Hi, I'm Dr. John Ennis, CEO at Aigora. In this episode, I enjoyed speaking with Jeff Garza, principal and founder of Garza Consulting. Jeff and I talked about better sensory research, focusing on designing experiments before analyzing data and using AI without giving up expert judgment. I hope you enjoy this conversation as much as I did. And remember to subscribe to AigoraCast to hear more conversations like this one in the future.
Jeff Garza is Principal and Founder of Garza Consulting, where he helps teams use sensory research, consumer insights, and statistics to guide product decisions.
Jeff Garza has more than 20 years of experience in food and beverage, including work at ConAgra Foods and PepsiCo. His work spans experimental design, consumer segmentation, and product optimization. In this conversation, he discusses mixture designs, rigorous qualitative research, and the value of expert oversight when using AI.
Jeff Garza holds an MS in Mathematical Statistics from Texas Tech University and a BS in Mathematics and Statistics from the University of Nebraska.
Welcome to AigoraCast. Conversations with industry experts on how new technologies are impacting sensory and consumer science.
John Ennis: Hi, I'm Dr. John Ennis, CEO at Aigora. In this episode, I enjoyed speaking with Jeff Garza, principal and founder of Garza Consulting. Jeff and I talked about better sensory research, focusing on designing experiments before analyzing data and using AI without giving up expert judgment. I hope you enjoy this conversation as much as I did. And remember to subscribe to AigoraCast to hear more conversations like this one in the future.
John Ennis: All right, welcome back everyone to another episode of AigoraCast. Today I'm very happy to have my friend Jeff Garza on the show. Jeff Garza is the principal at Garza Consulting and an experienced sensory and consumer insights statistician with over 20 years of experience in the food and beverage industry. Throughout his career, he's worked with major CPG companies, including PepsiCo and ConAgra Foods, utilizing his deep expertise in market research, sensory science, and the design of experiments. Jeff's love for strategic problem solving has enabled the creation and optimization of a multitude of successful products. He specializes in bridging the gap between complex statistical data and a complete understanding of the target consumer. Recognizing that today's marketplace changes rapidly, Jeff and his consulting team strive to put the specialized skill needed for agile product development and optimization within reach of their clients. So Jeff, welcome to the show.
Jeff Garza: Thank you so much. It's awesome to be here, John. Thanks for the invite.
John Ennis: No, it's great. We always have great conversations privately, and I'm glad that we have a chance to finally record one and put it out there for the world. So, maybe just quickly, I would expect most listeners will have heard of you, but it might be good if you go, you know, quickly kind of through your background and how you got to where you are now, you know, as I think really one of the preeminent statisticians in the field.
Jeff Garza: Yeah, I mean, I actually just fell into the sensory world out of graduate school. I worked for Linda Papadopoulos at ConAgra Foods, and I think at the time I knew nothing of sensory or consumer research. And so I had some great experiences there. I worked for some really good people: Todd Renn, Nancy Eicher. I mean, they really kind of built me up over the years, and like I—I mean, the people I worked with, and I just can't name them all, but they they really taught me everything I know today. And I was lucky enough to bring my expertise of just kind of the basic stats knowledge to the table there, and then it just kind of grew. And I did work for ConAgra for, I think, six or seven years, and then I worked for PepsiCo for another six or seven years. And then I broke off and kind of did my own thing.
John Ennis: Well, let's talk about that transition, because that's interesting to me, because you know, I actually had never worked at a large company. I went straight from postdoc to working for my dad, and then I started Aigora. Can you talk about that transition? Like what was it that motivated you to kind of go out on your own, and like what was the—what was that experience like?
Jeff Garza: For me, it was my family. For for those that don't know, my wife's a physician. She's a neonatologist. And really, the reason I left ConAgra to go to PepsiCo was my wife was getting ready to look for residencies. And so we we—I followed her to the Chicago area, but she ended up liking Wisconsin more, so we ended up in Milwaukee, and I commuted down to Barrington at the old Quaker Tropicana Gatorade facility, and it was amazing. I had some great people I worked with there, and then kids came. And I was commuting. I mean, Pepsi was great to me.
John Ennis: Right.
Jeff Garza: I commuted two or three days a week and worked from home already, and this was probably like 2008, 2007. So like I was kind of already doing this hybrid thing. And then kids came, and and things just started to get a little bit more difficult just slowly but surely. And eventually, I had—I'm going to call them an angel supporter who basically said, 'Jeff, if you're going to go on your own, let us know, and we can give you X amount of business.' And like, for somebody that's contemplating going out on their own, like having that angel support is amazing. And really, that just allowed me to break off and kind of do my own thing.
John Ennis: Right.
Jeff Garza: It was interesting because at the time, my wife was really still a resident as well, and so like when you're the primary income and you've got little kids going around, you got to figure out how to make things work.
John Ennis: Yeah.
Jeff Garza: And consulting is tough at first, like—
John Ennis: Oh yeah, it's always tough.
Jeff Garza: Yeah. And you've really got to like be ready to like work all hours of the night. Like projects change, like data comes in at unexpected times, like the deadlines don't change. It's tough.
John Ennis: Yeah. No, I can relate to that. I mean, you know, my dad when he started IFP, he had a similar situation where, you know, I think SC Johnson was—we've published with SC Johnson, whatever, there's not anything confidential there. But without them, I think it would have been hard for him to go out on his own. And actually, in the early days of Aigora, our first client was IFP, and my dad helped me there. You have to have that. I think it's very—you know, people ask me a lot about starting their own business, and I think the two things you said: first off, make sure you've got some sort of business lined up, because otherwise it's going to be very hard. And the other thing is you can—you have total freedom, right? You can work any 20 hours a day that you want! So, like—
Jeff Garza: That is totally true! And actually, I think you know the the two people that were really kind of led my angel support: Dal Perio, who's at Starbucks now, and then Stephen McIngvale, who's at InsightsNow now, but they were both at WhiteWave at the time.
John Ennis: Okay. Yeah, two really good guys, actually. Yeah, I should have Stephen on the show. We—I had Dal on the show, I don't know, a year ago.
Jeff Garza: He was one of your early ones, right?
John Ennis: Yeah, he's been on twice, actually. So yeah, yeah, it's good. All right, great. Well, then let's talk about your kind of journey, because it is interesting the different paths that people take into the field. And you know, it's one of the things I love about sensory is the diverse background. So what were the things you had to kind of get up to speed on when you're coming out of, you know, purest stats, math, and now you're doing, you know, sensory consumer science? What was the kind of learning curve for you like at the beginning?
Jeff Garza: You know, one of the things that made that transition really easy is that sensory and consumer research really does use statistics pretty well. Like, a lot of times, my friends when they go to banking or insurance or whatever they branched out into, they don't end up using what they learned in school quite as much for whatever reason, like just the methodologies, whatever. But like sensory and consumer research, they really have a strong foundation in stats, right?
John Ennis: Right.
Jeff Garza: There are some tweaks. We treat things like continuous that aren't necessarily continuous. We do some things that are that I think people would or some good statisticians that I know might start crying, right? Like they just see how we treat the data. But there's good reason for that, and we've seen seen like it work well over time. We've been able to really use our results really well. I I love learning about segmentation. I love learning really putting my multivariate stats knowledge to work. And of any field, we use multivariate statistics so heavily that— I mean, it's honestly that's the most fun part about statistics to me is just the multivariate,
John Ennis: Right.
Jeff Garza: the segmentation, like realizing that people respond to these stimuli differently.
John Ennis: Yeah.
Jeff Garza: It can be fascinating.
John Ennis: Good experimental design is really important in our field too, I think, that we have such small—you know, you're never going to have as many—unless you're my dad at Philip Morris and in the in the '80s, they could do triangle tests with 1,400 people because their budget was like infinity! But, but generally speaking, that's not the case. Usually, we're resource-constrained, right? And so that forces a certain amount of creativity. So, you know, maybe you could—because I think in our preliminary call, you were talking about some of the forced creativity that comes from the resource constraints. So what are some of the things that you've seen, some of the fun projects you've been involved on, some of the innovations you've had to kind of come up with?
Jeff Garza: You know, some of those, some of the initial work that I've done over the years, I really loved working on popcorn. When I was at ConAgra Foods, and ConAgra at the time had Orville Redenbacher, they had ACT II, they—I think they also had some Jiffy Pop thing that like you'd buy in like this flat pan and put it stove top and it would pop. But like, the reason I loved it is it's really such a simple food. Well, two, the second reason is probably I love popcorn. But like, that slurry that's in the microwave bags just was a perfect like mixture design. Like it was the perfect mixture design. And and food and beverage has this special connection to mixture designs that they're just one of the most fun types of designs to work on. And you don't usually get trained mixture designs in school, but it's a natural extension. They're a special case for response surface designs. Optimization is fun. You get to work with the product developers, the chefs, the sensory scientists. You just continue to build those relationships. I loved working on popcorn. I loved working on something like Gatorade at Pepsi, that was that was fun. Tropicana orange juice was was awesome to work on. French fries—at the time Lamb Weston was part of ConAgra Foods. We look worked on french fries a lot. Even today of just walking down the aisle and just seeing the different products that we've worked on over the years, right? It's kind of fascinating. And I'm the type of person who works on projects, we get the results, we present them, we make decisions, move forward to the next steps, but then like I kind of forget what I did. Like as soon as the project's done, it goes goes into the background. We also worked on, I think, Cracker Jacks, soups, hot dogs, I remember hot dog drivers of liking.
John Ennis: Yeah.
Jeff Garza: And I really worked pretty closely with Tom Carr in those early years too, as as he was really so foundational in a lot of that early, probably 2000s stats work and drivers of liking types of approaches.
John Ennis: Right.
Jeff Garza: I think my my love of experimental design really took off in all aspects of sensory and consumer research, and that includes even the qualitative type of stuff, which I think people usually have this disconnect.
John Ennis: Right.
Jeff Garza: But but I remember working with some of the really good qualitative people, like Jackie Beckley comes to mind right away— —and how she set things up was actually as if it was a design.
John Ennis: Right.
Jeff Garza: The data's different, right? But like the way you draw your conclusions, the way you set up a good experiment, the way you you really try to foolproof it so that the conclusions you make are actually valid is is fascinating to me. And I think the best people in our industry, whether or not they, you know, they were quantitative or qualitative or whatever path they chose, like they still looked at their problems in a very statistical way.
John Ennis: Right, very scientific with the methodological.
Jeff Garza: Yeah, yeah.
John Ennis: That's really interesting. You know, actually, I had never really thought about that with qual, because of course, quant and qual have, I think, basically merged at this point with LLMs and I mean, even we were at EuroSense, right? We did that workshop where we had a phone at each table and we recorded the conversations and we were able to analyze the data just while people are getting coffee. It took two minutes to do the analysis and had it up on—it's really amazing. It's totally amazing, right? But I think that there's so much emphasis on the analysis of text. I think you're right that there could be a lot more thought put into the design before you do the focus group, going in.
Jeff Garza: You should, mm-hmm.
John Ennis: Yeah, that's really that's really quite interesting. Yeah, I should have Jackie Beckley on the show. I've talked to her about being on the show. I think I'll I'll reach out to her after this. Yeah, have her on the show. That would be really interesting. Okay, well then maybe let's talk that leads into how you've seen things change, because obviously we're going through a massive change in all of society with AI. And I think AI—I'm one of those people who is simultaneously pro-AI and also AI-skeptical, because I think that AI is awesome, but you have to use it very carefully. I think there's a lot of promises being made right now that are not really, actually supported by the capabilities. Yeah, maybe we could talk a little bit about what do you think? What do you see? How do you see the field changing with these new tools?
Jeff Garza: You know, I actually just was texting Todd Renn like a little bit ago, like— earlier today about something else, and I said like, 'I have this love-hate relationship with AI.' And it can make some things—I think I think it works for everybody a little bit differently, like the how how you and I might use it might be similar. You're probably going to take it to a more grandiose level than me. But like how I use it and how my wife might use it could be very different. And that's an amazing thing about AI is that it can actually be used in all these situations, right, in different ways. But it's also probably a trouble point, because it's like how do you do that well? And and so my love-hate relationship, the love side, wow, it makes like creating simple applications like amazingly easy,
John Ennis: Right.
Jeff Garza: Now, frustratingly, sometimes I cross-check those, and I have to cross-check them quite a bit sometimes, and when you end up cross-checking it enough that you're like, 'Oh, I could have done that myself in this amount of time,' like you get a little frustrated. But honestly, I think you just learn how to ask it better questions, so it gives you what you what you're really after. And I think that's kind of an exercise that everybody has to learn to do is to really learn how to ask it for what you really want and need. And then I think you also have to still be an expert in your field.
John Ennis: 100%.
Jeff Garza: Because if like, I've I get stuff from other people, and they have some stats knowledge, but there's some basic mistakes in there that they didn't—they just didn't think to ask. It's not really their problem, but like they didn't think to ask. And I do have a fear that like in these larger companies, you're going to end up with a somebody who just has kind of a tertiary statistical knowledge developing things, and then at some point they're going to find out that they're not getting what they thought they were supposed to get.
John Ennis: Yes. Yeah. That that's a real risk, I think, that you've—and we see this all the time, that the danger with AI is it always gives you something that sounds good at first, right? That the—it always looks good, sounds good, but it's not—I mean, I see it's weird, even these models, you know, that like even Opus 5.5—now, that just came out, so I would say I've yet to find a good example with this, but even Opus 5, which is quite a strong model, I gave it an optimization problem. And of course, you know, we get the code. All right, I started looking at it, like this is totally wrong! You know! And so then start pushing back on it, and it's like, 'Oh sorry, you're right. Okay, here's another attempt.' All right, it's wrong too! All right, let's let's look again. Oh, it's wrong a third time! And you know, Anthropic CEOs out there saying it's going to take all the jobs, well, it's going to be a mess if, you know— Now, 5.5 is probably a little better, but I just don't—I think, like you said, there's no—I don't think the current path is going to get to a place where human expertise is not needed anymore. I think that's really just not true. And my concern is I I do have a lot of concerns around education, that the—and I see it with my children, you know, that I really wonder—we're lucky we got educated in the before times, because when AI is always there and it's always going to give you something that sort of sounds right, you know, I used to spend so much time just by myself, pencil and paper, doing stuff, and now I can use AI well, but what is it going to be like for somebody who didn't have that experience, you know? That's definitely a concern.
Jeff Garza: I think that's completely true. I'm seeing it hit education at really all different levels right now. And maybe on the on the hate side of my relationship with AI right now is just last week we got the reviewers' comments back on an article, and one reviewer was like completely positive, no changes, it was really simple. The second reviewer, I read the first couple comments, and then—and it was a whole page—and it was obvious to me right away that it wasn't written by a human.
John Ennis: Mm-hmm.
Jeff Garza: And so I I wrote back to the lead author and I said, 'You know, I I think this person just copied the manuscript into Claude and asked it to be critical on the article, and, you know, 'Give me four or five potential things to work on or solutions to make the article better.'' And like that person then copied it into Claude, and it gave her almost like not verbatim verbatim, but very close to verbatim the same response. And so I was like, 'Wow, so this reviewer just took the manuscript, copied it into AI, and copied and pasted the results into the review.'
John Ennis: Right.
Jeff Garza: And in sensory and consumer world, like our our studies are usually set up a little bit differently, there's some unique twist to how the data is analyzed sometimes, and Claude caught that stuff and said, 'You know, this this may not be an appropriate way to analyze this.' So like it was interesting to me, but it—I don't think my—I don't know that I hate that. What I hate in my love-hate relationship is that it allows us to be lazy sometimes. Sometimes our human nature wants us to take advantage of that opportunity opportunity to be lazy.
John Ennis: Yeah. Right, right. Especially when you have a lot to do and you're busy, it's very hard not to give, yeah, that's right, yeah.
Jeff Garza: We're going to—I mean, that's just that's just human nature to some degree, is like we've got something that's going to help us get to the answer right away, let's use that, whether or not the answer is correct.
John Ennis: Right. It becomes a bit of a charade or a puppet show where there's there's no—yeah.
Jeff Garza: But that's—like you've just said, like it's not going to get rid of the experts, right? We need experts in the field. But used properly, it really empowers you. Like you can do something so much faster than—
John Ennis: Yeah.
Jeff Garza: I mean, it's almost like going from scanning scanning ballots into like the like we used to at ConAgra when I first started, they were still like it was still paper ballots that people were filling out and they'd scan in the data. And then that transitioned, right, to like everything's like automated now, Compusense and FIZZ and all these other other places, like that just cleaned up our data immensely.
John Ennis: Right.
Jeff Garza: We used to have to spend so much time just cleaning up data.
John Ennis: Right.
Jeff Garza: And now it's it's a completely different world.
John Ennis: Yeah. Now, I think used properly, it's automating mental manual labor, right? Where it's—that's the right use of it, you know? Like when I do a review, I use AI to help me do reviews, I've got a lot to do, but it would always be, you know, I read through the paper, I have my objections, I have my concerns, and then I work, you know, with an AI to help me write it up into a nice review. But at the at the heart of it are my concerns, right? And I think AI is an amplifier when used properly, where you have the expertise, you amplify it, right? That's, I think, good use of it. But when there's nothing being amplified, when it's just the raw Claude output with no human input, then I think it just becomes a charade. And then you have to wonder what's the point. Like, you could have put it into Claude yourself, right? Right, then what was the point of getting a reviewer to put it into Claude? So yeah, that's quite interesting. Okay, well we actually only have a few—we have about five minutes left, so I did want to talk about what you're excited about, and the things that you see that are like, you know, in the last couple years. What are some of the kind of new applications, use cases, things that you're—I mean, for me, obviously there's new models all the time. I'm really into text analysis right now, but what are some of the things you're excited about?
Jeff Garza: Oh man, that's a good question. I am fascinated by text analysis and how it's changed just really in the last—man, it's changed so quickly, like the last 10, 15 years, like it's just night and day. Where I really get involved with people a lot is when things go wrong. So like when—and in the from the AI situations, like sometimes people design a study, and they might actually ask AI to develop the design for them, and usually it does a pretty good job, like for the most part. Where where it trips up sometimes is just like in our world, there's always special circumstances that tend to arise, and it doesn't necessarily know what to do with those. So what I like like doing is I really like going back and forth with AI, asking it different questions, helping it having it help me think of some different paths of analysis that I may not have thought of before. And then I like to compare it.
John Ennis: Yeah.
Jeff Garza: Like it's a it's a powerful tool to kind of have this other path or paths of analysis to actually compare things to. It does some fascinating things with data quality, like just making sure that—and we kind of have our our kind of rote checks that we can do on data when we get it back to say, you know, these these people whatever, tended to flatline, or tended to like answer in a pattern, or whatever. But like those things are pretty powerful to just have AI do that for you, and to have a double check on the data data being clean.
John Ennis: Right.
Jeff Garza: I do like—like some of my favorite studies are actually crop all the way to like consumer. So a good friend of mine, Tommy Lee, did a lot of work with melons, a lot of seed work. And we kind of forget, when you work in a place like Pepsi or ConAgra Foods, you kind of forget that things go all the way from soil—
John Ennis: Yeah, yeah.
Jeff Garza: —and that whole path is fascinating to me. And I think it always has been, always will be. But I I just think we can do things so much better now than we used to be able to do them: the way we think about the problems, structuring the problems, attacking the problems. And AI, like really in every aspect there, there's a space for it.
John Ennis: Yeah. Yes.
Jeff Garza: And I think if you can use it really really well, it just makes you so much more efficient. I actually think your answers are going to be better.
John Ennis: Yeah.
Jeff Garza: But it does take the experts, and and it doesn't nix the jobs, I don't think. Maybe coding. I think if you're an amazing coder, like there's always a place for you, I think. But there's a lot of like kind of middle, middle-tiered—
John Ennis: Yeah. The job of write—the job of writing code is going away, but the job of man—but but technical—now it's just becoming technical management. There's more and more code that's getting written written, and people have to manage it. It just goes up a level. There's still lots to do, it's just touching the keys is is not the main thing.
Jeff Garza: You know, one fascinating use of AI for me has been almost treating it as if it's another employee. And I can say, 'Hey, go off and build this application for me that does XYZ. Make it reproducible. Button it up on all the different sides.'
John Ennis: Right.
Jeff Garza: It'll come back, it'll present to me what it did in a few minutes, right?
John Ennis: Right.
Jeff Garza: And then like I'll look at it and I'll go through and I'll say, 'Oh, you know, I would actually like to add XYZ as capabilities to this.
John Ennis: Right.
Jeff Garza: And can you do that? What are some ideas to maybe make it better?'
John Ennis: Right.
Jeff Garza: And it'll go off and do that. Like it'll, you know, you can do something that took months in really like a day, right? Like—
John Ennis: Yeah.
Jeff Garza: Now, I might run out of time, like my pre-purchased allotment of Claude or whatever, I might, you know, burn through my five hours of computational time in what seems like 30 minutes sometimes, because I ask it to do something it probably shouldn't do.
John Ennis: Right.
Jeff Garza: But like it resets, it allows me to think through my questions a little bit more clearly.
John Ennis: Oh, that's interesting.
Jeff Garza: You really have to take the time to—see, if you want to use it most efficiently, take the time to really structure out your questions and give it clear clear directions so that it gives you what you want. Otherwise, you will get some junk back.
John Ennis: Yeah, that's right.
Jeff Garza: But I actually enjoy giving it giving it very broad things sometimes, too, like, 'Hey, build me an application that does this,' and I want to see what it does, what the guts look like.
John Ennis: Right. Just for ideation. It comes up—I mean, right, for coming up with alternate ways to present the data you wouldn't have thought of, and that are interesting. Yeah. Yeah, that's really good. All right, Jeff, well, it's always a pleasure to talk to you. Unfortunately, we're pretty much out of time here, but how can people get in—[laughs] well, a couple—let's do two things. First, advice for young people right now. It's always a good question. Everything is changing so fast. It's very—people ask me for advice, I don't even know what to say. Just, you know, like the two things I would say: don't give up your thinking, and use AI a lot to get used to it. But what what what advice would you have for people right now?
Jeff Garza: I think for the the next generation that's coming up, um, I think it's don't be afraid to work at it. Like, a lot of the things that you're going to tackle through your education, through your job, they're not going to be easy. Like, and and the shortcuts can be really detrimental. Especially in this age of AI, when there's a temptation to really get lazy and take the shortcut, I think it's dangerous because there's ramifications to that down the line. And we're seeing it when we interview people, we're seeing it when people actually get hired and and they start their new job. We're seeing it with graduates from high school going to college. Like there's there's a temptation to take the easy path, but you really still need to know your subject matter, and you need to know it well. If you don't know it well, it's it's going to get called out at some point.
John Ennis: Right. Yeah. Feel very related to that.
Jeff Garza: For young people, it's it's really, you know, don't be afraid to put that work in. Like, learning to work hard is an amazing gift, like learning to be efficient. And I think I think AI plays plays right along with that. Like you can use it in a in a way that's going to take you down a slippery slope quickly, or you can use it to where you're going to like—I mean, you could change things. You could you could change change everything.
John Ennis: Yeah, no, I totally agree. Yeah, the fact that you can learn anything now, right, if you lean in. And it's all available to learn. But you have to put—but no one can replace the effort you have to put in personally. I agree with that.
Jeff Garza: Knowledge management is like amazing now, right? Like—
John Ennis: Yeah.
Jeff Garza: that's just, it's so different than the year 2000, like—
John Ennis: Yeah, that's right. Yeah. No, I mean I see THEUS—well, we have THEUS, you know, our knowledge management platform. And it's crazy how precise it is. And but it is, um—yeah, it's an exciting time, but like you said, you can't turn off your brain. You have to be personally involved. You have to be putting the work in yourself. Otherwise, you know, it's just this empty charade, and nothing is—yeah. Yeah. All right, Jeff, how can people get in touch with you? What's the best way to—
Jeff Garza: The best way is probably with through LinkedIn or to email me at jeff.garza@the-gc.com, but I think you have that in the notes.
John Ennis: Okay. Yeah, and we'll have your website also, they can reach out through the website.
Jeff Garza: Yeah, yeah. No, thank you so much. This this has been really cool.
John Ennis: No, I always love talking to you, so thanks a lot, Jeff.
Jeff Garza: I'm looking forward to seeing you at SSP, so—
John Ennis: Oh yeah, I'll be there at SSP. We actually have a workshop at it with, I think, Todd is going to be doing the workshop with us on on AI,
Jeff Garza: Okay, awesome.
John Ennis: so yeah, great.
Jeff Garza: Awesome.
John Ennis: Awesome. All right, thanks a lot, Jeff.
Jeff Garza: All right, take care.
John Ennis: Okay, that's it. I hope you enjoyed this conversation. If you did, please help us grow our audience by telling a friend about AigoraCast and leaving us a positive review on iTunes. And if you'd like to learn more about Aigora, please visit us at www.aigora.com. Thanks!
Aigora is a contributor to the Aigora blog, sharing insights on AI-powered sensory science and product development.
Tell us what your team is working on through our contact form. We'll review your request and reply within one business day.