38:19

        Is this where you scream?

    21. WMWill Marshall38:20

        Yeah, exactly. I'm gonna shut the door-

    22. MOMolly O'Shea38:22

        Okay

    23. WMWill Marshall38:22

        ... and then you can just talk a little bit.

    24. MOMolly O'Shea38:24

        Okay. So we are here at Planet Labs, um, in San Francisco, and now we are trapped inside. [laughs]

    25. WMWill Marshall38:32

        Catch that?

    26. MOMolly O'Shea38:33

        Yeah.

    27. WMWill Marshall38:34

        It's cool, right? This is-

    28. MOMolly O'Shea38:34

        It's really cool. [laughs]

    29. WMWill Marshall38:35

        So this is where we test the radios to, um, to go to space.

    30. MOMolly O'Shea38:40

        Faraday cage or is it a soundproof room? What is it?

Episode duration: 39:53