1015: Mathematical Optimization in the Agentic AI Era, with Gurobi's Jerry Yurchisin

28:39Here is the model they're trying to solve. And then Garobi runs, gives you the output, you know, sort of gives the solution. And then you can dive deeper into why, why is this happening? You know, why, why did I decide to build a new production facility in Atlanta as opposed to Baltimore or something like that. And those are actual questions that you can get answers to with mathematical optimization. You can, because essentially what can happen in that situation is it'll resolve with the Baltimore production facility there and say, this is the difference. It is the difference because the cost is going to be this much higher, or you're going to have this much less demand or something, whatever it may be.

29:22You can actually sort of figure those things out and, and get to be able to answer questions that people are going to have when it comes to, you know, business problems and decision making is why this, why not that? Those are all things that can happen with mathematical optimization because of the, because of the structure and the rigor that's there.

29:39Jon Krohn:And so that kind of best of both worlds that you were describing there, where you can be having a conversation with a cutting edge LLM. You can be at the time of us recording this. Fable 5 is probably the most advanced LLM that the general public has access to. And so you could be having a conversation with Fable 5 about some business problem that you have, and it can be identifying potential gaps in your thinking. But then when it comes down to defining the mathematical optimization problem, it can also be helping you generate the code. And then you can review the code and say, okay, great. Nothing is missing here.

30:15Jon Krohn:and it seems like soon you're going to be able to have Groby provided MCP servers, model context protocol servers that allow that Claude agent or whatever agent, MCP is like a portable protocol that could be used by any LLM, any agent. And so a Groby optimization solver could then be called by the agent so that you get this flawless, deterministic, guaranteed optimal solution that the LLM on its own wouldn't be able to do. Yeah, we're working on a lot of things in that space. And one is MCP server. So how you can call our, we have a whole thing called the Groby Intelligence Hub now. And it has several agents within there that mostly right now we have a lot of interaction, you know, sort of just with like a chat interface and stuff like that.

31:09But it helps you really with that modeling part right there, that was just sort of just talking about how do I develop my problem statement? How do I write the code? How do I get the formulation and everything? We have a modeler agent that helps with that. So then you can then call that modeler agent within your IDE or wherever you want to work to help you sort of with all of that. Sort of say, okay, check my, I have this formulation now, can you check it? And this is what, you know, and so it's really cool where this is going and where we're trying to, what we're trying to take things next is we really want to streamline the modeling process.

31:45We want to streamline the support process as in like, hey, I have an optimization model. It's not running fast enough. Or I get like these issues or these errors. What can I do? First line of support is also we have an agent called Growbot that does that as well. And we're working on an explainer as well. So if one of the big issues that you get in optimization modeling, and if you don't get this, you consider yourself very lucky, is an infeasible model. It happens all the time. So if you're starting out and you get infeasible models, that's okay. It needs to happen. And what an infeasible model means is, so I've had all my arms so far, is essentially if that feasible region that I was describing has no points within it.

32:30So you have one constraint that points this way and another constraint that points that way, and there's nothing in between. So there's nothing that actually satisfies all of your constraints, that's an infeasible model happens all the time. How do I understand what that like, why is it infeasible? It could just be because somebody fat fingered a, you know, an extra digit somewhere and that's it. Or it could be because you literally have types of business rules that are legitimate, that are just, that just can't work together.

33:00Jon Krohn:Yeah. So, so yeah, helping you sort of identify and explain those things as well. So being able to call all of that type of stuff where you work, what we think is pretty important. And again, lowering the barrier to entry, that's what we want. We want more people to be able to use optimization. And so that's what we're working for. And that's sort of like our vision is having all these other agents do all those other parts or help with all those other parts. But when it just comes to the actual churning of getting that optimal solution, the wrong tool for the wrong job. Yeah, perfect. So agentic AI, LLMs, mathematical optimization, they can work perfectly together through these kinds of approaches that you're describing, MCP servers, chatbots, explainers that are helping you identify when you have created a model that is infeasible because you've added a bunch of constraints that you think maybe some, the business people in the organization.

34:01Jon Krohn:You talk to a bunch of different people in your business to identify where the constraints are on some problem. But when you put all those constraints together, you're like, wow, okay, there's no solution here because there's no place where, you know, there's no point in the space where reality can exist. And yeah, I love that. I love that, you know, you guys are kind of taking the best of what's been happening on the AI side, the LLM side, the agentic side, and allowing that to make using mathematical optimization easier than ever and increasingly more automated than ever. The explainer part of it is when you have people together and someone who says, oh, I'm on the planning side of things and this is going to be our budget for this or whatever.

34:48And then when you're able to clearly articulate, like say in this infeasible model, why it's infeasible and be like, oh, this is it's infeasible because these three constraints or these 20 constraints, one of which is a budget number, one of this is this and this, you're able to really sort of say, if we had more budget by this percentage, you can get very, very precise in this. There's tools that Garobi has that this explainer can help, one of which is called fees relax. Do you have an infeasible model? You run this sort of helper command and it essentially expands the model and makes it relaxes the model in a minimal way to sort of make it feasible.

35:31And it's a really helpful thing to then be able to say, oh, if you increased, if you increased our budget by 10%, then this is what we'd be able to do. So you can actually very specifically, like not just say, oh, well, it's infeasible. That's we're done here for today. No, you could actually really say, oh, to this group or to that group, what would need to change? And it just really helps with that process and say, oh, if I were to do this, then this is what would be able to happen. So it's a really cool way of, again, the whole framework of optimization and everything, it really brings that stuff to light.

36:07Jon Krohn:Does any of the functionality that you've been describing relate to, I know that a couple of years ago, we talked about on the podcast, Grobi building custom GPTs in chat GPT, which was a big trend for like a month, two years ago. And then I really haven't heard anybody talk about it since. And you've since brought that kind of custom GPT capability in-house as a standalone product. Is that product one of the things you were just discussing or something else? Yeah, that's it. Yeah, that's our intelligence hub. If you need to work through chat GPT or something like that, those custom GPTs still exist and they are helpful.

36:42But yeah, we decided to bring it in-house and really leverage the expertise of our technical teams to help guide these agents in their responses. We found that there's either sort of the best way to interact with an LLM or an agent about optimization is either using like the best of the best models out there from an agentic perspective or an LLM perspective. Or if you can't do that, then sort of like what is also equally as good, sometimes a little bit better, sometimes a little bit worse, you know, it all depends, is using information from like our sources. So using our, we have a ton of what we call knowledge-based articles.

37:26And these are articles that explain how to do things. I have this error. What do I do? I'm looking at my log file and this is this, this number that should be going down, isn't going down fast enough. Let's say, what should I do? All of that information, all of that knowledge is captured in what we call our, it's our grow bot is our, is, is essentially our product support agent. And all that information is there. So you can get, get as technical as you want. And And it should be able to help you improve your formulation or improve your runtime if you already have a model. And as I was talking about, the modeler agent before really, really helps you go from.

38:02I have a twinkle in my eye of an idea like, ah, yes, this would be great. And you could just sort of start with very basic stuff. And again, ask you all those interesting questions to help you really define a good problem statement. One thing that we noticed is if you were to go to, let's say you're not an optimization. expert and you were to go to any other, I'll call it vanilla agent or something like that, nothing that is sort of that has the knowledge of specifically that is looking at the knowledge of like Garobi or something like that. It likely won't follow sort of what we would call best practices of building an optimization model.

38:39And part of that is, you know, the iterative process of understanding the problem statement. But it's also building sort of test scenarios in which I know if I have a certain point that it should be a certain set of values for my decision variables, that it should be feasible at least. So you can then test that and it'll build tests that do that. I know this point should be infeasible. So it'll then test that. So it really helps you get that testing done that helps you get confidence in that the model that you're building is actually representative of the problem that you have. And which I think is as, as people who are probably not most of your audience is probably not optimization experts.

39:22That's an awesome thing to be able to do. It really just helps instill best practices. Garobot is the name of that, right? Garobot is the support agent. We just call the modeler, the modeler. I don't know. We didn't come up with a fancy name for that. Um, yeah, but it's all under the Groby, um, intelligence hub. Fantastic.

39:39Jon Krohn:All right, I'll have a link to the Groby Intelligence Hub for sure, and a specific link to the Grobot. I also just quickly, at some point while you were talking a while ago, I did look up the name of that Sinan Osdomar book where he has lots of experiments on LLMs not doing things that you specifically told them to do, which is a problem that you don't get with mathematical optimization. and that book is called Building Agentic AI and I can't believe I didn't remember the name of it because that book is in the John Crone signature series that Pearson publishes but I wasn't 100 % sure he has so many books that I wasn't 100 % sure that it was that book which is the first and only book that he's published so far in my series that Pearson does.

40:21Jon Krohn:I promised our listeners at the beginning of the episode that we would have case studies beyond supply chain examples which are kind of the bread and butter historically of optimization. Do you want to hit us with some of those energy and financial services examples? Yeah, energy and financial services are two of the areas that we're seeing a lot more adoption of mathematical optimization. And part of that is some of the stuff that I was talking about before, particularly with, actually for both of these, but particularly in energy, the nonlinear aspect of things was kind of like, oh, yeah, this isn't representative of what we want.

41:00So we're not going to do it. Or if we do try and linearize things, it goes with the one of two ways where it blows up the problem or becomes not representative enough. So there's a bunch of problems that more people are using optimization for in terms of what we call a unit commitment problem. So essentially, how do I sort of what power supplies should I be using in order to meet demand? How should they be scheduled? What units should I commit at certain times and things like that? And there's other problem variants that really take into consideration the physics of energy, of energy supply and everything like that.

41:35And we're seeing a lot of renewable dispatch optimization problems as well. So, OK, I'm able to have like solar panels or wind energy or something like that. and those can fill out batteries. How can I then dispatch that in order to, when should I do it, in order to make sure that you meet demand and minimize costs and things like that. So those are a few of the problems in energy that we're seeing more adoption of optimization for. And on the financial services part, there's a lot in sort of retirement planning is one where we have a pretty cool um case study um from a company called uh my goals uh i believe i believe they're called so uh definitely uh sort of hop on and check check out that that case study as well and what's really interesting about about that case study is there's just a lot of regulations that need to be met when it comes to planning for your retirement and i think i believe this is in it's a canadian company so this is from the canadian yeah yeah i looked it up while you were speaking so it said i could

42:40Jon Krohn:put a link in the show notes and my goals is a Toronto based fintech platform. And they use the Groby optimizer to help individuals balance competing life and financial goals. You talk about these constraints and you could imagine, uh, people, this is a really good example of like how you could as an individual kind of have an infeasible region, uh, in, in the way that you're thinking about your finances where you're like, all right, I'm going to have this sweet car, send my kids to private school and have these kinds of savings on this salary. And, uh, yeah, the optimizer is like, sorry, that's infeasible.

43:17Jon Krohn:That's rough. But then it could, uh, if you built this, you know, you have, if you have, uh, like this model, you can then see like, okay, well, what should, what changes should I make? Again, it's, it's, there's a lot of the explainability that I really want to sort of emphasize is like, okay, if it is infeasible, which kind of rough to say, okay, should I not send my kids to this school or should I not buy this card? I mean, but that's life. Yeah, that is, that is. And, and those, those decisions can be sort of brought to light and what changes you would then need to make. For sure. And so according to this case study, my goals using the Groby optimizer improved after tax retirement income by 2 % to 10 % compared to conventional planning tools, resulting in income outcomes, 10 to 20 % greater, which is a lot.

44:03Jon Krohn:Like if you think about how much more you'd have to work or the kinds of things you'd have to save on in order to, you know, to save 10 or 20 % more over your life. And then it also said that because of the kinds of things that you've been talking about throughout this episode, where you can run the mathematical optimization in different scenarios. Like you were talking about Baltimore versus Atlanta. And so that kind of thing applied to your own personal finances, your own life. It allows the My Goals platform powered by Groby Optimizer to, instead of generic rules of thumb, evaluate multiple goals simultaneously and build actionable, tailored strategies.

44:43So that's a really cool example that I bet a lot of our listeners are going to want to

44:47Jon Krohn:check out. All of the other regulation stuff that happens is all stuff that, yeah, those are all hard constraints. You don't want to run afoul of that. You don't want to mess that stuff up. Yeah, just make sure that the things that can't happen can't happen. The things that must happen will happen. Cool. And I believe you also have a fun USA Cycling example. Is that right? Yeah, this one's one of my favorite over the last year. So when you think about riding a bike in a competitive situation, how that's not at all like long term supply chain network design planning. You know, it's just like so different.

45:24I'm like, okay, how should I physically be riding a bike? And that is just, they're just so different. That's why I sort of really like this problem. There's a paper, an academic paper that was written about this as well. So you can look into it. You can find a video on our website. I think you need to put in some information to get to it. Yeah. So essentially there was USA Cycling, I believe the women's team, they were doing sort So the indoor, one of the indoor events. And there's a lot of interesting sort of decisions that can be made when you think about I have a four rider team and they're in certain positions.

46:04Each of those positions have different sort of like drag amounts and things like that in terms of like how much wind resistance there is. And you can think about how, okay, so I'm riding around in circles with my team. And then how can I conserve energy? How can I make sure that certain people are in certain positions at the right time? How can I make all these sort of types of decisions like rotation strategies and things like that while also making sure that you're adhering to the rules of the game? I think I use that as an analogy like the first or second time I was on. It's like optimization is like rules to a game.

46:39This is actually rules of the sport that need to be adhered to. But essentially with optimization, they were able to sort of develop a sort of like a prescriptive plan about how much, literally how much effort you're supposed to be putting forth at a certain time. What sort of order you're supposed to be in a rotation strategy between you and your teammates. What's the best way for us to run a race given all of these physical, like sort of the physics of air resistance, plus energy levels, plus all this sort of stuff. in order to minimize the race finishing time? How fast can we go? And it's just a really interesting and very different case study in which there's a lot of detail that happens in there, a lot of cool things.

47:26And it's just a very different perspective on optimization, which I think highlights the usefulness of it. Because if you think about going back to what I was talking about at the beginning and before, what are the building blocks of optimization models? I have decisions to make. Okay, who's going to be in the front at the beginning? When do they start swapping? how much energy, how much effort should I be giving at certain times? Those are my decisions. How are they constrained? Well, I need to have people in a line and then like other things that need to happen. And then what's my objective?

47:52I want to minimize the time it takes to finish a race given all of these things. Yeah. That problem has those characteristics and therefore is able to be solved with mathematical optimization. So it's a really cool case study and really interesting application of optimization in a way that you just wouldn't normally think. And I find myself part of the problem sometimes with that because like there's such big use cases this big case studies where tons of money has been saved and all this sort of stuff with these big companies doing big problems and it's like all supply chain logistics and all that yes that's awesome but then these things come around where something just very different is there and and the benefits are awesome and it led to i mean it led to a gold medal finish too so that's so that's the thing i also want to mention too it wasn't just like oh we got better it was like literally like Like they were like part of the process was regression analysis to sort of figure out what times that they would need in order to fit it in order to take the gold.

48:49And that set like their standard for the time. And then given this sort of like we need to be in this ballpark, like if our objective can get in this range, we have a shot. And it's just really interesting sort of how they put everything together. And I highly recommend reading the paper on it if you don't mind seeing a little bit of math in there. Even if you sort of gloss over those parts, it's still a really cool story. but then also heading over to our website to sort of check it out. And I know we'll probably hit on this a little bit but the presentation that you would see there was given at our Decision Intelligence Summit.

49:22So that's the type of stories we like to tell when you go to our summit event to sort of learn more about optimization. So I think we'll hit on that a little bit.

49:36Jon Krohn:On this podcast, I'm always going on about how Claude Code is mind-blowing, but now Claude Cowork is making my jaw drop as well. For example, I recently wanted to quantify how healthy my sales pipeline is for my AI consulting business. I simply asked Claude to estimate my sales for the coming quarter, and it brought info from relevant Google Sheets and my Gmail to create a professional spreadsheet of clients with estimated revenue for each one. Whoa, this might've taken me a day. Instead, it was done flawlessly with Claude Cowork in minutes. Claude is the AI for minds that don't stop at good enough.

50:07Jon Krohn:It's the collaborator that actually understands your entire workflow and thinks with you. Whether you're debugging code at midnight or strategizing your next business move, Claude extends your thinking to tackle the problems that matter. Ah, and you'll appreciate that I can ask Cowork to show me data, such as my sales spreadsheet, and it provides an interactive chart right in the conversation. For problems worth solving, get started with Claude at Claude.ai slash superdata. That's Claude.ai slash superdata. And check out Claude Pro, which includes access to all of the features mentioned in today's episode.

50:36Jon Krohn:claw.ai slash superdata. We will. We'll hit on that for sure. Yeah. So I'll have a link to this paper in the Informs journal on applied analytics. It's called Project 405, Optimizing USA Cycling, USA Cycling's Women's Team Pursuit Gold. It's a mouthful of a title. But the key thing is that in this project 405 uh the specific event that usa women's team won gold at was the paris 2024 olympics yeah and yeah so super cool we got the paper and they used uh python mixed integer programming and the groby optimization solver to be able to optimize and contribute to that gold medal results. So super cool.

51:23Jon Krohn:Um, it sounds like it even identified talent for the team, which is a wild kind of thing that I wouldn't have even thought was a possibility, but basically talent that wouldn't have even been in the team were identified by identifying optimal physiological profiles and matching cross training athletes to different cycling disciplines. That That is wild. That right there sort of just shows the multidisciplinary sort of approach that I always preach with this kind of stuff. A lot of that information, a lot of the data and a lot of that stuff is perfect for your traditional machine learning type of things.

52:06And that is so important. But then also, it is also so important to come up with this optimal strategy. So, yeah, these these types of of analytics are need to be working hand in hand, pretty much like for every problem, I think. So if you're not using both something that is like a prescriptive, it doesn't always have to be mathematical optimization. I'm not going to say it's it's the it is like the holy grail of prescriptive techniques. It does a lot. But, you know, but I just always encourage to make sure that you're using as many techniques to fill in the gaps as possible. Now you don't want to just throw, you know, everything at every, at every problem.

52:44You want to make sure that that it's actually applicable. But again, you know, we just always sell ourselves short. I think as many quivers as you can fit on your back. Yes. That's the same.

52:55Jon Krohn:Um, all right. So let's say we have a listener who's like, sweet, aeropy optimization sounds perfect for this situation that I have in my business. and then they go check out some of your tutorials, chat with Girobot or take advantage of Girobi Intelligence Hub materials and then they actually identify a problem that they're like, wow, look at this perfect situation. I'm pretty sure I identified an opportunity to save us money or increase profits or whatever. How do you get that change management to happen in your organization? How do you explain mathematical optimization to your boss, your boss's boss, and so on to actually get your solution implemented?

53:41Yeah, this has been a big effort on our part with internal Tegurovi to help our customers do this. Because that exact problem is something that we hear a lot of. There'll be someone who is like what you just described. We would describe them as an internal champion of optimization. They're sold. They know the benefits. They know what they can do. They know the problem they can solve. But they're not going to be able to do that. You can't just like go run off and spend half of your time solving a problem that your boss doesn't think is useful. So up the chain, you're going to get some resistance.

54:15And also in implementing things and down onto the more like planning level or something, the people actually doing the things that the model says, you might get some resistance there as well. So we've been putting together a lot of material, which is yet to be released, but we're working on it to really help with those questions to help people understand, OK, if I'm say I'm an optimization modeler now or your data scientist who's doing optimization and you've identified this. if I'm talking to, you know, like my CFO or CEO or, or maybe just like a couple levels up, it's like a, you know, a manager, a director, somebody up there, how do I talk to them?

55:00Like, what should I be bringing to their attention about the benefits of optimization? And a lot of that would be stuff like a big thing is the difference that I was talking about between sort of agentic sort of AI, LLMs, generative AI, what that's good for and what that's used for. versus optimization, what that's useful for, versus like sort of, again, traditional machine learning, what is that used for? So being able to clearly articulate those, like the benefits of each of those things, because you're, if you bring this up and you say, oh, you know, hey, I think I have a way to save us millions of dollars is using optimization and here's all the things that we need to do.

55:35Like probably a question is like, you know, we have a clause description, we have a chat GPT subscription, we have this, we have that. Why can't I just ask the LLM to do it? Because an LLM is going to be like, oh, yeah, I got you. Again, that confidence that it has is so misleading at times that it'll be like, yep, I'm optimizing your supply chain right now.

55:55Jon Krohn:And then it forgets all the stuff that we talked about before. So being able to clearly articulate the differences there is super important. Understanding the right terminology to use, how you should frame the business problem. Hey, because if you talk about to sort of management and you say, oh, well, I'm able to increase productivity by a small percentage or something like that, they'd be like, well, OK, that's great. But what does that really do for us? What what benefits is that, you know, from our maybe possibly probably likely the bottom line? Like what how much monetary value is this producing?

56:27So that's that's one way to think about it. And then also, but then down, you know, sort of downstream of things when you have the people who are actually who have 15 years of planning experience or something that they've been doing their job with, you know, with with their their brains, their gut and maybe an Excel spreadsheet or something like that. And they've been doing it that way for like 10 years and they have all this experience. All of a sudden you're like, oh, well, I'm going to I'm going to bring in this tool that is going to optimize things. And and they're going to be like, well, what the heck's going on?

56:56Like, how do I fit in? Am I being replaced? Those are lots of questions that you need to be able to answer. You're going to get pushback on that. Internally, when we talk to a big effort for us to understand this, is talking to our sales representatives, our leadership on the sales team, our technical sales folks as well. And that is a legitimate concern is if I implement an optimization model for like some scheduling problem and you have someone whose job it is to do the scheduling, they're going to be like, well, where does this leave me? What is this like? Are you forcing me out or what's happening there?

57:37And essentially, one of the big takeaways that I like to talk about from our NFL example, where again, Groby is used for as the engine to solve the NFL scheduling problem every year. It didn't replace the scheduling team. They're just able to be more like super more efficient instead of like trying to come up with like one schedule. Now they're able to analyze like thousands of them and they're all high quality schedules. So they're able to do their job differently. And I think that's what you want to articulate to the people who are, who's sort of quote unquote jobs, this might replace or something that is like, no human in the loop is always going to need to be there.

58:19There's always going to be, there's the saying of all models are wrong, but some are helpful, that type of thing. There's always going to be some sort of like human, like, well, maybe this one's slightly better than this one, or this is the thing, you know, we, I would rather go with this because of that, you know, something like that. There's going to need to be some sort of human in the loop. And optimization could still be teaming up with people in that respect. So when it comes to talking to sort of one audience about optimization, you need to be highlighting, hey, this is the value that it brings.

58:51This is how it affects the bottom line. This is how it helps us become maybe more robust as an organization. And then down the line, when you get to the implementers of the decisions, this is how it's going to make your job easier. This is how it's going to incorporate your expertise. Because one of the easiest things, you know, start poking holes in these tools and the arguments that these tools bring is, you know, you're on an optimization model and somebody with like their, you know, 15, 20 years of experience, like I'd never do that. That's stupid to do that. I would never make this decision.

59:27Well, now you just learned a new constraint. That is something that should be that that shows that you need to have these people involved in the in the modeling process to be like what is the thing that you would never do or why would you never do this and be like oh well because of x y and z we would never do that and now you just learn something about how your system needs to operate so so those types of people have the experience and the expertise to really bring the realism to your optimization model so they should be you know just as involved as anybody else in terms of building the model, building the application and things like that.

1:00:04So, so being able to talk to both sides, here's the value, here's where it affects our bottom line, but here's how it's going to make you more productive. Here's going to help your life. Here's how it's going to make your job easier or better are things that you need to be able to articulate as you're sort of going down this optimization path. Yeah.

1:00:22Jon Krohn:So you can speak to management about the value, the bottom line, how they're going to save money while simultaneously you can be speaking to the people who are going to be using these tools and make it clear that this is not going to replace them is going to make them better at their jobs for people who now want to be able to get going and add optimization to their toolkit where should they start the first website to go to is just groby.com slash learn that will take you redirect you to another site where it has essentially all of the the training that that I've led over the past few years. We have a whole series of four trainings.

1:01:00It's optimization for data scientists, Opti 101, 201. We did a 202 and then a 301, where it takes you from the absolute beginning of optimization to some pretty techniques and things where we hit along things about the difference between machine learning and optimization. And again, from an AI perspective, how it fits into sort of the AI landscape and how do you deal with uncertainty? Because that's a big thing. You know, your demand forecasts are not perfect all the time. So we really sort of tried to run the gamut there. So that's a great way to start. We have a, we worked with a professor, Dr.

1:01:37Joel Sokol at Georgia Tech. He helped us produce another more in-depth training. So the training that I was talking about, each of those are like two, four to five hour sessions and stuff like that, which all of those things are YouTube video, YouTube playlist now with Jupyter Notebooks on our GitHub. The other thing is on a Udemy course that has four parts. So you can check all that out to really get from I'm just starting out to I kind of know what I'm doing now. I'm dangerous and a good kind of dangerous. I can actually solve some problems here. But again, I'll always say that there's always room to learn.

1:02:14So I think between that, And then honestly hopping on at the Intelligence Hub, using the Modeler to help you understand your problem in the context that you want. So you can say, I'm new at optimization. I want you to help me solve this problem. Limit the notation for now. Like, I just want to see this. And really, the Modeler does an exceptional job of not showing you all of the, here's your formulation, and it's all math right away. Like, just get rid of that for a while. You do need to understand it at some point. But you can really sort of give it a little bit of a profile on you and what you want.

1:02:49And that's super helpful as well. So I say that that website, we have tons of Jupyter notebooks that you can use that are all over the place in terms of the industry and the application and the difficulty as well. So I'd say that's kind of like your one-stop shop. And if you do need to explain the optimization part, the burrito optimization game is good for you to learn. but then also that's a great tool to send to your management or to to the planners the the end users and be like oh this is why optimization is helpful because within again like two rounds of that people are severely suboptimal same thing for the groving game as well there's a little bit more randomness there um because there there is some simulation involved and stuff but but you can really quickly see that you know gut intuition experience what i think you know i ended up just not they're not accurate ways of making decisions.

1:03:42So all of those can be found at that one webpage. So I'd say that's the first place to start.

1:03:50Jon Krohn:Cool. Garobin, the burrito optimization game, but above all, garobin.com slash learn for all the educational resources that you and your team have been putting together. If people want an intensive, more interactive session, I believe you also have an annual two-day training called optimization for data scientists coming up. Do you want to to talk about that? So all of those, the Opti series that I was talking about that is we have decided to rebrand that a little bit. So we're done with the optimization for data scientists, but it's going to be more Gen AI focused. So, and not just talking about the tools that we have, it's not just going to be, oh, we're going to use the Groby Intelligence Hub for everything.

1:04:30We know that that's not how everyone's going to want to work. And we want to try and teach the lessons that we've learned of really how to put optimization together with generative AI and how these things should really work together in a more general context, general framework. So we're not going to be using all of our stuff, but we will be using sort of cloud code and things like that. And how can you really get the most out of this? What are the things you really need to focus on in order to get the best output? What are the best ways for me to prompt things? when should I be doing this versus that?

1:05:06So a bunch of techniques and a bunch of ways, a bunch of lessons learned that we have. So that will be, I believe, in mid-November. So we got some time, but it's going to be like, I think we're calling it like OptiGenAI something. I don't, we haven't really finalized the name yet.

1:05:20Jon Krohn:Are there dates finalized or a URL people can go to or anything like that yet? We don't have a URL or anything, but we do know that this training is going to happen either November 19th and 20th or one of those two days. We haven't finalized if it's going to be one day or two days, but the end of, you know, that the end of that week in November 19th or 20th, we'll have, we're going to have that, that training that's again, focused on Gen AI and optimization working together as two best friends should. And that's online. It'll all be all remote. If you can't make it, if you're, you know, you're, you have other stuff happening, you can still register and do it all on demand afterwards.

1:05:56Everything's recorded. Notebooks are there, you know, all that sort of stuff will be there. and we leave it open for I think like a month or something like that. So you have plenty of time to dive in to that content and work through it.

1:06:10Jon Krohn:Nice. We'll keep an ear out for that or reach out to Jerry as November approaches. I suspect we might have sponsor messages on the podcast for it. But something that we do already have sponsor messages running for is the Grobi Summit, which is in person in Las Vegas. That is coming up as well. that is kind of, that's not necessarily as technical as the, what used to be called optimization for data scientists thing. It's something it's on September 22nd and 23rd, uh, at the Aria hotel and resort in Las Vegas. And that's more general, right? Like that isn't, that isn't necessarily targeted at just technical people, right?

1:06:50We know our audience. And if we didn't have some technical stuff there, they would be very upset with us. That's why we kind of have two days. The first day is sort of more focused on the, you know, the usefulness of optimization, getting actual, like we invite our customers, our people who use Garobi to tell their story. So that's where, again, where that USA Cycling example was discussed, was at that event. So you'd be able to hear those cool stories, see how people are really using optimization and not just like see it. And then you can just, then you can go talk to them like oh that is something that's really close to what i'm doing can you tell me more about it and it's a it's an event in which people really love to share what they're doing so we have a lot of that a lot of like let's let me share my story with what how i'm using optimization and and the benefits that it's giving that's kind of like the the big day one focus um the second day is more a little bit more technically focused and we have two tracks one of which is what we call an advanced track.

1:07:50So if you are someone who is really good at optimization, you can hear from our super genius experts on the cool stuff that they're working on and how to deal with these problems at a very super advanced level. That's there. And then we also have what we call a beginner track. And again, we start from the basics and that is going to cover sort of, hey, what is optimization again in the context of the AI world that we're living in now. I want to get some basic examples out of the way, sort of start with basic modeling. We use our Python API, so Garobi Py, and then we are going to go actually through a pretty longer session of using the intelligence hub and using the modeler and developing a model, and then using Garobot to help sort of debug and make it run faster as a support tool.

1:08:44And then also the explainer as well, like, hey, things have gone wrong. Why? What can I do? So we're going to try and have that whole story told there as well. So it's a great way to meet people who are doing the problems that you feel like you should be able to be doing in your in your company and sort of really see firsthand the benefits there. um so i can't suggest the event enough i will be there so if you want to say to my face that you did not like my opti 101 training then you can do that as well or you can say hey that's pretty cool i appreciate it um i don't i'm always a little i'm a little self-deprecating at times so um just in case if anyone does have some criticism but uh but you can then meet other people who are much smarter than me on this as well we do bring a we do bring a lot of grovi folks there.

1:09:33And you'll be able to talk with the best of the best to help you out.

1:09:36Jon Krohn:All right. So yeah, Jerry and some smart people at the Decision Intelligence Summit 2026 coming up in Las Vegas, September 22nd and 23rd. Jerry, we are out of time today. This has been another fantastic episode. So great to hear all the updates happening in the mathematical optimization world this year, particularly as it pertains to, say, Agentic AI and lots of other industry applications, including energy, finance, those USA Cycling successes. Before I let you go, do you have another book recommendation for us? Yes, I do. And this one's going to be a little on the oddball side of things. I did two stints of graduate school.

1:10:15One was general applied math, and then I got into operations research and statistics after that. But when I was doing the more general applied math, I had to take a graduate level geometry class. and part of the reading that we needed to take we needed to do in there is we needed to read this book called flatland and it is a super unique way of exploring the relationship between geometrical objects like a point versus a line versus a polygon versus a three-dimensional shape and if you were to take all of those sort of things and take those and make them sort of like living beings then also put it in like a medieval setting um that is what you would get in in flatland and it's just a really interesting way of of sort of exploring uh sort of the basic principles of geometry in a really weird way uh i that's the only way i could describe this book is really weird but it's really interesting and it's really fun to to read it's got like a little bit of um it has some issues in it but overall it's still pretty it's still pretty cool um i would i would recommend reading it for just for it just for the comedy alone but it is a really good way of i guess sort of one of the through lines that i've been talking about is like you need to be able to talk to people the way that they are you know in their language you need to be able to communicate complex ideas in different ways to reach different people.

1:11:51And that's kind of the takeaway of this book is, is you need to be able to talk about what you are as a geometrical figure and relate it to other ones that just kind of don't understand. If, imagine if you were a two dimensional line, how would, and somebody said, Oh, I have three dimensions. I have height, you know, not just length and width or something like that. Um, or, you know, I have, I have three dimension instead of two, like it's sort of, but it really does like an interesting, has like the interesting interplay of like, how do you talk about something that somebody has no idea what you really mean?

1:12:25Um, so, uh, so it's pretty cool from that perspective as well. So I highly recommend it.

1:12:29Jon Krohn:Nice. And you're not the first person who has recommended flatland to me. So thank you for that recommendation. I think it's probably a good fit for this audience, uh, as opposed to an oddball, suggestion. And yeah, final question, Jerry, as always on this show, we already know about things like groby.com slash learn is a great resource for groby. But for you personally, how should we follow you for your thoughts after this episode? So I'm relatively active on LinkedIn. So follow me there. Follow groby on there as well. I also have a blue sky handle so you can check out what I have to say there so often.

1:13:05So that's a math with Jerome, um, on that platform. Um, and cause I do also go by Jerome, um, just to, just to throw that curve ball in there. Well, I think we probably explained that away a long time ago. Um, so you can follow me there.

1:13:21Jon Krohn:Yeah. So, um,

1:13:26nice. Um, so yeah, that's probably the best ways to sort of keep up to date with what, what I'm thinking and, and what Garobi's working on and what's happening in optimization.

1:13:36Jon Krohn:Well, thank you, Jerome or Jerry or whatever you'd like me to call you. And I hope we'll have you on again next year to see whatever wild AI environment we're in in 2027 and how mathematical optimization is making all kinds of problems solved that otherwise would still not be solvable. You'll probably talk to an AI agent named Jerome, and I just won't be here. Sounds good. All right. Jerry, thanks so much again for coming on the show and catch you again soon. All right. Thanks, John. I appreciate it. So great to have Jerry Yurchison back on the show today. In this episode, he covered the three building blocks of any mathematical optimization problem.

1:14:21Jon Krohn:That's one, decisions you control, two, constraints on those decisions, and three, an objective to maximize or minimize. He also talked about how any problem with those three characteristics can potentially be solved optimally regardless of industry. Separately, he talked about why LLMs shouldn't be trusted with high-stakes decisions on their own, since they'll confidently claim they've optimized your business while occasionally ignoring an instruction, whereas optimization treats constraints as hard guarantees that cannot be violated. He talked about the division of labor he sees for the agentic AI era.

1:14:57Jon Krohn:Agents help you define the problem statement, write the formulation and generate the code, then hand off to a solver like Garobi, soon callable via MCP servers, for a defensible, explainable, guaranteed optimal solution. And he provided some fun case studies at the end of the episode, including improvements in after-tax retirement income relative to conventional planning tools and USA Cycling, which used mixed integer programming to plan rider rotations and effort levels en route to gold at Paris 2024. As always, you can get all the show notes, including the transcript for this episode, the video recording, any materials mentioned on the show, the URLs for Jerry's social media profiles, as well as my own at superdatascience.com slash 1015.

1:15:40Jon Krohn:Yes, these numbers are getting big. Yeah, thanks, of course, to everyone on the Super Data Science podcast team, our podcast manager, Sonja Breivich, media editor, Mario Pombo, partnerships manager, Natalie Zajski, our researcher Serge Masise, and our founder Kirill Aromenko. Thanks to all of them for producing another Optimal episode for us today, for enabling that Optimal team to create this free podcast for you. We are so grateful to our sponsors. You can support this show by checking out our sponsors' links, which are in the show notes. Otherwise, help us out by sharing this episode with folks that would like to learn about mathematical optimization, review the episode on your favorite podcasting platform or YouTube.

1:16:22Jon Krohn:If you rate an Apple Podcasts review, that is particularly helpful for us for getting word out about the show. So bonus points if you do that. Subscribe if you're not already a subscriber. And most importantly, I just hope you'll keep on tuning in. I'm so grateful to have you listening and I hope I can continue to make episodes you love for years and years to come. Till next time, keep on rocking it out there and I'm looking forward to enjoying another round of the Super Data Science Podcast with you very soon.