1 00:00:00,032 --> 00:00:03,804 We don't have a data problem. We have a decision problem. 2 00:00:04,269 --> 00:00:07,961 How can we parse the data in a way that allows us to 3 00:00:07,961 --> 00:00:11,284 have the context that we need to make an 4 00:00:11,332 --> 00:00:15,168 operational decision now when every 5 00:00:15,265 --> 00:00:18,796 minute or every hour has cost and increased 6 00:00:18,812 --> 00:00:22,536 risk associated with it? So it's not the data side, it's 7 00:00:22,648 --> 00:00:26,453 how do we boil all of that data down and filter it into 8 00:00:26,453 --> 00:00:29,905 the key decisions that we need to make today. 9 00:00:30,228 --> 00:00:33,839 Industrial companies don't have a data problem, they have a decision problem. 10 00:00:34,342 --> 00:00:38,067 Andy Pruitt explains how AI can turn mountains of sensor data 11 00:00:38,310 --> 00:00:41,550 into smarter, faster decisions about physical asset risk. 12 00:00:42,117 --> 00:00:43,057 Welcome to Data Driven. 13 00:00:51,462 --> 00:00:54,962 Hello and welcome back to Data Driven, the podcast where we explore the 14 00:00:54,962 --> 00:00:58,785 emerging industry of data science, artificial intelligence, 15 00:00:58,993 --> 00:01:02,590 and without data engineering, all of it is for nothing. 16 00:01:03,104 --> 00:01:06,861 My favoritest data engineer in the world is unable to make it today. 17 00:01:06,942 --> 00:01:10,618 However, I do bring you a different Andy. Today's guest is 18 00:01:10,795 --> 00:01:13,412 Andy Pruitt, who is a 19 00:01:14,649 --> 00:01:18,438 co-founder and CEO at Lumiscent. Lumiscent. Let 20 00:01:18,438 --> 00:01:21,890 me say that again. As the co-founder and CEO of Lumiscent, 21 00:01:22,356 --> 00:01:25,982 And he drives the vision and execution of innovative 22 00:01:25,982 --> 00:01:29,592 solutions that optimize asset performance, reduce risks, 23 00:01:30,137 --> 00:01:33,892 and enhance customer financial outcomes. Welcome to the show, Andi. 24 00:01:34,806 --> 00:01:38,031 Hey, thanks for having us, Frank, and welcome to the Lumisphere. 25 00:01:38,897 --> 00:01:42,588 Nice, nice. I like it. I like it. Next thing you'll have an attraction in 26 00:01:42,668 --> 00:01:46,390 Vegas. Yeah, yeah, yeah. And it's good that— it's 27 00:01:46,438 --> 00:01:49,711 never good when Andi Leonard isn't here, but at least I don't have to get 28 00:01:49,727 --> 00:01:53,147 confused between the 2 Andis. But so tell us about your company. 29 00:01:53,500 --> 00:01:57,323 What is it that you do? And in the virtual green room, we did mention 30 00:01:57,339 --> 00:02:00,904 IoT. And I know that IoT is a— 31 00:02:02,013 --> 00:02:05,177 you don't hear that term as much anymore. You hear physical AI, you hear 32 00:02:05,868 --> 00:02:09,289 IoT seems to be falling out of favor within 33 00:02:09,722 --> 00:02:13,160 the industry, probably because the S in IoT stands for 34 00:02:13,160 --> 00:02:16,790 security. Yeah. Which is a joke that I thought everyone had 35 00:02:16,790 --> 00:02:20,499 heard. But apparently yesterday I said it to somebody and She laughed, 36 00:02:20,547 --> 00:02:24,267 so here we go. We're living in a post-widget 37 00:02:24,267 --> 00:02:28,099 era, Frank. We want the proper insights and outcomes from 38 00:02:28,164 --> 00:02:31,499 whatever devices we have on the shop floor. Lumasent is the 39 00:02:31,611 --> 00:02:34,433 intelligence layer for physical operations, so 40 00:02:34,770 --> 00:02:38,378 specifically decision intelligence for physical asset risk. 41 00:02:39,661 --> 00:02:42,579 So who is your primary 42 00:02:43,253 --> 00:02:46,877 customer base? Is it industry? Is it— you deal with the 43 00:02:47,438 --> 00:02:51,262 SCADA drivers or the software layer on top of that, or you feeding the data 44 00:02:51,262 --> 00:02:53,688 into a pipeline? Like, where do you sit on that stack? 45 00:02:54,989 --> 00:02:58,154 So if you think about traditional operation 46 00:02:58,749 --> 00:03:02,155 with the various levels of software, whether it's 47 00:03:02,267 --> 00:03:05,802 ERP, SCADA, manufacturing execution, building 48 00:03:05,802 --> 00:03:09,031 control systems, all the way up the stack, we are the 49 00:03:09,111 --> 00:03:12,935 first kind of platform that is solely focused on 50 00:03:13,112 --> 00:03:16,898 the risk layer. And so that's our core kind 51 00:03:16,914 --> 00:03:20,393 of focus area. And reason being is that over half the 52 00:03:20,409 --> 00:03:23,985 industry doesn't have dedicated asset risk managers. So how 53 00:03:24,113 --> 00:03:27,945 can we create visibility from an asset risk 54 00:03:27,945 --> 00:03:31,216 standpoint into that stack in an 55 00:03:31,232 --> 00:03:34,968 unencumbered way that allows you the information that you need 56 00:03:35,016 --> 00:03:38,864 to make decisions around physical asset risk? So 57 00:03:38,864 --> 00:03:42,665 how do we find gold in the data that we're generating? by 58 00:03:42,793 --> 00:03:46,534 consolidating it, analyzing it, and then providing direction, 59 00:03:46,903 --> 00:03:49,376 next step direction to the people that are using it. 60 00:03:50,580 --> 00:03:53,823 Interesting. What is physical asset risk? What do you mean? 61 00:03:54,128 --> 00:03:57,885 That's a great question. Yeah. Physical asset risk could 62 00:03:57,885 --> 00:04:01,642 be any failure that you have. And let's 63 00:04:01,642 --> 00:04:05,223 say you're in a food plant, single points of failure 64 00:04:05,608 --> 00:04:09,123 sometimes aren't always abundantly clear. So if you're in a food 65 00:04:09,203 --> 00:04:12,971 plant, like your makeup air system, so if you think about a big food 66 00:04:13,036 --> 00:04:16,884 production facility, usually on the roof they got this big jet motor that's 67 00:04:16,884 --> 00:04:20,428 creating negative air in the facility, because if that's offline, then we may 68 00:04:20,428 --> 00:04:24,164 suck a whole bunch of dust and debris into the facilities and contaminate food. 69 00:04:24,597 --> 00:04:27,996 So that single point of failure is a risk asset. 70 00:04:28,541 --> 00:04:32,261 If it fails during operations, 71 00:04:32,614 --> 00:04:36,463 likely that's a business interruption claim. So likely they there's going to be 72 00:04:36,463 --> 00:04:39,691 an insurance claim that is associated with that failure. 73 00:04:40,333 --> 00:04:43,834 So we're really there to help manage those single points of 74 00:04:43,850 --> 00:04:47,479 failure in your organization that leave you exposed. 75 00:04:47,960 --> 00:04:51,606 So it's looking at that specific activity for those 76 00:04:51,654 --> 00:04:54,962 specific assets and pulling that information 77 00:04:55,154 --> 00:04:58,944 out so that you can make decisions today on the things that 78 00:04:58,944 --> 00:05:02,445 are going to cause failure in your environment that may cause an 79 00:05:02,557 --> 00:05:06,392 undue exposure. Does that make sense? Oh, that makes a lot of sense. So 80 00:05:06,424 --> 00:05:09,825 it's that type of asset risk because that could— it was, it was 81 00:05:09,938 --> 00:05:13,788 interesting because asset risk could mean a lot of different things to a lot 82 00:05:13,788 --> 00:05:17,253 of different people, right? I might— started my career in finance, so when I heard 83 00:05:17,301 --> 00:05:21,055 that, I was like, doesn't jive with the physical AI aspect of this. 84 00:05:21,247 --> 00:05:24,776 But what you said makes a lot of sense. I totally appreciate it. When I 85 00:05:24,840 --> 00:05:28,338 do say asset risk, a lot of people immediately go to 86 00:05:28,370 --> 00:05:31,819 financial risk. The 2 things are related, right? 87 00:05:32,156 --> 00:05:35,077 But we're talking about the physical 88 00:05:35,687 --> 00:05:39,297 machinery, the physical operations that when 89 00:05:39,297 --> 00:05:42,748 they're impacted, they cause a downstream financial 90 00:05:42,812 --> 00:05:46,390 risk. And so one of the things that we highlight 91 00:05:46,743 --> 00:05:49,969 is 6 different dimensions of risk. So when we're 92 00:05:49,969 --> 00:05:53,499 classifying those assets, what could happen if they 93 00:05:53,499 --> 00:05:56,869 fail? Is this an environmental— Right. Is it a strategic 94 00:05:56,934 --> 00:06:00,705 risk? It is a supply chain risk. 95 00:06:01,042 --> 00:06:04,619 So it's quantifying the downstream impact of that 96 00:06:04,715 --> 00:06:08,565 individual asset failure. And the dollars associated with 97 00:06:08,565 --> 00:06:12,094 it, it is financial risk directly related, 98 00:06:12,415 --> 00:06:16,169 just outside of the banking industry. And I'll give you an example. You can have 99 00:06:16,345 --> 00:06:20,019 risk exposures and single point of failures that could be half a billion 100 00:06:20,051 --> 00:06:23,500 dollars or more. So there are, are big 101 00:06:23,500 --> 00:06:27,350 exposures here that we're talking about. It's not small dollar with single points 102 00:06:27,350 --> 00:06:31,197 of failure. And I would imagine that if you can quantify that to 103 00:06:31,197 --> 00:06:34,948 a real number, so what, you can imagine somebody, maybe 104 00:06:34,948 --> 00:06:38,699 not in the food industry, but, oh, the HVAC system goes down, right? What does 105 00:06:38,715 --> 00:06:41,697 that mean? That, so what is that? So what, you call somebody and they fix 106 00:06:41,697 --> 00:06:44,470 it? But if you can quantify that, no, the downstream effect of this is, 107 00:06:45,688 --> 00:06:49,166 in the extreme case, probably half a billion dollars, now you gotta get the board's 108 00:06:49,166 --> 00:06:52,965 attention. When you think about how we've designed 109 00:06:53,061 --> 00:06:56,366 our industrial systems to really absorb 110 00:06:56,366 --> 00:07:00,108 failure instead of building risk as 111 00:07:00,220 --> 00:07:03,320 infrastructure and then using data to drive those 112 00:07:03,352 --> 00:07:07,175 decisions around risk. We need 113 00:07:07,207 --> 00:07:10,981 to shift our thinking around it because things may not be quite 114 00:07:10,981 --> 00:07:14,466 as intuitive as we think they are, Frank. We may not think about a 115 00:07:14,514 --> 00:07:18,289 single leak depending on where it happens taking down 116 00:07:18,289 --> 00:07:22,095 the entire operation, right? We think about those things as, hey, They're going 117 00:07:22,095 --> 00:07:25,883 to happen eventually. We've got to deal with them. We can design systems not only 118 00:07:25,995 --> 00:07:29,702 to absorb the failure, but to alert us early on those things because 119 00:07:29,750 --> 00:07:33,570 we're on an industrial site. You have leaks that come up all the 120 00:07:33,618 --> 00:07:37,293 time. Where are the important ones? The one that's gushing 1,000 121 00:07:37,534 --> 00:07:41,065 liters a second or a minute. So it's really 122 00:07:41,145 --> 00:07:44,628 understanding the context of where the risk exists 123 00:07:44,917 --> 00:07:48,705 and then highlighting when it bubbles to the top. What do I need to 124 00:07:48,705 --> 00:07:52,493 do right now? Because you think about the amount of information that's 125 00:07:52,557 --> 00:07:55,864 flying at you at an industrial site, it's hard to 126 00:07:55,864 --> 00:07:59,460 parse. Think about today, all the social 127 00:07:59,460 --> 00:08:02,767 media that you get, all the bombardment of information. 128 00:08:03,217 --> 00:08:06,893 How do you surf through all that stuff to find 129 00:08:07,166 --> 00:08:10,987 the information that you really need or you're really discovering? The same thing 130 00:08:11,003 --> 00:08:14,695 happens in big business, right? Our customers are heavy industry, so it's 131 00:08:14,888 --> 00:08:18,685 Mining, oil and gas, forest products, heavy industry manufacturing, 132 00:08:19,037 --> 00:08:22,642 and they're being asked to make decisions faster 133 00:08:23,107 --> 00:08:26,952 with less information. So how do we, one, give them 134 00:08:26,952 --> 00:08:30,413 better information and better data to drive the decisions they have to make, 135 00:08:30,734 --> 00:08:34,323 but contextualize it in a fashion where it's really understood? 136 00:08:34,755 --> 00:08:38,584 So it's intelligence with integrity, but it's also 137 00:08:38,729 --> 00:08:42,318 driving contextual awareness of the decisions that have to be made 138 00:08:42,494 --> 00:08:46,181 around asset risk. That makes a lot of sense because all these industrial 139 00:08:46,838 --> 00:08:50,143 organizations and entities are probably— there's sensors everywhere now, 140 00:08:50,832 --> 00:08:54,457 right? This isn't the early 2000s, right? There's sensors on everywhere and 141 00:08:54,457 --> 00:08:58,275 everything, but they're probably just spewing tons and tons 142 00:08:58,307 --> 00:09:01,996 of data. So we are— sorry, Frank, go ahead. 143 00:09:02,189 --> 00:09:05,621 No, go ahead, go ahead. We have plenty of data, but we don't make use 144 00:09:05,621 --> 00:09:09,407 of that. What do you make of that? You're bang on. 145 00:09:09,776 --> 00:09:13,466 We don't have a data problem. We have a decision problem. 146 00:09:13,931 --> 00:09:17,619 How can we parse the data in a way that allows us to 147 00:09:17,619 --> 00:09:20,939 have the context that we need to make an 148 00:09:20,987 --> 00:09:24,820 operational decision now, when every 149 00:09:24,916 --> 00:09:28,444 minute or every hour has cost and increased 150 00:09:28,460 --> 00:09:32,213 risk associated with it? So it's not the data side, it's 151 00:09:32,293 --> 00:09:36,094 how do we boil all of that data down and filter it into 152 00:09:36,094 --> 00:09:39,567 the key decisions that we need to make today, 153 00:09:39,977 --> 00:09:40,895 that we need to make now. 154 00:09:43,310 --> 00:09:46,755 Interesting. Volume of data. This goes back 155 00:09:47,127 --> 00:09:50,524 years ago, but I was trying to highlight 156 00:09:51,026 --> 00:09:54,849 the sheer volume of data we were trying to deal with. And this 157 00:09:54,898 --> 00:09:58,441 is a mining example. So I was giving a presentation at the 158 00:09:58,441 --> 00:10:02,101 time. It was when 1 gigabyte thumb drives were brand 159 00:10:02,150 --> 00:10:05,066 new. And you and I are old enough where we remember That was a big 160 00:10:05,066 --> 00:10:08,535 deal. It was a big deal. And I came out on 161 00:10:08,584 --> 00:10:12,230 stage and I pulled out my thumb drive and I said, this holds 1 162 00:10:12,407 --> 00:10:15,956 gigabyte of data. How much data 163 00:10:16,438 --> 00:10:19,779 do you think we have as an organization? And this is 164 00:10:20,133 --> 00:10:23,634 advising a major corporation. So we have enough of these 165 00:10:23,811 --> 00:10:26,558 thumb drives to fill a ship the size of the 166 00:10:27,056 --> 00:10:30,751 Titanic. Wow. And that's 167 00:10:30,879 --> 00:10:34,240 all data, corporate financial, geologic, health, safety, 168 00:10:34,352 --> 00:10:38,098 environmental risk, asset, and its compounded 169 00:10:38,114 --> 00:10:41,433 growth is 10% a year. So 170 00:10:43,028 --> 00:10:46,234 how do we actually parse through that volume of data to 171 00:10:46,331 --> 00:10:49,842 find the specific information that we need, 172 00:10:50,277 --> 00:10:53,788 turn it into knowledge that allows us to execute on it? 173 00:10:54,384 --> 00:10:58,063 That's kind of a needle in a haystack problem. But I think the era that 174 00:10:58,095 --> 00:11:01,749 we're living in now, where we have the right tools, 175 00:11:02,327 --> 00:11:05,452 as long as it has the right harness around it, I think we have a 176 00:11:05,452 --> 00:11:09,203 way to parse that data. And if we have specific subject 177 00:11:09,252 --> 00:11:12,955 matter expertise, then those things can be more 178 00:11:13,147 --> 00:11:16,866 agentically driven. That makes a lot of sense. And I, 179 00:11:16,930 --> 00:11:19,847 when you say subject matter expertise, I would imagine 180 00:11:21,034 --> 00:11:24,192 a few years ago would have been human only, but now I think we're talking 181 00:11:24,208 --> 00:11:27,831 about some kind of hybrid of human and some kind of AI subject matter 182 00:11:27,831 --> 00:11:31,169 expertise. I think you have to have hybrid, 183 00:11:31,667 --> 00:11:35,054 right? I think you have to have a hybrid solution. You look at the 184 00:11:35,054 --> 00:11:38,554 industries that we serve, Frank, and 2029, 185 00:11:39,147 --> 00:11:42,583 which is what, 3 years away, 4 years away? Scarily, 186 00:11:42,679 --> 00:11:45,986 yes, 3 years away. That means 187 00:11:46,275 --> 00:11:49,823 3 quarters of the people that I came up with in 188 00:11:49,823 --> 00:11:53,162 industry will be retired. They're gone. So no longer is 189 00:11:53,612 --> 00:11:57,369 it a 10-year time horizon. We're within 3 years, so 190 00:11:57,369 --> 00:12:00,757 it's happening every day. And when that knowledge 191 00:12:00,885 --> 00:12:04,241 walks out, it is impossible to replace 192 00:12:04,899 --> 00:12:08,384 because there's just not enough people entering the industry, whether it's a risk manager, 193 00:12:08,753 --> 00:12:12,157 whether it's maintenance managers, whether it's trades, your 194 00:12:12,221 --> 00:12:15,256 millwrights, your electricians, your, your Red 195 00:12:15,256 --> 00:12:18,499 Seal-type carpenters, right? So we have to 196 00:12:19,206 --> 00:12:23,043 provide tools. that enable them to make better decisions when they 197 00:12:23,043 --> 00:12:26,672 don't necessarily have the longevity or operating context 198 00:12:26,672 --> 00:12:30,253 to make those decisions because they just haven't been in industry that long. 199 00:12:31,650 --> 00:12:35,214 Wow. Yeah, no, I think that there's some kind of— people talk about the 200 00:12:35,246 --> 00:12:39,003 job apocalypse, but I also think there's a retirement apocalypse, and 201 00:12:39,036 --> 00:12:41,139 particularly in the trades, I would say. 202 00:12:42,632 --> 00:12:45,811 Absolutely, absolutely. And those senior people too. 203 00:12:46,390 --> 00:12:49,939 Sometimes they'll come back, do contract work, but they don't want to deal with any 204 00:12:49,972 --> 00:12:53,618 of the corporate stuff, right? 205 00:12:54,070 --> 00:12:57,874 Hey, I can help you to achieve this objective, but I only want to 206 00:12:57,874 --> 00:13:01,594 do that. And then I want to go back to being retired. Yeah, I imagine 207 00:13:01,594 --> 00:13:04,460 that there's going to be a lot of people that are going to be called 208 00:13:04,460 --> 00:13:07,629 out of retirement and things like that. And you're seeing that also in the tech 209 00:13:07,629 --> 00:13:11,441 sphere too, where companies are offering early retirement to people who 210 00:13:11,714 --> 00:13:15,355 literally built the company, right? Yeah. And I understand they have 211 00:13:15,355 --> 00:13:19,076 reasons, they have their financial reasons, right or wrong, but I 212 00:13:19,188 --> 00:13:22,283 just think that they're throwing out the baby with the bathwater when it comes with 213 00:13:22,315 --> 00:13:25,731 the, the institutional knowledge to do it that quickly and that 214 00:13:25,780 --> 00:13:28,923 rapidly. I, I just, I think we're gonna see the long-term 215 00:13:28,971 --> 00:13:32,531 consequences of that in short order. I, 216 00:13:33,542 --> 00:13:37,230 I totally agree. And that's what LumaSint is here to help 217 00:13:37,230 --> 00:13:41,031 solve for, is to help you make those decisions, capture the 218 00:13:41,031 --> 00:13:44,672 information, make those decisions so that you don't lose 219 00:13:44,929 --> 00:13:48,636 step when you lose resources. So you can maintain some 220 00:13:48,636 --> 00:13:51,974 consistency and contextual awareness. So it really is 221 00:13:52,487 --> 00:13:56,226 driving that decision intelligence that comes from a place of authority. 222 00:13:57,125 --> 00:14:00,880 And the other way I like to think about it too is this is 223 00:14:00,992 --> 00:14:04,716 not— what we focus on too is not general 224 00:14:04,844 --> 00:14:07,957 purpose. It is specific. Right. So our 225 00:14:08,053 --> 00:14:11,808 expertise is a wedge. So if you think about Everyone talks about like 226 00:14:11,808 --> 00:14:15,561 council of agents doing things. Right. We're really focused on 227 00:14:15,593 --> 00:14:19,281 that asset risk in heavy industry. That's our focus area. 228 00:14:19,682 --> 00:14:22,970 And we're deep, deep on that subject. So 229 00:14:23,435 --> 00:14:27,108 we want to make sure that people understand that when we're 230 00:14:27,124 --> 00:14:30,877 looking at risk, it can't be good enough, right? 231 00:14:31,294 --> 00:14:34,212 It needs to be contextual. It needs to be 232 00:14:34,742 --> 00:14:38,527 validated and it needs to be validatable. We like 233 00:14:38,527 --> 00:14:42,326 to say intelligence with integrity. In that we can show you the math 234 00:14:42,679 --> 00:14:46,430 of how a decision was arrived at. So that's a— that 235 00:14:46,446 --> 00:14:49,988 was a good segue into my next question is a sensor 236 00:14:49,988 --> 00:14:53,723 detects an anomaly, maybe a family of sensors that are related. What happens 237 00:14:53,755 --> 00:14:57,281 between signal and making a 238 00:14:57,281 --> 00:15:00,808 decision? Because I would imagine that capturing the data, capturing the signal, 239 00:15:01,353 --> 00:15:04,574 that used to be a technical hurdle. I think that's— those days are gone. But 240 00:15:04,574 --> 00:15:08,181 now I think the last mile problem is very real. You have all this data, 241 00:15:08,662 --> 00:15:12,500 You have all this. Okay, now what? How do you make a decision? And 242 00:15:12,516 --> 00:15:15,856 then obviously different time horizons and things like that. How do you— 243 00:15:16,370 --> 00:15:19,341 what happens after that? Yeah, the 244 00:15:20,128 --> 00:15:23,885 signal through capture needs 245 00:15:23,902 --> 00:15:27,691 to take the next step. So we've got the first mile out of 246 00:15:27,691 --> 00:15:31,497 the way, to your point. I think we've got the sensor stuff figured out. 247 00:15:31,706 --> 00:15:35,303 I think we have most of the infrastructure figured out. We know how to collect 248 00:15:35,303 --> 00:15:38,773 the data. We know how to consolidate it. We even know how to put 249 00:15:38,773 --> 00:15:41,954 together good dashboards, right? Lots of blinking lights. 250 00:15:42,693 --> 00:15:46,131 But I've also encountered over the last half a dozen years 251 00:15:46,645 --> 00:15:50,212 that people are blind to dashboards now. So we've gotten to this 252 00:15:50,244 --> 00:15:53,956 level where the dashboards has gotten us so far, we've 253 00:15:53,956 --> 00:15:57,779 got to take the next step, which is what are the decisions that 254 00:15:57,795 --> 00:16:01,201 have to be made based on the data that we have? Right. And so 255 00:16:01,442 --> 00:16:05,185 it's no longer signal, gather the 256 00:16:05,185 --> 00:16:09,007 data, turn it into some level of a 257 00:16:09,200 --> 00:16:12,814 base of knowledge, and then turn those into actionable 258 00:16:12,814 --> 00:16:16,524 outcomes. You really need to do that as a whole stack 259 00:16:16,764 --> 00:16:20,603 in order to go beyond the dashboard. So it, 260 00:16:20,699 --> 00:16:24,120 it's really driving that decision intelligence by being 261 00:16:24,233 --> 00:16:27,750 smart about the data that you look at, the data that you collect, 262 00:16:28,071 --> 00:16:31,749 how you parse it, and how it drives those decisions. 263 00:16:31,877 --> 00:16:35,506 So it really is beyond the signal because sometimes it's too 264 00:16:35,539 --> 00:16:39,232 much, right? Let's take a one-sensor example. You can have a 265 00:16:39,232 --> 00:16:42,572 high-fidelity sensor on your shop floor that generates 266 00:16:43,022 --> 00:16:46,555 50 gigs worth of data in a year. Right. It's delivering 267 00:16:46,715 --> 00:16:50,425 more if it's streaming. What's important in that data 268 00:16:50,875 --> 00:16:54,616 was the anomaly that I was able to detect and the resource 269 00:16:54,649 --> 00:16:58,178 that I was able to get to that anomaly to address it before it turned 270 00:16:58,178 --> 00:17:02,009 into a larger issue. So I'm even 271 00:17:02,602 --> 00:17:06,448 like thinking about this is not predictive because that's where we always go. 272 00:17:06,769 --> 00:17:10,167 Isn't— aren't you talking about predictive maintenance? No, I'm talking about 273 00:17:10,199 --> 00:17:13,709 prioritizing the risk that's coming through a signal 274 00:17:14,141 --> 00:17:17,956 so you know what to do today. Wow. The predictive stuff is 275 00:17:18,052 --> 00:17:21,786 great. There are people that, that are really awesome in that 276 00:17:21,914 --> 00:17:25,280 space that are telling you 6 months from now this is going to 277 00:17:25,280 --> 00:17:29,052 happen. We're talking about the operational block and tackle of risk. 278 00:17:29,357 --> 00:17:32,488 What do I need to do today? What do I need to do tomorrow? What 279 00:17:32,488 --> 00:17:36,278 do I need to do on Friday? This seems like the tactical version of preventative 280 00:17:36,278 --> 00:17:39,505 maintenance. It seems like your heads-up 281 00:17:39,505 --> 00:17:42,411 display that's really going to help to drive better 282 00:17:42,459 --> 00:17:45,928 decisions around physical asset risk. 283 00:17:47,180 --> 00:17:50,183 Interesting. Interesting. So 284 00:17:51,756 --> 00:17:55,538 Not all anomalies are created equal, right? So obviously 285 00:17:55,538 --> 00:17:58,903 there has to be some kind of way to determine, because we're 286 00:17:58,903 --> 00:18:02,621 beyond, you know, you're working beyond, way beyond kind of traditional 287 00:18:02,893 --> 00:18:06,483 predictive maintenance, right? Not all anomalies are created equal. 288 00:18:07,220 --> 00:18:10,794 Not all breakdowns are created equal. How do you 289 00:18:11,066 --> 00:18:14,656 address that? Obviously there's gotta be some kind of, you mentioned blocking and tackling, 290 00:18:14,752 --> 00:18:18,037 obviously you wanna block the big— Yeah. You don't wanna block the biggest guy on 291 00:18:18,037 --> 00:18:21,546 the other team, but you wanna block the, I'm gonna use an American football analogy, 292 00:18:21,579 --> 00:18:24,562 sorry for my European friends, and global listeners, 293 00:18:25,092 --> 00:18:28,788 but you want to block the guy who is about to tackle your quarterback, 294 00:18:28,820 --> 00:18:31,471 not the biggest guy, right? And I think that 295 00:18:31,857 --> 00:18:35,456 traditional preventive maintenance blocks the most 296 00:18:35,456 --> 00:18:39,281 obvious threat, but, or the, the biggest guy on the other team. 297 00:18:39,554 --> 00:18:42,301 You want to protect your quarterback, right? That's really the, what you're trying to do. 298 00:18:43,040 --> 00:18:46,608 Absolutely. Those are the people who win games. Absolutely. 299 00:18:46,865 --> 00:18:50,221 I love your analogy and the framing of it. Because 300 00:18:50,654 --> 00:18:54,469 that's it, is that, hey, if my predictive maintenance strategy 301 00:18:54,501 --> 00:18:58,349 is focused solely inside plant on rotating equipment, but 302 00:18:58,349 --> 00:19:01,988 I haven't looked at the sectional valves that supply my fresh 303 00:19:02,196 --> 00:19:05,883 water for my system, and that goes down and my 304 00:19:05,883 --> 00:19:09,635 plant catches on fire, what predictive maintenance system 305 00:19:09,635 --> 00:19:13,177 actually helped me drive production when my water's off? So 306 00:19:13,177 --> 00:19:17,010 it's making sure that you know where that little guy is going to come 307 00:19:17,010 --> 00:19:20,685 out of nowhere and take out your quarterback, even 308 00:19:20,717 --> 00:19:24,295 with all the big guys. So that's where our focus area is, 309 00:19:24,392 --> 00:19:28,034 that there's all these pieces that are inside and around plants 310 00:19:28,098 --> 00:19:31,853 that will catch you off guard. And normally we don't figure 311 00:19:31,869 --> 00:19:34,789 that out during the engineering of the plant because we're not 312 00:19:34,998 --> 00:19:38,801 designing risk as infrastructure. We're designing it 313 00:19:38,913 --> 00:19:42,299 for production outcomes. So yes, we design it to be hardy, we design it for 314 00:19:42,299 --> 00:19:45,654 the output, But as we build and 315 00:19:45,895 --> 00:19:49,137 operate, new context comes in, new 316 00:19:49,346 --> 00:19:53,022 risks that didn't necessarily occur when you actually built the operation. 317 00:19:53,070 --> 00:19:56,891 I'll give you a really good example about this. Let's say 318 00:19:56,891 --> 00:20:00,599 you're playing football and all of a sudden they put an autonomous robot on the 319 00:20:00,599 --> 00:20:04,067 field. Right. Changes the game, right? So we had a 320 00:20:04,131 --> 00:20:07,935 customer that came to us and said, look, we've started to put all 321 00:20:07,984 --> 00:20:11,340 these autonomous robots on the factory floor. And we didn't 322 00:20:11,436 --> 00:20:15,051 realize that they're heavy. And so they're using the 323 00:20:15,051 --> 00:20:18,682 same infrastructure on our walls and our ceiling where our lighting is 324 00:20:18,746 --> 00:20:22,184 hung, where our fire control systems are hung. It's 325 00:20:22,184 --> 00:20:25,992 causing a high level of vibration. We need all that stuff 326 00:20:26,056 --> 00:20:29,478 to work. How do we deal with that? We don't even have 327 00:20:29,976 --> 00:20:33,752 mass contextual awareness about robots coming into the factory floor, and now we 328 00:20:33,752 --> 00:20:37,561 have a risk that's being introduced almost in real time. That 329 00:20:37,561 --> 00:20:41,250 is impacting things like health, life, safety systems. So 330 00:20:41,491 --> 00:20:45,003 we have to be aware that game of football is going to change 331 00:20:45,421 --> 00:20:48,841 and we're going to have new dimensions that are added all the time. 332 00:20:49,328 --> 00:20:52,428 And it's not slow, Frank. I'm not talking about 2 years, this is going to 333 00:20:52,493 --> 00:20:56,259 change. It's next week, it's changing. It may be next 334 00:20:56,323 --> 00:20:58,745 month. There's a new operating context. 335 00:21:00,870 --> 00:21:04,395 No, and factories are not built for— factories are not like 336 00:21:04,395 --> 00:21:08,124 software, right? These things are built for Decades of run. 337 00:21:08,621 --> 00:21:11,880 And I don't have a lot of experience in manufacturing, but as a car guy, 338 00:21:12,024 --> 00:21:15,620 I kind of understand. If they change up the model of the Cadillac Escalade, they 339 00:21:15,620 --> 00:21:19,327 have to take down the assembly line and re-engineer it. 340 00:21:19,392 --> 00:21:22,281 But you're right. But these factories have probably 341 00:21:22,281 --> 00:21:26,037 been going part running, some of them probably 342 00:21:26,037 --> 00:21:29,359 the better, these buildings, these infrastructures, at least a century old. 343 00:21:30,611 --> 00:21:34,126 Yes, some of them are. We have customers that do have facilities that are 344 00:21:34,126 --> 00:21:37,736 100 years old. But it's also the new stuff that's being 345 00:21:37,849 --> 00:21:41,683 built as well, is that— Right. We're always trying to drive optimization, 346 00:21:41,699 --> 00:21:45,164 and that's a nice way of saying we're trying to optimize for cost. 347 00:21:45,854 --> 00:21:48,678 And so we don't end up getting all of the 348 00:21:49,480 --> 00:21:53,234 risk infrastructure that we necessarily need as part of the project. So 349 00:21:53,250 --> 00:21:56,635 how do we enable those customers by having something that's really 350 00:21:56,764 --> 00:22:00,486 quick to set up, really quick to deploy, really 351 00:22:00,486 --> 00:22:04,063 quick to gather information, and really quick to drive decision 352 00:22:04,063 --> 00:22:07,580 intelligence? I think that's very important to our customers is 353 00:22:07,676 --> 00:22:11,515 just speed. Is this is happening to us, how quickly can you 354 00:22:11,547 --> 00:22:15,177 help us address this challenge that's coming up? In the 355 00:22:15,177 --> 00:22:18,694 field, whoever adopts this faster is going to get better 356 00:22:18,694 --> 00:22:22,115 profits, better, better output, better, ultimately better profits, and 357 00:22:22,147 --> 00:22:25,328 potentially put you out of business. There's definitely a real, 358 00:22:26,066 --> 00:22:29,809 there's definitely a real motivator there. I think another analogy would be my wife and 359 00:22:29,841 --> 00:22:32,747 I are house hunting. And we saw this beautiful 360 00:22:33,487 --> 00:22:37,314 farmhouse. This thing was built in the 1800s or something like that. And the cable, 361 00:22:37,845 --> 00:22:40,948 the coaxial cable is kind of stapled to the outside of the wall. 362 00:22:42,547 --> 00:22:46,279 And so, and I was, we were looking at the 363 00:22:46,279 --> 00:22:49,963 aesthetic problems of that. And it was just like, pretty sure they didn't have 364 00:22:49,996 --> 00:22:53,836 Cat5 in mind or co— you know, co— cable 365 00:22:53,868 --> 00:22:56,771 TV in mind when they built the house. Right. So you kind of have to— 366 00:22:57,196 --> 00:23:00,661 There's— in that example, it's just mostly 367 00:23:00,661 --> 00:23:04,399 aesthetics in terms of the cables showing. But if you look at newer construction, 368 00:23:04,976 --> 00:23:08,682 there's fiber optic cable inside the house in some extreme cases and things like 369 00:23:08,682 --> 00:23:12,339 that. Like, how far can you push old infrastructure? 370 00:23:13,799 --> 00:23:16,767 How far can you push it? I think we're at a breaking point. So you 371 00:23:16,767 --> 00:23:20,552 look at how far can you push old infrastructure? We've got something 372 00:23:20,552 --> 00:23:23,841 like 420,000 miles of unmonitored, 373 00:23:23,985 --> 00:23:27,530 unmanaged, like fresh and wastewater treatment systems across North 374 00:23:27,530 --> 00:23:31,367 America. So how far can you push it? Only so far until it breaks, 375 00:23:31,383 --> 00:23:35,075 and then there's an incredible amount of pain, right? We 376 00:23:35,139 --> 00:23:38,173 have, I think, the benefit of having 377 00:23:39,474 --> 00:23:43,150 designed, engineered, built, and operated 378 00:23:43,808 --> 00:23:47,195 feats of amazing infrastructure, whether it's our 379 00:23:47,195 --> 00:23:50,647 railroads, whether it was our bridges system, whether it is water 380 00:23:50,647 --> 00:23:54,468 treatment or wastewater treatment. I'm from Alaska originally, so I always 381 00:23:54,500 --> 00:23:58,154 go back the construction of the Trans-Alaska Pipeline. Right. And man, 382 00:23:58,330 --> 00:24:00,958 peak construction, that thing was a global— 383 00:24:01,855 --> 00:24:05,316 absolute global— one of the largest global projects in the world. 384 00:24:05,716 --> 00:24:09,385 Billions and billions of dollars being spent on its construction. And it's 385 00:24:09,401 --> 00:24:13,150 lasted for 40-some years. We don't build infrastructure 386 00:24:13,166 --> 00:24:16,948 like that anymore. And the infrastructure that we did build to that 387 00:24:16,996 --> 00:24:20,536 level, to that capability, is aging. And the vast 388 00:24:20,536 --> 00:24:23,981 majority of it, again, is not measured. It's not monitored. 389 00:24:24,302 --> 00:24:28,059 It's not managed. And our big goal is to be able to 390 00:24:28,059 --> 00:24:31,495 replace it. But the cost of it is just amazing. 391 00:24:31,993 --> 00:24:35,269 I think in the US, the infrastructure backlog is 392 00:24:35,365 --> 00:24:39,058 trillions and trillions of dollars of what needs just to replace the 393 00:24:39,154 --> 00:24:42,157 20% of either poor or 394 00:24:42,382 --> 00:24:45,304 dangerously poor deteriorated assets. 395 00:24:46,524 --> 00:24:48,965 Yeah, no, that's a sobering thought. 396 00:24:51,277 --> 00:24:54,360 What are the major points of failure in industrial AI, 397 00:24:55,371 --> 00:24:58,775 right? Are these bad? Because it sounds like what you do 398 00:25:00,269 --> 00:25:03,464 is a very comprehensive approach. You don't just look at the building, you look at, 399 00:25:03,544 --> 00:25:06,338 oh, this pipe fails this. There has to be some kind of 400 00:25:06,611 --> 00:25:10,272 human and expertise that you have to go in. And do you 401 00:25:10,449 --> 00:25:13,820 offer the services or do you offer the software or do you offer both? That 402 00:25:13,820 --> 00:25:16,968 would be my question. With our customers, we've 403 00:25:16,968 --> 00:25:20,741 got a program that's a luminaries program. 404 00:25:20,837 --> 00:25:24,578 So we partner with the businesses that want that extra 405 00:25:24,578 --> 00:25:28,047 help. Because what we found is that customers just don't want to 406 00:25:28,528 --> 00:25:31,708 buy software anymore. They want you to partner with them 407 00:25:32,205 --> 00:25:35,914 deeply. And I don't mean that like marketing partner. They want you to 408 00:25:35,914 --> 00:25:39,607 be helping to own the results that you're 409 00:25:39,607 --> 00:25:42,949 trying to drive. So it's not necessarily 410 00:25:42,965 --> 00:25:46,789 traditional consulting because when we're there for the life of the asset, 411 00:25:47,078 --> 00:25:50,211 we're there to help you throughout the life of the asset. And so when we're 412 00:25:50,757 --> 00:25:54,533 talking with you, it's about optimizing everything from maintenance strategy to risk 413 00:25:54,533 --> 00:25:57,891 strategy. So we're just looking at things slightly 414 00:25:58,003 --> 00:26:01,715 different. So yeah, we help customers with the software, but I think our 415 00:26:01,763 --> 00:26:05,474 human touch is something that's really important in today's kind 416 00:26:05,474 --> 00:26:09,229 of AI age. and the expertise we bring to the table, 417 00:26:09,245 --> 00:26:13,042 right? To find a company that actually has depth and expertise that 418 00:26:13,074 --> 00:26:16,487 can deeply partner to help walk you through that 419 00:26:16,600 --> 00:26:20,381 journey is important. And you said fairly comprehensive. We're 420 00:26:20,381 --> 00:26:23,955 comprehensive in our focus area. So we're not building 421 00:26:23,987 --> 00:26:27,816 control, we're not a process control system. We're 422 00:26:27,896 --> 00:26:31,326 looking at it again strictly from that risk lens for those 423 00:26:31,358 --> 00:26:35,066 60% of companies that don't have a dedicated asset risk manager. 424 00:26:35,436 --> 00:26:38,966 That's our piece of the pie where we focus. 425 00:26:41,046 --> 00:26:44,829 Interesting. Yeah, it seems like there's a lot of places where somebody 426 00:26:44,829 --> 00:26:48,387 can get distracted, right? In terms of like, 427 00:26:48,532 --> 00:26:51,255 because there's a lot of moving parts here, right? And I think that's an understatement. 428 00:26:56,537 --> 00:26:59,486 What, how do you start? It seems to me, for me, I'm looking at this 429 00:26:59,599 --> 00:27:02,789 as somebody who's not in industrial control and not in this industry. 430 00:27:03,556 --> 00:27:07,267 I look at these problems and I'm like, where do you start? It's not 431 00:27:07,267 --> 00:27:10,962 just blueprints. You actually have to walk around and kick the dirt around, right? And 432 00:27:10,962 --> 00:27:14,609 like, where do you start? Where does one start? I know that's a 433 00:27:14,658 --> 00:27:17,887 kind of a small question with a big answer. Frank, 434 00:27:18,032 --> 00:27:21,647 that's another great question. Where do you start? Where do we start? 435 00:27:22,386 --> 00:27:26,065 So all of our customers have an insurance partner, and 436 00:27:26,065 --> 00:27:29,551 that insurance partner has— most of them will 437 00:27:29,583 --> 00:27:32,922 have what's called risk engineer. Oh, okay. And that 438 00:27:33,051 --> 00:27:36,806 risk engineer is a subject matter expert that's 439 00:27:36,806 --> 00:27:39,968 coming in to define what are the things that need to be 440 00:27:39,968 --> 00:27:43,307 monitored, what are the things that need to be managed. And 441 00:27:43,708 --> 00:27:47,496 we're in to help after that. So we'll partner with 442 00:27:47,496 --> 00:27:51,267 those insurers, we'll partner with those risk engineers to make 443 00:27:51,267 --> 00:27:54,542 sure that once they've done their assessment and the report, that's 444 00:27:54,542 --> 00:27:58,377 translated into the system. So it's translated into what needs 445 00:27:58,409 --> 00:28:02,245 to be measured, monitored, and managed. So we meet 446 00:28:02,245 --> 00:28:05,760 the customer where they're at in terms of defining 447 00:28:05,888 --> 00:28:09,403 single points of failure. Usually they already know, right? They've got the data 448 00:28:09,563 --> 00:28:13,335 inside their environment, pulling out the things that are important and working with 449 00:28:13,335 --> 00:28:17,170 the risk engineer to be able to make sure that they're— everything that's 450 00:28:17,170 --> 00:28:19,802 been identified is monitored correctly. 451 00:28:20,348 --> 00:28:24,036 So that's where we start. And that 452 00:28:24,036 --> 00:28:27,560 risk engineer is probably not coming in cold, right? That risk engineer 453 00:28:27,608 --> 00:28:30,841 probably, you know, has worked— 454 00:28:30,841 --> 00:28:34,658 Long-term relationships. One of the reasons why we have 455 00:28:34,658 --> 00:28:38,396 an FM-approved product, and Factory Mutual 456 00:28:39,804 --> 00:28:43,307 is an engineering-based risk 457 00:28:43,452 --> 00:28:47,100 leader, but insurance company, and we make 458 00:28:47,229 --> 00:28:50,996 FM-approved products. FM approvals is their approvals 459 00:28:51,092 --> 00:28:54,818 division. So they focus on making sure the products that 460 00:28:54,963 --> 00:28:58,769 hold the FM logo have been tested to their most rigorous 461 00:28:58,994 --> 00:29:02,656 standards. FM, when they come in— and this is not 462 00:29:02,656 --> 00:29:06,045 us, right? We're the, we're the help block and tackle afterwards. You've 463 00:29:06,045 --> 00:29:09,787 decided what field looks— let's help you play the game. FM 464 00:29:10,140 --> 00:29:13,818 in 2025 wrote 48,000 465 00:29:13,899 --> 00:29:17,045 recommendations for their customers. Right? Wow. So 466 00:29:17,045 --> 00:29:20,589 48,000 things that we need to do to mitigate 467 00:29:20,813 --> 00:29:23,668 risks across all their customer base. That's one insurance company 468 00:29:24,486 --> 00:29:27,773 that covered almost $1 trillion in risk, 469 00:29:28,495 --> 00:29:32,328 those 48,000 recommendations. So now how do we take those 470 00:29:32,424 --> 00:29:35,840 48,000 recommendations and translate them into 471 00:29:35,952 --> 00:29:39,320 operational activity? What do we need to do to effectively manage them 472 00:29:39,577 --> 00:29:42,944 within the context of risk? So we 473 00:29:43,024 --> 00:29:46,519 partner deeply with our insurance partners who are very 474 00:29:46,855 --> 00:29:50,622 data-driven, Frank, very data-driven. But we're looking at the 475 00:29:50,622 --> 00:29:54,374 world slightly different in that we have engineered 476 00:29:54,390 --> 00:29:57,451 risk and we have actuarial risk, right? 477 00:29:58,317 --> 00:30:02,036 What's the difference? That's a great question. 478 00:30:02,485 --> 00:30:05,803 Engineered risk is based on, I've 479 00:30:05,803 --> 00:30:09,442 looked at the asset I understand 480 00:30:09,698 --> 00:30:13,529 how it's going to operate. I've written recommendations 481 00:30:13,561 --> 00:30:17,408 to mitigate everything from fire, flood, earthquake, tornado, 482 00:30:17,489 --> 00:30:20,823 whatever it is, but I'm making those recommendations 483 00:30:21,175 --> 00:30:24,942 based on a very long history that I've developed. 484 00:30:25,888 --> 00:30:29,719 Actuarial risk is what financial losses 485 00:30:29,975 --> 00:30:33,598 have I had and what financial losses have I had that can 486 00:30:33,742 --> 00:30:37,030 predict a loss in the future? So one is a 487 00:30:37,030 --> 00:30:40,271 financial activity and one is an 488 00:30:40,271 --> 00:30:43,866 engineering and field activity. And so insurance 489 00:30:43,866 --> 00:30:46,450 companies are split behind 2 lines: 490 00:30:47,060 --> 00:30:50,526 actuarial-based risk or engineering-based risk. 491 00:30:50,991 --> 00:30:54,410 We're solidly in the— we're there to help with your 492 00:30:54,538 --> 00:30:58,149 engineered-based risk outcomes, even though it has big 493 00:30:58,149 --> 00:31:01,711 implications for the actuarial risk outcomes as well. 494 00:31:02,225 --> 00:31:06,063 But we have to follow the physical operations. So that's where we're focused. is 495 00:31:06,159 --> 00:31:08,808 on that engineered risk side. 496 00:31:09,713 --> 00:31:13,347 Interesting. Interesting. It's such a fascinating world I didn't really 497 00:31:13,363 --> 00:31:15,765 think about. You think about 498 00:31:18,195 --> 00:31:21,881 factories and you think about, as long as you have an eyewash station and things 499 00:31:21,897 --> 00:31:25,617 like this, and you don't really think about, at least from my point of view, 500 00:31:25,665 --> 00:31:29,508 right? This is a whole world that's completely new to me. It's fascinating. And 501 00:31:29,524 --> 00:31:33,055 I would imagine those 48,000 items that have been 502 00:31:33,119 --> 00:31:36,342 highlighted are probably triaged or would be 503 00:31:36,503 --> 00:31:40,159 dependent on whatever the individual factory would be, not even the industry, 504 00:31:40,207 --> 00:31:44,056 not even the customer, right? The individual facility probably has to 505 00:31:44,265 --> 00:31:47,023 get their own triage of X, Y, and Z. 506 00:31:48,034 --> 00:31:51,305 Yeah. And, and our job for those customers 507 00:31:51,899 --> 00:31:55,074 is to take that information and illuminate it. 508 00:31:55,571 --> 00:31:59,354 What are the important things? Let's put them in, let's 509 00:31:59,370 --> 00:32:03,184 manage them correctly, and let's do it quickly 510 00:32:03,761 --> 00:32:07,222 and cost-effectively because the risks that we're trying to manage 511 00:32:07,670 --> 00:32:11,003 have pretty big implications to the operation. Otherwise they wouldn't be 512 00:32:11,612 --> 00:32:15,457 on an engineered report. As something, let's take a little bit of a 513 00:32:15,457 --> 00:32:19,175 dogleg and this is definitely data-driven. I think you'll 514 00:32:19,175 --> 00:32:22,523 find it interesting. I love you're using our podcast name throughout the whole thing. I 515 00:32:22,588 --> 00:32:25,199 love that. That'll definitely help with the AI optimization. 516 00:32:26,339 --> 00:32:29,712 Yeah, I just need to get to say Lumicent 10 more times and it's like, 517 00:32:29,792 --> 00:32:33,390 no, actually— There you go. You look at what's happened in 518 00:32:33,487 --> 00:32:37,052 terms of what are called natural catastrophes, right? Fire, 519 00:32:37,117 --> 00:32:40,827 floods, earthquakes, hurricanes, stuff like that. In that 520 00:32:41,373 --> 00:32:44,794 you have insurers that have pulled out of entire markets, said, 521 00:32:45,212 --> 00:32:48,954 yeah, too much risk there, we're not going to write there anymore, 522 00:32:49,404 --> 00:32:53,178 whether it's floods in Florida, whether it's wildfires in 523 00:32:53,195 --> 00:32:56,698 California, it's the insurance company. Commerce protects 524 00:32:56,698 --> 00:33:00,054 itself, right, where it's protected. So in order 525 00:33:00,587 --> 00:33:04,204 to get back, get insurance companies 526 00:33:04,300 --> 00:33:06,544 back to the table, new 527 00:33:08,285 --> 00:33:12,123 ways of monitoring, measuring, and managing 528 00:33:12,155 --> 00:33:15,525 risk outcomes had to be created. And one of them is parametrics. 529 00:33:16,100 --> 00:33:19,442 Parametrics is something that Normally when I say that, if you're not in the 530 00:33:19,442 --> 00:33:23,248 insurance industry, you have no idea what it is. Parametrics is almost 531 00:33:23,248 --> 00:33:26,765 a product that was brought out to help mitigate 532 00:33:26,765 --> 00:33:30,538 risk for the consumer, whether it's the business and the insurance 533 00:33:30,538 --> 00:33:33,974 company. And a good example, and this is again, we make 534 00:33:33,974 --> 00:33:36,881 devices that help enable this type of stuff. We're not a 535 00:33:36,881 --> 00:33:40,574 parametric product, but for example, you've 536 00:33:40,574 --> 00:33:43,978 had, you have no insurance, you run a distribution 537 00:33:44,331 --> 00:33:47,974 facility in Florida. And you've been flooded so many times you can't get insurance. 538 00:33:49,152 --> 00:33:51,968 And then the insurance companies pulled out of the market. They came back in, but 539 00:33:51,968 --> 00:33:55,447 they said, we're going to give you a parametric product. Oh, what's that? We're going 540 00:33:55,447 --> 00:33:58,325 to pre-agree what your losses are 541 00:33:59,082 --> 00:34:02,769 based on the level of water. Hmm. So they go in and 542 00:34:02,866 --> 00:34:06,553 put a sensor on and say, look, water gets to 5 meters, 543 00:34:07,229 --> 00:34:10,765 we're going to pay out. We'll pay out within 72 hours. Gets to 10 544 00:34:10,830 --> 00:34:14,151 meters, We'll pay out, we'll pay out in 72 hours. So 545 00:34:14,215 --> 00:34:18,037 then you've pre-adjusted, not post-adjustment. You haven't 546 00:34:18,037 --> 00:34:20,993 had a loss and then had to have an underwriter come in and figure out 547 00:34:20,993 --> 00:34:24,462 what your losses are and then end up in court. You're pre-agreeing what that 548 00:34:24,510 --> 00:34:28,204 looks like, and you have a sensor that's actually the arbitrator 549 00:34:28,606 --> 00:34:30,854 of the risk event. So 550 00:34:32,059 --> 00:34:35,431 that's one component. You also have the— 551 00:34:35,817 --> 00:34:39,301 we're looking at satellite imagery. We're looking at roofing systems, 552 00:34:39,510 --> 00:34:43,248 we're looking at positioning in terms of where the facility's at. All 553 00:34:43,360 --> 00:34:46,825 of those risk components that are around it from the 554 00:34:46,825 --> 00:34:50,483 insurance side are tools the insurer is 555 00:34:50,579 --> 00:34:54,397 using to make your policy go up. And they're not intentionally trying to make your 556 00:34:54,445 --> 00:34:58,103 policy go up, they're trying to manage their risk. Right. Our job on behalf of 557 00:34:58,215 --> 00:35:01,231 our customers is to mitigate the risk as much as 558 00:35:01,263 --> 00:35:04,972 possible so that they can prove to the insurer that 559 00:35:04,972 --> 00:35:08,715 they've taken every step possible to be able to 560 00:35:08,780 --> 00:35:10,918 mitigate the risks that have been identified. 561 00:35:12,764 --> 00:35:16,338 So insurers are using these tools to protect their risk. 562 00:35:16,741 --> 00:35:19,832 We've come up with a set of tools to help the customer 563 00:35:19,880 --> 00:35:23,205 protect their end so they don't have to end up with constant 564 00:35:23,205 --> 00:35:26,968 pressure on policy premiums. Oh, 565 00:35:27,050 --> 00:35:29,899 that makes a lot of sense. So 566 00:35:31,024 --> 00:35:33,889 Given that there's a lot of dollars attached to this 567 00:35:35,113 --> 00:35:38,718 and there's an IT element, there's an 568 00:35:38,815 --> 00:35:42,492 engineering element, who runs this? Who 569 00:35:42,492 --> 00:35:46,083 should— I guess there's the should— who should own this and who 570 00:35:46,277 --> 00:35:49,740 actually owns it, right? This is clearly, if you're a big manufacturing 571 00:35:49,999 --> 00:35:53,247 outfit, even a moderate one, like the C-suite, this has to 572 00:35:53,672 --> 00:35:57,322 bubble up to the C-suite, doesn't it? It does. 573 00:35:57,834 --> 00:36:01,600 We know that about 57% of industry doesn't have dedicated asset 574 00:36:01,600 --> 00:36:05,349 risk managers. So it ends up being— Really? Yeah, it's 575 00:36:05,349 --> 00:36:09,082 hard to believe, but they don't. And we don't make enough of them either. We 576 00:36:09,082 --> 00:36:12,783 don't have enough graduates. It ends up falling usually 577 00:36:12,815 --> 00:36:16,660 to the CFO, and the CFO usually manages 578 00:36:16,660 --> 00:36:20,313 it as an insurance policy. 579 00:36:20,826 --> 00:36:24,607 So we're managing the financial outcome. So it's back to actuarial risk. 580 00:36:25,537 --> 00:36:29,224 versus engineered risk. So what we're trying to do, what we 581 00:36:29,320 --> 00:36:33,087 are doing, is bringing decision intelligence 582 00:36:33,087 --> 00:36:36,662 to the table for that C-suite that gives them 583 00:36:37,079 --> 00:36:40,894 the operational knowledge to make better actuarial 584 00:36:40,943 --> 00:36:43,604 decisions around the insurance that they have to buy 585 00:36:44,229 --> 00:36:48,028 because there's nobody dedicated. And I, Frank, I always come at 586 00:36:48,060 --> 00:36:51,893 it from the maintenance side too, because at my heart, I'm an operations 587 00:36:51,926 --> 00:36:55,763 person. I, I'm a maintenance guy. I'm not a, a risk guy. But 588 00:36:55,763 --> 00:36:59,103 what I saw in my experience was that 589 00:36:59,697 --> 00:37:03,390 we don't have enough on the risk side, and our maintenance brothers and 590 00:37:03,390 --> 00:37:06,971 sisters end up being the people that are the de facto asset 591 00:37:07,019 --> 00:37:10,294 risk manager. So how do we put better tools for 592 00:37:10,294 --> 00:37:14,003 operational to understand what they need to do to 593 00:37:14,003 --> 00:37:17,185 manage risk? And how do we put tools in the place of 594 00:37:17,603 --> 00:37:21,144 plant managers and CFOs to be able to 595 00:37:21,144 --> 00:37:24,106 drive those decisions more effectively. 596 00:37:26,112 --> 00:37:29,887 Interesting. You mentioned that we don't graduate enough of this. So this is an 597 00:37:29,887 --> 00:37:33,678 actual degree you can get? I say this as a parent of a high school 598 00:37:33,678 --> 00:37:37,310 junior, because this seems like a growth industry and a stable thing. Is this an 599 00:37:37,390 --> 00:37:40,783 MBA? Is this a graduate level? Is— are there undergrad programs? Like, 600 00:37:41,591 --> 00:37:45,300 where would Risk engineering programs. So 601 00:37:45,365 --> 00:37:48,976 there are— Really? Absolutely. Absolutely. So 602 00:37:49,056 --> 00:37:52,427 you could go in specifically to risk engineering. And 603 00:37:52,507 --> 00:37:56,246 normally those people migrate into places like maybe they work for 604 00:37:56,471 --> 00:38:00,195 Tyco or Simplex or Siemens, right? Health, 605 00:38:00,211 --> 00:38:03,597 life safety control systems. You'll find risk 606 00:38:03,597 --> 00:38:07,032 engineers in your EPCMs, your engineering procurement construction 607 00:38:07,064 --> 00:38:10,515 management companies. So it's, there's a whole 608 00:38:10,643 --> 00:38:13,997 body around risk engineering that is invisible. 609 00:38:14,414 --> 00:38:17,833 If you've never worked in an industrial operation that has a dedicated risk engineer, 610 00:38:18,121 --> 00:38:21,893 which is again, 60%, you probably not know that 611 00:38:21,893 --> 00:38:24,910 the discipline even exists. That is 612 00:38:25,488 --> 00:38:29,211 fascinating to me that there's this whole discipline that you can get a 613 00:38:29,211 --> 00:38:32,854 degree in and had never heard of it, right? That's interesting. 614 00:38:32,966 --> 00:38:36,642 And it sounds like a growth market. So interesting to get a 615 00:38:36,642 --> 00:38:40,399 degree in, I would imagine. It's a growth market among 616 00:38:40,447 --> 00:38:44,189 so many other of the STEM that we need to invest more in, 617 00:38:44,205 --> 00:38:47,625 whether it's metallurgical engineers, right? I think China is 618 00:38:47,737 --> 00:38:49,857 graduating more metallurgical engineers a 619 00:38:49,905 --> 00:38:53,598 year than we have operating 620 00:38:53,758 --> 00:38:57,532 in the practice in North America. Yeah, I'm not surprised. For 621 00:38:57,532 --> 00:39:01,128 one, they have a 4-to-1 roughly Yes. Population 622 00:39:01,128 --> 00:39:03,871 advantage, right? So all things being equal, it would be a 4 to 1, but 623 00:39:03,871 --> 00:39:07,689 it's not. There's more to it than that. But how 624 00:39:07,721 --> 00:39:11,379 do you calculate— because it's always 625 00:39:11,475 --> 00:39:14,957 the thing that you never see coming, right? How do you prevent a failure that 626 00:39:15,005 --> 00:39:18,791 never happens? Because that, as someone who's been in data 627 00:39:18,791 --> 00:39:22,433 science and questions like that, one of the questions I'd get 628 00:39:22,561 --> 00:39:26,219 that would always amuse me and bother me philosophically, 629 00:39:26,396 --> 00:39:29,707 later was, how do we predict when XYZ 630 00:39:30,162 --> 00:39:33,700 is going to happen? And I said, when's the last time that happened? How often 631 00:39:33,700 --> 00:39:36,808 does it happen? It never happened. Like, how do you— 632 00:39:39,367 --> 00:39:43,049 and I say, this is predictive analytics. It's not predicting the future, right? Yeah. 633 00:39:43,113 --> 00:39:46,905 So how do you— is that 634 00:39:46,954 --> 00:39:50,778 possible to do that, right? Is that still impossible? Philosophically, 635 00:39:50,794 --> 00:39:54,436 I would say it's probably impossible to do. You can probably approximate it. 636 00:39:55,345 --> 00:39:59,143 But what is a better answer? Is there a better 637 00:39:59,159 --> 00:39:59,760 answer than that? 638 00:40:03,368 --> 00:40:07,196 I've always had a challenge with this too on the predictive side 639 00:40:07,791 --> 00:40:11,217 is that, okay, so you say you're going to give me this 640 00:40:11,265 --> 00:40:14,896 predictive analytic model and it's going to be a crystal ball and it's going to 641 00:40:14,896 --> 00:40:17,935 tell me that I'm driving down 642 00:40:18,776 --> 00:40:22,482 whatever Highway 1, Route 66 and 643 00:40:22,482 --> 00:40:26,190 at mile marker 328, my transmission's gonna 644 00:40:26,190 --> 00:40:29,881 go out. How do you know that, right? What gives you the indi— like, 645 00:40:30,282 --> 00:40:34,086 what tells you that? What dataset allows you to do that? 646 00:40:34,696 --> 00:40:38,516 That always frustrated me because I just can't really 647 00:40:39,014 --> 00:40:42,416 get aggregated. I could say maybe if I look at a 648 00:40:42,416 --> 00:40:46,188 million cars and I look at the same 649 00:40:46,188 --> 00:40:49,737 operating context with the same car on the same road, in the same 650 00:40:49,850 --> 00:40:52,959 context, maybe I can derive something out of that. 651 00:40:53,797 --> 00:40:57,551 I think a better way to look at it is if we have inputs on 652 00:40:57,551 --> 00:41:01,384 the car that I'm driving, engine temperature, the type of 653 00:41:01,384 --> 00:41:03,832 fuel I put into it, I can have a 654 00:41:04,347 --> 00:41:08,034 probability of certainty, which is one 655 00:41:08,179 --> 00:41:10,399 level, and I can have a 656 00:41:12,008 --> 00:41:15,355 certainty around the context. So I can have 657 00:41:15,612 --> 00:41:19,370 multidimensional Hey, I just detected 658 00:41:19,370 --> 00:41:23,111 an issue with the engine. It may be one of 659 00:41:23,143 --> 00:41:26,885 5 things. Can you give me some more information? If you give me some 660 00:41:26,901 --> 00:41:30,529 more information on one of those 5 potential things, maybe I'm 661 00:41:30,529 --> 00:41:34,142 low on oil, maybe I'm low on gas, but if you give me more 662 00:41:34,142 --> 00:41:37,755 context, I can get a greater certainty of what the 663 00:41:37,819 --> 00:41:41,576 problem is. And I can actually adjust my probability 664 00:41:41,592 --> 00:41:45,008 of failure based on those inputs. So to me, 665 00:41:45,377 --> 00:41:49,128 it's much the whole context around, yeah, we've 666 00:41:49,128 --> 00:41:52,671 got predictive that's based on all of our past history, but we want to look 667 00:41:52,671 --> 00:41:56,246 forward. That's saying, hey, my mean time between failure was 668 00:41:56,358 --> 00:42:00,045 this, so we know that about every 60,000 hours we're going to have an 669 00:42:00,045 --> 00:42:03,235 operating failure in the engine. I think a better way to look at it 670 00:42:03,235 --> 00:42:07,018 contextually for what we have to do today is, what's my probability 671 00:42:07,259 --> 00:42:10,484 that this is going to happen? the likelihood. What's my 672 00:42:10,484 --> 00:42:14,290 certainty? What information and context do I have around that probability 673 00:42:14,787 --> 00:42:18,577 that actually allows me to make that decision? And that's again decision 674 00:42:18,577 --> 00:42:22,334 intelligence. That's really highlighting what information do 675 00:42:22,414 --> 00:42:25,979 I need to give a better and more accurate 676 00:42:26,428 --> 00:42:30,154 insight into what needs to be done. So I want to take kind of 677 00:42:30,154 --> 00:42:33,782 the crystal ball out of the equation and really talk about 678 00:42:34,613 --> 00:42:38,389 Hey, there's probabilities and certainties that we need to talk about and 679 00:42:38,389 --> 00:42:41,924 we need to actually put into the equation so that we deal with the 680 00:42:41,924 --> 00:42:45,459 reality of what we're dealing with today, not what may 681 00:42:45,523 --> 00:42:47,130 happen. Right. 682 00:42:48,817 --> 00:42:52,513 Fascinating. I'm just— not every day I find out that a 683 00:42:52,513 --> 00:42:56,193 whole new field exists, so I'm still processing that. 684 00:42:56,630 --> 00:43:00,428 How did you get into this? I'm sorry, go ahead. Go ahead. Were 685 00:43:00,444 --> 00:43:04,115 you Googling it? I did. Yeah. I was like, there's a number of 686 00:43:04,115 --> 00:43:07,774 schools. You weren't kidding. There was, there was, I was just like, wow, that's— and 687 00:43:07,855 --> 00:43:10,407 I would imagine that you probably have to be pretty good at math. You probably 688 00:43:10,423 --> 00:43:13,938 have to be like a, like a nerdy MBA, almost an 689 00:43:14,050 --> 00:43:17,228 engineer, right? That would be kind of the way I would describe it. 690 00:43:17,838 --> 00:43:21,145 Though my, my oldest is very good at math and he, 691 00:43:21,899 --> 00:43:25,688 you know, he builds robotics and he's in a— so I'm like looking, 692 00:43:25,704 --> 00:43:28,625 I'm like, right now he wants to be a mechanical engineer and I certainly want 693 00:43:28,625 --> 00:43:32,106 to encourage that, but if he decides he doesn't like it, I'm definitely going to 694 00:43:32,106 --> 00:43:35,939 float this in his direction of— because it's an 695 00:43:35,939 --> 00:43:39,339 interesting— as a dad, you're always selfishly looking out for your kids, right? 696 00:43:40,204 --> 00:43:43,332 But how did you get into this, right? You mentioned you grew up in Alaska, 697 00:43:43,412 --> 00:43:47,100 and Alaska seems like an interesting place to grow up 698 00:43:47,100 --> 00:43:50,837 because obviously you're not that far from the wilderness, but also it 699 00:43:50,869 --> 00:43:54,621 takes just a lot of good engineering just to survive year-round up 700 00:43:54,621 --> 00:43:58,467 there, right? So How'd you get 701 00:43:58,467 --> 00:44:01,824 into this? I come by 702 00:44:03,725 --> 00:44:07,155 the industrial operation space naturally. So I 703 00:44:07,204 --> 00:44:10,909 started my career as I was growing up and through university in 704 00:44:10,909 --> 00:44:14,422 oil and gas. And so it's wired into me that we're 705 00:44:14,519 --> 00:44:18,226 always planning for the worst-case scenario. So you don't go 706 00:44:18,713 --> 00:44:22,053 outside of 40 below zero to do something without 707 00:44:22,053 --> 00:44:25,073 planning Planning ahead. 708 00:44:25,506 --> 00:44:28,921 Yeah. I mean, the couple of times that I did 709 00:44:28,953 --> 00:44:32,640 that were not good, right? A couple of times I went into the outback 710 00:44:32,640 --> 00:44:36,487 hiking without a gun, for example, and got pinned down by a 711 00:44:36,567 --> 00:44:39,709 moose who a bear had just eaten her calf. So 712 00:44:40,495 --> 00:44:44,182 if you think about risk engineering, it's part of planning, but 713 00:44:44,182 --> 00:44:47,436 it's also about building resiliency. How do you 714 00:44:48,029 --> 00:44:51,847 deal with that issue? And then how you respond to it, how you manage 715 00:44:51,943 --> 00:44:54,975 it, is actually the determination of if you survive. 716 00:44:55,809 --> 00:44:59,531 And so that kind of underlying thought process, I didn't 717 00:44:59,595 --> 00:45:03,076 even think, I didn't even know risk engineering was a thing until 10 718 00:45:03,172 --> 00:45:06,798 years into my corporate career. But what I found is that 719 00:45:07,102 --> 00:45:10,648 it's built into me naturally because where I come from, what I was exposed to, 720 00:45:11,193 --> 00:45:14,834 and from who I learned from, right? From the people I learned from, they 721 00:45:14,883 --> 00:45:18,588 went, look, we're running a multi-billion dollar operation 722 00:45:18,588 --> 00:45:22,131 above the Arctic Circle. that's housing 1,000 people. This is oil and 723 00:45:22,131 --> 00:45:25,148 gas. We have to plan, schedule, 724 00:45:25,600 --> 00:45:29,069 execute, measure, monitor, 725 00:45:29,792 --> 00:45:33,192 manage seamlessly. Our tolerances for 726 00:45:33,337 --> 00:45:35,779 risk are really low, right? Really low. 727 00:45:37,299 --> 00:45:41,104 I was in an event that actually forced me further into this 728 00:45:41,104 --> 00:45:44,645 area, and that was an event where we actually lost 729 00:45:44,645 --> 00:45:48,280 power at 40 below zero. So it was an 730 00:45:48,329 --> 00:45:51,570 entire site in Alaska where the 731 00:45:52,100 --> 00:45:55,775 80 kV high voltage power line was dug 732 00:45:55,775 --> 00:45:59,209 up by an excavator, right? And here you are, you got, you have 733 00:45:59,241 --> 00:46:02,739 600 people out in the middle of nowhere. It's 40 734 00:46:02,836 --> 00:46:06,334 below zero. And I had a, at the time, a 735 00:46:06,623 --> 00:46:09,993 just fantastic general manager that I learned a bunch from, 736 00:46:10,458 --> 00:46:13,510 you know, called all the leadership into a room and said, I need you to 737 00:46:13,510 --> 00:46:16,370 go look at ventilation systems. I need you to go to wastewater, and I need 738 00:46:16,370 --> 00:46:19,490 you to go to freshwater treatment. I need you to go to living facilities. He 739 00:46:19,490 --> 00:46:23,290 knew what to do to help manage the outcome because 740 00:46:23,290 --> 00:46:27,110 he knew we got about 2 hours before stuff starts freezing up. And if 741 00:46:27,110 --> 00:46:30,350 it freezes at 40 below zero in February in 742 00:46:30,350 --> 00:46:34,150 Alaska, we're down. We're done, right? We're done until the spring 743 00:46:34,150 --> 00:46:37,170 because we're not going to get this stuff unthawed, everything that we need to get 744 00:46:37,170 --> 00:46:40,851 unthawed. So my experience in that was, wow, 745 00:46:41,140 --> 00:46:44,751 this is amazing. You have like a Captain Picard that knows 746 00:46:44,912 --> 00:46:48,523 what to do. Oh, and then I made— 747 00:46:48,587 --> 00:46:52,247 I come from oil and gas when this incident, so I came with my mental 748 00:46:52,279 --> 00:46:55,826 model of oil and gas because this is when I started oil and gas 749 00:46:55,826 --> 00:46:59,116 post-Valdez oil spill. So we had all these 750 00:46:59,116 --> 00:47:02,535 emergency management and drills that we went through and 751 00:47:02,904 --> 00:47:06,722 very structured. What I saw in that organization was we 752 00:47:06,722 --> 00:47:10,556 had personality-driven risk leadership. We had people that had longevity 753 00:47:10,573 --> 00:47:13,620 in industry that knew the decisions that they had to make and how they had 754 00:47:13,620 --> 00:47:17,342 to make them. 25 years later, we don't have 755 00:47:17,342 --> 00:47:21,176 enough of those people. So the incidents that I was in are like, I don't 756 00:47:21,176 --> 00:47:23,422 know what to do. Do you know what to do? I've got a piece of 757 00:47:23,422 --> 00:47:27,080 it. You've got a piece of it. But a single person that could actually 758 00:47:27,112 --> 00:47:30,962 quarterback all those things, that had the risk model in their head to go, We 759 00:47:30,962 --> 00:47:34,615 got an hour here, we got 3 hours over there. That was very 760 00:47:34,871 --> 00:47:38,429 personality-driven, not process-driven. And so now 761 00:47:38,813 --> 00:47:42,338 fast forward today, that's what we need to do with Lumicent. 762 00:47:42,499 --> 00:47:45,431 That's what we are doing with Lumicent is really 763 00:47:46,024 --> 00:47:49,837 being that risk manager in a box for physical asset 764 00:47:49,869 --> 00:47:53,459 risk, not full enterprise risk management, but physical asset 765 00:47:53,459 --> 00:47:57,256 risk to be able to look at those things, make a determination of what's 766 00:47:57,256 --> 00:48:00,881 important, and direct your people to those things. I, my 767 00:48:00,913 --> 00:48:04,586 experience over the last 25 years is that our complexity has 768 00:48:04,699 --> 00:48:08,084 increased enormously. Our volume of data 769 00:48:08,469 --> 00:48:12,126 to be able to sift through, turn into knowledge, has increased enormously. 770 00:48:12,543 --> 00:48:16,217 But our ability to actually make decisions founded 771 00:48:16,393 --> 00:48:20,195 in data and be able to execute on them has actually decreased. 772 00:48:20,243 --> 00:48:23,949 And that's mostly due to we don't have enough people in industry with the 773 00:48:23,949 --> 00:48:26,672 longevity to be able to help make those decisions. 774 00:48:29,120 --> 00:48:32,860 Interesting. Wow. It's a, it's a whole, I think it's a 775 00:48:32,860 --> 00:48:36,488 testament to how good the people were at their jobs that we didn't know this 776 00:48:36,488 --> 00:48:40,251 existed. You never had 777 00:48:40,299 --> 00:48:43,262 to guess whether or not if you turned on the light switch, the light would 778 00:48:43,262 --> 00:48:46,563 come on. You never had to guess whether or not if you flush the toilet, 779 00:48:46,579 --> 00:48:50,427 whether it was going to flush because the infrastructure was there and supported 780 00:48:50,443 --> 00:48:54,151 and built by people that knew how to manage it. And you only know 781 00:48:54,151 --> 00:48:57,924 when it's not there. Yeah, I'm sorry. You only know when it's not there. Yeah. 782 00:48:58,968 --> 00:49:02,596 Wow. Wow. We're coming close to 783 00:49:02,596 --> 00:49:06,097 time and I want to be— this is fascinating. Not every day a whole new 784 00:49:06,113 --> 00:49:09,581 world opens up. And just for your information, I'm going to 785 00:49:09,806 --> 00:49:13,194 fold this to my kid. I live near Johns Hopkins University and they have a 786 00:49:13,194 --> 00:49:16,405 master's degree in risk. So maybe I can talk him into staying closer to home. 787 00:49:16,951 --> 00:49:20,671 But But what, what can people do to 788 00:49:20,671 --> 00:49:23,914 find out more about you and your company and how to reach out 789 00:49:25,349 --> 00:49:27,652 to you? www.lumicent.com, 790 00:49:27,910 --> 00:49:31,469 L-U-M-I-C-E-N-T.com. Reach out to me on 791 00:49:31,469 --> 00:49:34,899 LinkedIn and I'm available, right? I just love 792 00:49:35,076 --> 00:49:38,895 talking to customers about this subject. And yeah, you reach out 793 00:49:38,895 --> 00:49:42,600 directly through the website, me or anyone on our team, but I'm happy to 794 00:49:42,665 --> 00:49:46,064 talk to customers anytime I get the opportunity. I'm 795 00:49:46,064 --> 00:49:49,783 passionate. About helping customers solve the challenges 796 00:49:49,783 --> 00:49:53,165 that they have around physical asset and decision intelligence. 797 00:49:54,840 --> 00:49:58,654 Awesome. That's amazing. And we'll make sure all the pertinent links are in the 798 00:49:58,654 --> 00:50:01,519 show notes. And with that, we'll go to the outro. 799 00:50:03,040 --> 00:50:06,751 That was great, man. I really— that was amazing. I'm just floored 800 00:50:06,751 --> 00:50:10,431 that there's this whole— Thanks again to Andy Pruitt for joining us and showing 801 00:50:10,527 --> 00:50:14,335 how AI and decision intelligence can help organizations turn 802 00:50:14,384 --> 00:50:17,960 mountains of industrial data into smarter decisions about asset 803 00:50:18,008 --> 00:50:21,778 risk. Subscribe, share the episode, and join us next time on 804 00:50:21,778 --> 00:50:22,293 Data Driven.