[Darin Detwiler] Welcome to Spoiler Alert! I'm Dr. Darren Detweiler.
[Callin Godson-Green] Callin Godson-Green
[Darin Detwiler] And we are coming live from the International Association for Food Protection, IAFP, in a very kind of a niche place. You've either been there, and this is our first time. This is your first time? First time. First time, for the three of us, this is our first time here in Cleveland, Ohio. You know where another niche place on the map on this big planet of ours is?
[Callin Godson-Green] Where?
[Darin Detwiler] Dublin, Ireland.
[Callin Godson-Green] Very niche.
[Darin Detwiler] Very niche. Have you ever been there?
[Callin Godson-Green] I have.
[Darin Detwiler] You have.
[Callin Godson-Green] Just once, though.
[Darin Detwiler] Just once.
[Callin Godson-Green] Maybe for 27 years.
[Darin Detwiler] I can hear it in your accent.
[Callin Godson-Green] Oh, thanks.
[Darin Detwiler] You know who else has been to Dublin, Ireland?
[Callin Godson-Green] Who?
[Darin Detwiler] I have.
[Callin Godson-Green] Oh.
[Darin Detwiler] One time.
[Callin Godson-Green] How long?
[Darin Detwiler] Four or five days.
[Callin Godson-Green] Nearly. Nearly the 27.
[Darin Detwiler] Yeah. Then I went over the west side of the island, went up to Galway. You know who else has been to Dublin, Ireland?
[Callin Godson-Green] Who?
[Darin Detwiler] Our guest.
[Cronan McNamara] Hailing from Dublin, Ireland. I've spent a few more years there than you. Proud to still live in Dublin, Ireland, but glad to be here in Cleveland at the IFP. It's always good to visit.
[Darin Detwiler] Well, ladies and gentlemen, this is Cronan McNamara of CREM Global, based out of Dublin, Ireland. And you and I have had the great opportunity to collaborate. We've been to Dubai together a couple of times. We did the whole Predict UK about predictive analytics.
[Cronan McNamara] Ireland.
[Darin Detwiler] Predict in Ireland. Ireland. Yeah. And we've had the opportunity to meet up at other IFP locations, including near where I lived last year. But here we are in Cleveland, Ohio, and we're talking about spoiler alerts. I want to focus on the idea of what you would probably know best in looking at data and data analytics. But I think for our audience who has no idea who you are, they know where you're from. Yeah. That's the most important. That is most important. All right. But they don't know much about you. Tell us a little bit about who you are and what you do and about Crem Global.
[Cronan McNamara] Thanks, Darin. Great to be here, Callin. Thanks for hosting us. It's a great setup here at IAFP. So Creme Global is a data science scientific analytics company based in Ireland. I formed it 20 years just in April, so it was our birthday this year.
[Darin Detwiler] Happy birthday.
[Cronan McNamara] Thank you. We spun out from Trinity College. My background is physics and maths and computing. And I met a professor there called Professor Mike Gibney, who has passed away last year, unfortunately. But we started working on applying mathematical modeling to food safety risk assessment and exposure assessment in particular. So looking at pesticides and food and combining that with data on who's eating what and what the risks of exposure are. So a company formed in April of 5, and we've been building out a cloud-based analytics platform, which is very secure. And now we're using that to help organizations aggregate and anonymize data. So trade organizations can now gather a lot of data from all their members, anonymize that, aggregate it, and look for hidden trends. And spoiler alert, potential spoilers that you could never see otherwise unless you get this big data. and also the metadata that comes with it. So location, timestamp, time of year. So you can then relate that to climate and weather and location data and the type of product it was, whether it was pre-processed or what stage of processing the product was tested at, or was it the water test, et cetera. So all of that data kind of inform so much about food safety. And that's what we're working hard on to try and do.
[Darin Detwiler] As you're talking about 20 years, I would imagine that landscape has changed radically, not only in terms of the technology you're using, but how this data is being used.
[Cronan McNamara] Yeah, like in 20 years, we're probably on our third generation of tech now. We started out always on the cloud, always on the web. Our vision was to kind of make high-performance computing accessible to anybody with a web browser. So that was kind of our mission. to make that accessible to all scientists and no matter what company they're in, if they just kind of log into our system, they could access powerful computing. And of course, then we moved on to cloud computing and we do a lot of, we have all our stuff on the cloud. But now we're into the age of AI. AI has truly arrived. You know, we've been waiting for it for many decades and it was always a decade away. But now I believe it, the genuine AI has arrived. So In the last one year, once, two years, probably, so these models are super powerful, and they're trained on the whole public internet, right? So then... What you can do then is actually combine in the proprietary data that we've collected that's private to industry and actually supplement those models and train them up on the specifics of what you want them to study, like all this data we mentioned, like food safety testing, water testing, and then like apply that powerful AI with all the knowledge it has with this new data and see what it can predict. And this is a very exciting time. So the message is AI is truly now in arrived and ready to go.
[Darin Detwiler] And I would imagine that a lot of people think that AI, like, it takes the place of people's jobs, whereas from your description, it totally accelerates what people can do in those roles.
[Cronan McNamara] There's the risks and the opportunities of AI, and I'm not saying it will transform the way we work and potentially make us far more efficient in certain jobs and maybe reduce the need for as many people in certain roles. But I really see it as an opportunity, especially for us as a company, to leverage that power, empower our team to do more. So we want to grow. We want to use AI and discover new things that were never possible before. So yeah, so there's definitely huge opportunities that will come with disruption, though, for sure, in the jobs market. So I don't even know where that's going, to be honest with you. But we'll have to watch and learn, I suppose.
[Callin Godson-Green] You mentioned, so you started 20 years ago. When you began, what problem were you trying to solve or like what had happened that made you be like, there's a space for this?
[Cronan McNamara] I think the, what was called data science at the time even, you know, was only in its infancy, especially in the food sector, right? So we saw a huge opportunity to bring the kind of advanced maths modeling that was kind of prevalent in like financial services and insurance and all these other industries, but it wasn't being used in food safety. So we were like genuinely trying to bring as much data as we could into that and then develop scientific models. So we published a lot of papers on the methods and using what's called probabilistic modeling, Monte Carlo simulation, and just applying that to the data to understand consumer risk, consumer exposure. So like what foods are higher in different levels of heavy metals, pesticides, et cetera. Who's consuming those foods? What exposure levels are they getting? Are they safe? Should we have some more restrictions or less restrictions? So very much working with industry and government to understand that landscape with much more refined mats and data. So that was the opportunity we started with. And we still do that to this day, exposure modeling. Done a lot in the chemicals and cosmetics space, actually. in the same approach of aggregating a lot of industry data and providing this rich information on consumer habits and practices and exposure to different ingredients. And then the food safety side has really moved on into more, you know, pathogen testing, predictive around agriculture and processing environments, which seems to be a huge challenge. You know, it's a very Complex system of food production, a lot of things can go wrong, so the more data you can bring to the table, the better.
[Darin Detwiler] Speaking of bringing to the table, when I was out there my one time... in Dublin, Ireland. There was a fascinating conversation in that, I believe it was with the big newspaper, how they were using predictive analytics, how they were using technology. And what the gist of the conversation was is that you have the people that are making the purchasing decisions and the evaluating and the ultimate decision makers. But you also have the people that are going to be using this and trying to make the biggest change. And sometimes those people are far apart on a spectrum. And what someone was looking at in terms of this would be the positive indicator of success. is not necessarily what these people over here are saying, this is the positive indicator of success in using and why we invested in this technology. Do you encounter that kind of disconnect or that give and take sometimes?
[Cronan McNamara] Often food safety isn't the top priority for a lot of big organizations, maybe, let's say, so if we can provide other value, as in efficiencies or operational efficiency data, that can be a more attractive proposition to try to get at least started on initiatives to gather data and analyze data and always with the ultimate goal of food safety and quality underpinning that. So sometimes you have to bring something else to the table to kind of join those dots between the different departments and make sure that the project can get support, right?
[Darin Detwiler] That sounds like short-term and long-term goals. Or short-term and long-term successful targets.
[Cronan McNamara] You want to try and show, as you say, quick wins, low-hanging fruit, get some success early. If people are investing in these projects, they can be quite long-term to get the real value. So you have to have little wins along the way, I think is a good strategy.
[Darin Detwiler] Well, one of the things, have you ever heard of being data rich but information poor? Always. That seems to be one of those, we don't want to end up in that situation kind of things. But it's not like that's an accidental situation. It seems like if you're not asking the right questions, or if you're not prioritizing the right data, or if you're not... empowering your team with what to do with this data, that becomes the missing link in terms of how do you turn data into actionable information.
[Cronan McNamara] Like in a lot of places, data is collected for a certain purpose. It could be just for, you know, regulatory, you know, box ticking and it's left on the shelf. And with all this new powerful technology that's out there to analyze data, I think you're right. I think the key issue is asking the right questions because the answers can be formulated using the technology. And it's not as challenging as it would have been like 10 years ago. So in this day, age of data and AI, it's all about the right questions, in my opinion. That's where the human element comes still into the loop is where do you ask the right questions.
[Callin Godson-Green] That's like the theme across all. AI use. when people are using ChatGPT for general writing emails and stuff, you need to ask it the right questions or it's just going to present you with kind of generic information and overload.
[Darin Detwiler] Well, yeah, if you're not asking it enough detail in your prompt, right, and you get some result back and you're like, that was useless. I can't use it. You're garbage.
[Callin Godson-Green] You have no idea what I'm talking about.
[Darin Detwiler] Maybe it's not.
[Cronan McNamara] It's not its fault.
[Darin Detwiler] Yeah, exactly. It's like the computer AI is like, I'm trying to do my best here, but.
[Callin Godson-Green] I have no idea what you mean.
[Darin Detwiler] Throw me some useful details to build upon.
[Callin Godson-Green] You're like, oh wait, I didn't tell it in relation to food safety.
[Cronan McNamara] I don't want to work with you anymore. It says the AI, you're just not clear enough in your thinking or your questioning. So yeah, it's a real skill now, I think. I always think of it as collaborating with AI, you know, as a team and as our team collaborates with AI to get results. It's now part of our team, but it's not infallible. It'll give you sometimes answers that are sound truthful. So you do have to check, triangulate sometimes the results from different AIs, our standard Google searches, you know those old-fashioned Google searches we used to do? Yeah. And they come with AI answers anyway nowadays. You notice that?
[Darin Detwiler] They even prompt you on, I mean, there's little times that like you can ask a question better. It's like, wow, thanks for assuming I didn't know how to ask this question or whatever. But I get it in terms of the idea that if the AI or the solution is trying to sell itself in terms of the best possible conditions, it's got to help you ask a better question. I recently saw a video about how, you know, like asking better questions One of the questions you should be asking is, there a better way to ask this question?
[Cronan McNamara] Yeah, that's a really good question. Yeah.
[Darin Detwiler] If you're looking at collecting data and people say, well, here's my data, like here's a shoebox full of papers that are collecting dust or whatever, maybe it starts with, well, we need to collect this better data, not just the convenient data. We need to collect it this way.
[Cronan McNamara] What's missing from the data that would add most value? You know, it can answer those kind of questions really well. So I have all this data and I'm looking to try and figure out these things. What other data should I be looking for? And it'll actually come up with strategies and, you know, opportunities to collect that data. So yeah, I think that's right. And asking it for help and all. One of the podcasts I was listening to on the way here, the guy says he has signs up all over the office and says, have you asked AI yet? because that's now your first protocol, ask AI, not just don't go around like asking people in the office anymore.
[Darin Detwiler] Which is weird, isn't it? Yeah. But let's flip it to another set of questions. Hi, we're from company X, and we don't collect any data. We don't analyze any data. We want to start doing it. We want to hire you, and we're going to start Monday, and we're starting from zero. And so give us some solutions.
[Cronan McNamara] Right away, first thing you do is sit down and talk, maybe some workshops trying to find out, well, is that actually true about the no data? There must be some data in there. So I think there's like these jobs to be done frameworks, right, that are very useful. So we run them quite often with clients and literally blank page, you know, all questions, no, I won't be giving you any solutions. We'll be just asking a lot of questions on the first meeting or two. And then we'll form, you know, a priority list. We'll rank and rate it, and then you guys will decide what data is easy for you. Well, it's always about like, well, what's possible, what's doable on your end, and where's the most value. So that's where you start, you know.
[Callin Godson-Green] Like what problem are you trying to solve? Like what do we need help with? What do you want to do in your business?
[Darin Detwiler] Sure, what are our priorities? So it sounds like it's not, it wouldn't be us as a company outsourcing as much as it is now we have a partnership because we want to go down a path on this journey to figure out how we can collaboratively start collecting data. Who's going to collect the data, what data, where are we going to store it, how are we going to secure it?
[Cronan McNamara] That's not the hard part. The hard part is more, you know, get those workflows in place, and then we'll figure out all that storage and technology, maybe a few sensors and cheap things you can install in your business to help automate some of that process, you know? So it's really a discussion and a collaboration. And then trying to figure out the opportunities for you, the best solutions then will fall out of that. So we would never be proposing a solution without having had those conversations.
[Darin Detwiler] I would imagine that the people come to you and say, we want an answer, but we have our board meeting in three weeks.
[Cronan McNamara] There's a funny thing now with like FOMO on AI. Oh, we're seeing it. Yeah, we're seeing it like there's companies coming to us. We need to do this AI stuff. What do we need to do? And they're like, Okay, let's have a talk, let's chat, But they're really keen now to not miss out on this AI wave. They now see it, you know, it's really happening because they're waiting for it to happen for so long, and they're like, we need to be doing some of that AI stuff. And we're like, okay, let's talk.
[Callin Godson-Green] I mean, I kind of understand it. I felt like that as well. Like everyone's talking about what they were doing with ChatGPT, being like, why are you still planning holidays yourself? And I was like, well, I better use this. Even though, and then afterwards, it's like, I actually enjoy planning the holidays myself, but I feel like I should use it because I might be missing out on something.
[Cronan McNamara] I love the old Google Maps, looking at the radius on Google Maps and finding the location, how to?
[Callin Godson-Green] Get from A to B. Yeah.
[Darin Detwiler] Now, here's another conversation we had in Ireland. Just because this company has all these answers, has all this information from you, They can decide, yeah, thank you for showing us how to maximize X, Y, and Z. We're not going to do that.
[Cronan McNamara] So the company decides, oh, look at all this powerful data, but I really don't want to touch that in case it tells me something I don't want to know. Yeah, I don't want to know that. That's interesting. That's the head in the sand.
[Darin Detwiler] It's like the option of FOMO. Yeah, the head in the sand.
[Cronan McNamara] Yeah, not a great strategy, obviously, but it is something you do see. Because once they know, then what are they going to do? Sometimes it means, do I have to shut that plant or stop farming that lot? And now that I know that and I keep doing it, now am I going to have to defend that in court someday? So... there's a risk aversion to trying to find things out. So when you have an AI model and it's saying, oh, there's an elevated risk over here of this at this time of year, what did they do with that? So that's a bit of a tricky one, still in fairness to them, because should they stop or should they do more testing? Sure. I think the latter, you know, just be a little bit more vigilant, do a little bit more testing if you find an elevated risk somewhere. At least you can then say, well, yeah, we used AI, found some risk, that's a little bit elevated in this particular product line on this particular time of year. So we did this, that's fair enough, right?
[Darin Detwiler] Sure. Can you give us an example of spoiler alert, something that data you went down to theoretical, but ideally some real. You go down a journey and data has revealed something that, wow, we would never have known that if it wasn't for our ability to find it through the data and analytics.
[Cronan McNamara] Yeah, that's cool. And like we've seen success in lots of projects. One of them using next generation sequencing around the manufacturing environment. And this kind of data, you know, is very powerful because it's like looking at the microbiome of a facility. And essentially, what you can do there is, and what the company found, is that you can predict when the microbiome is becoming risky, because you're doing your classical pathogen testing in parallel. So you're training a model to detect when the environment might become a little bit friendly to the bad bugs, right? And then you can make an intervention. I think that's incredible, like, you know, to see that predictive power. coming from the swabbing the environment on a regular basis and then figuring out, actually, we never would have known that except for this technology. And we're seeing an elevated risk of the bad bug growing. And the cool thing is, instead of using bleach, you could actually use other microbes to actually out-compete the bad bugs. An interesting approach to keeping a safe facility now. That's not being done in real life yet, but the science has proven it to be possible.
[Callin Godson-Green] I used to work in, actually not in Dublin, in Wicklow, in the old potable water testing plant, and we were having massive problems with biofilms. But we could not figure out any correlation. Like, you know, one day they'd be there, one day they wouldn't, the water came out, we were using UV to treat it. But if we had something like that, because we were doing all the records.
[Cronan McNamara] Everything's there somewhere that you just have to go, you know, finding more, using More powerful tools might bring it out, and then you'd be like, Oh, there you go.
[Callin Godson-Green] Yeah, obviously, it's every time a bob is working and he's just not cleaning it properly.
[Cronan McNamara] Yeah, it could be that, even. Yeah, the cleaning rotors, the staffing, everything should go into the mix.
[Darin Detwiler] Yeah, sure. Well, let's go back to this conversation about... When you're looking at data and any kind of digital solutions, it's got to be a bit of a partnership. The idea of when you are making an investment into a solution, it's not taking a package off the shelf and just plugging it in and it starts working. You can do that. But you're going to get what you invest into.
[Cronan McNamara] It, which is what you want.
[Darin Detwiler] Probably not as effective of going down this partnership.
[Cronan McNamara] Maybe someday there'll be AI packages that can plug in and go in and figure it all out, but not yet. Yeah.
[Darin Detwiler] Maybe. But you would still think that you have so many different moving parts.
[Cronan McNamara] Yes. You still need to ask it the right questions. Exactly. You know.
[Darin Detwiler] Yeah.
[Cronan McNamara] So that's a conversation to be had about the capabilities, their needs, what's possible. All of those things have to be discussed. Yeah.
[Darin Detwiler] Do you would then suggest that it would be harder for a company that's been around for 100 years, but has never done much in terms of data analytics, as opposed to a brand new company. If you're a brand new company, you might want to make sure that this is part of your game plan from the beginning.
[Cronan McNamara] I don't know, because if you think about the latter, right, they're in startup mode, their budgets are probably tight, you know. It'd be nice to do everything right from the start, but you're so many things to do to get started. Maybe, you don't have the bandwidth. And imagine you're around for 100 years, you should have some budget. As long as you have the leadership that, you know, understands that things need to change, then you have your other challenge of change management, right? So.
[Darin Detwiler] Well, whether it's an existing company of many, many years or a new company, if you're looking at bringing on technology to collect data, analyze data, all that kind of thing. This has got to be an interdisciplinary, multi-department type of approach. Otherwise, you're kind of going to leave Swiss holes, or you're going to leave Swiss cheese holes in your attempt.
[Cronan McNamara] Like that is the challenge, say, that 100-year-old company, they have their finance department operations, their procurement, their sales, their processing, the operations, their food safety, whatever they have in those areas. There's a lot of things to think about, right? But I guess that's where it comes down to that workshopping of the what's there already, what's possible, what's easy to do, and ranking and rating the challenges and the opportunities. And you just have to get started. I don't see any, I'm a bit biased being a data science company, but you know, I just couldn't imagine not using your data to try and make your business better.
[Callin Godson-Green] We obviously, we do. very different things, but it's a similar principle, like businesses that we work with come to the digital side of food safety for a reason to prevent that, you kind of used the analogy earlier of the big box of documents. Think of like a warehouse of documents, you know, if it's a grocery store or production plant. So we look at like what are the benefits of going digital besides that? And, sometimes people come just for that reason. They're like, we need to get rid of this warehouse that we have all this paper sitting and it's fire hazard. That's fine. But, you know, it'd be very easy for us to just move them over.
[Cronan McNamara] So you move everything off paper into digital, right?
[Callin Godson-Green] But then, you know, we could easily be like, there you go, everything's digital, see you later. But that's, you know, there's no use. We now have these kind of abilities to trend. And again, to use your analogy of data rich, information poor. We want to swap that. We want to give them these new insights that like, you know, your fridge is performing fine, but it's trending in a concerning direction. What can we do about that proactively? The information is there. So we have that same mindset of like, we have this information, we want to do something with it and get action out of it.
[Cronan McNamara] The nice thing is, you know, all of that digital data could have been like scanned PDFs or all sorts of stuff. But the good thing about AI now is that it can start to actually pull the data off those even handwritten PDFs. with reasonable reliability. So all of that information that was kind of locked away because it was too hard to scan in off of PDF is now becoming available because these AIs can figure it out. So that's on opportunity. Then you get to structured data, right? So there's data and then there's structured data, which is where you want to be. And once you have structured data, then you can really look at opportunities to apply new AI models. So Yeah, there's AI is solving a lot of the different pain points on that journey that you're part, you're digitizing as well. So the next step would be to try to figure out how to get all the value from all that information into the business.
[Darin Detwiler] So there's been a lot of conversation about the idea of the C-suite, the corporate executive offices, and how the food safety quality assurance leader, whether it's a VP or a director or whatever the title is, often not at that table. Would you say that this data has got to be in the room? It's got to be at that table. If the leaders, whether they are in finance or whatever it is, logistics or whatever, if they're not looking at this data in terms of predicting their next quarter or evaluating their past quarter, they're missing a big opportunity from the highest levels of that kind of corporate totem pole.
[Cronan McNamara] Definitely. So probably the CIO role is probably what you're thinking. Chief Information Officer probably is at that table and maybe the CFO. So you know, those people are very data-driven and they should be bringing all of that in. Now I think AI should be at the table as well. Sometimes you can just turn on AI in the meeting and listening to the meeting and ask it for suggestions. So maybe they'll just add an extra team member, which is cost effective, $20 a month AI into that meeting, right? Why not?
[Darin Detwiler] Sure, you can have the CIO in the room. And how are things going, CIO? They're fine. Okay, good. Moving on. Next item on our agenda. Or, okay, can you show us the data? Can you walk us through what this data? Can you show us the trend? Because it's one thing, I think, to say, the trend shows us this. That's another thing to put that in front of the people at the decision level and saying, I want you to look at this growth or this decrease or whatever, this change over time.
[Cronan McNamara] Yeah, visualize the data.
[Darin Detwiler] Because that would make data points become much more of something that's tangible in front of those decision makers' eyes.
[Cronan McNamara] Absolutely. And you really have to, I'm just thinking, you really have to trust that CIO because they could probably tell any story they want with the data, right? So you have to make sure that they're, you know, on the same vision and mission as the other leadership members and really honest about the business and showing the real data, right? So Because it's a small, at that level, they're probably going to have 5, 10 minutes, right? They're not going to be able to go into deep dive into their questions and answers. So you have to trust those people to really bring those, the right questions and the right visualizations into that meeting. The really crucial points about the business. Is food safety on that data set? I don't know. I don't know. I hope so. It should be. Yeah.
[Darin Detwiler] For a food company.
[Cronan McNamara] Yeah, for a food company.
[Darin Detwiler] It should be the number one question.
[Cronan McNamara] Yeah, of course. And we know. I think so.
[Darin Detwiler] It all isn't. Yes. Probably a lot more finance and profit margin and sales and distribution and all that.
[Cronan McNamara] Logistics. Yeah, but what about the food safety? So let's hope that becomes an important agenda item and the data is there to support it, right? And I think AI should be at that table and they should be asking it questions about, well, what is this data telling us? What are the big risks? What are the big opportunities? What are the big opportunities for my business, you know, based on all this data, new sales opportunities, et cetera? You know, that's where I think the power will come.
[Darin Detwiler] I think that this is going to have a big impact in terms of if you're looking at investment, you're looking at the stock market, things of that nature. Remember those Chipotle outbreaks year after year for multiple, there were six different pathogens, all those big outbreaks. There were insurance companies and there were large capital venture companies that were contacting me. And the first thing they said was, wow, we understand about this. And they used to be our number one. We realized we weren't asking the right questions. Think about that. So it's not even about food safety in that case, it's about their investors and those blind spots that they assume because it's a big company that's been around for a while, that they need to need to ask those things taken care of. Exactly. I'm sure it's smart.
[Cronan McNamara] Imagine being an investor in a food company and not thinking about food safety.
[Darin Detwiler] Those food safety questions may seem like that's a very niche area, but those have a direct impact on the investment, the economics, the growth of the capital.
[Cronan McNamara] The risk of your investment, right? Yeah.
[Darin Detwiler] So data analytics is a big picture. We have to look at what questions are being asked. We have to look at that journey. It's not just a outsourcing or a plug and play solution.
[Cronan McNamara] Collaboration with a data science provider. It's a collaboration with AI, with your leadership team. And it's all about those right questions. I think that's where we got to, right?
[Darin Detwiler] Well, I thank you for letting us ask some questions as we went on this journey, talking about digital solutions, talking about AI and data collection and analytics. I think that it's one of those things that ultimately at the end of the day, when we look at the price that we pay for food, whether it's at the grocery store, at the restaurant, we kind of make the assumption that, oh, if it's more expensive, it's because all this is going on behind the scenes. Thanks, guys. Well, thank you very much for joining us. We're going to put this in the can and get it out to you as soon as possible. Anyway, join us next time for our next episode. Who knows where we'll be? Thank you very much. This is Spoiler Alert!
