Videos

Map is where Imubit starts. Every plant runs to a plan, built on economic and operational assumptions. If the plan lives in multiple places, Map pieces them together. Then Map looks at how the plant really runs, across the whole facility, and finds the gaps between the two.

It traces each gap to its causes, and to the recurring decisions behind it. It ties every objective, concern and constraint to those decisions, to the disturbances and the measured outcomes in the plant, and to the people who own each one. What looked like a monolith becomes a map you can act on: which gaps matter most, and which decisions to take on first.

Model is the cause and effect behind the map. It shows how each decision moves each outcome, against its objective and its constraints. These relationships are nonlinear and dynamic. They change over time, and plant data is never complete, so data alone is not enough.

That is why first principles are built into every model, and nothing sits in a black box. Every relationship is visible, causal rather than correlated, and deterministic. A Deep Learning Predictor learns each unit's dynamics from years of its own data. And with DLPC Builder, your process engineers build models of their own units, without Python or a machine-learning background.

Your engineers can make their own models and create their own competitive advantage.

Control is where the decisions get executed. AI controllers take the key recurring decisions behind your gaps, and steer them around the clock, minute by minute, to maximize your objectives inside your constraints, through your existing APC and DCS. Reinforcement learning trains them across every regime the unit has run, millions of simulations and thousands of simulated years, before anything reaches the plant. What ships to the plant is a deterministic controller your engineers can certify and validate.

It does not hallucinate. Given the same inputs, it gives the same move, to every person, every time. Closed loop always runs inside the envelope your engineers set. And every gap you close is measured, continuously, against the plan.

So this, again, is about the community. This is not just about the technology. Technology is a way to advance our thought process and find new ways of doing it. Because technology is just a means, you know?

It's not the ultimate goal. It's been cool to see that there's other companies that are in the same boat. I'm here to try to understand what other companies are doing with similar problems. So it's very hard to find a real technology company that's actually making a real impact on the world.

Third is, as corny as it sounds, the people, right? A ton of smart, amazing people that I got to meet. I've learned so much and I've grown so much being around some of the smartest people I've ever met, and jumping into new topics I never thought I would have discovered. And so bringing together my love of technology and my desire to help make the world a bit better, I found myself at Imubit, and it's been an amazing run.

Until right around COVID, I joined a big company where I was the serial number, and I started chasing margin and volume. And I've never been as uninspired in my life as I was at that time. So finding Gil, finding Imubit, I kind of re-centered myself back to making an impact. And I've been here five years now, and every day I come to work, I make an impact.

My background is in electrical engineering, mathematics, computer science. Shamefully, I'm not a chemical engineer, but I am trying to learn from you all. So first, you know, I got to be empathetic to those black box vendors. We used to be one as we started.

And some people here and colleagues may remember explaining, Gil, you don't want to be a black box. They know that we're genuine people trying to help them solve problems, and I think that's really, for a product person, you can't do much better than that. But it was only when we started to release the power of our technology into the end users, to actually be empowered to build their own models and see the challenges they're facing on a daily basis, that we started to really see the unlock that's really possible here, and we're just at the surface of it. Feel free to join the team.

If you don't want to participate, that's fine, but we've got prizes. And we're actually going to use Claude Code and actually solve a real problem. The other point is, we have an aging workforce that we also talk through. It's not necessarily just talking to the folks that have been doing it for decades and have all this knowledge in their head, that they're finally at a point where they're indispensable for their respective company.

But if they want to retire, what's their legacy they're leaving behind? And now, more than ever, there's the ability to bridge that gap, catch them up, and then have them go even further. So it's a legacy play, and it's, I think, something that's gonna be really interesting to see how far that new generation takes it, and on a whole new way of solving the problems that these legends have solved for decades. So you are all the first movers in this, in my opinion.

We're the first step of what is a revolution. We push boundaries, we solve real problems, and 25 years in the industry, not everybody does that.

Combining abstract mathematics with real-world critical systems has been a big passion of mine. And unlike chatbots and things like that, when you're deploying AI in the real world, the foundations are oftentimes necessary. In the real world, as opposed to playing Go, trial and error over a system could be something that's super costly or dangerous or both. So what you can do is take a model-based approach, which means that you do the trial and error, instead of over the system, you do it over a model of the system.

So it works like this. You start by taking historical data. You learn a model of the system. Then you take that model.

You train a controller. It gains experience through reinforcement learning. All of this happens offline in the cloud. And then you take that controller and apply it to the real system.

This is kind of teeing up what we're seeing. I've heard lots of discussion about, are we falling behind? And the answer is, well, if you're not one of the pacesetters, yes, you are. The closer you get to control, the more rigorous and more math and engineering-based you need to be.

I'd put Imubit firmly in this category that we're calling the autonomous execution agents, where they are using typically anything from neural nets, physics-informed neural networks, and various techniques. And they are more about human on the loop, or closing the loop, because they've got that rigor. So, kind of to clarify, our models are, the DLPC models are not large language models. They're actually deterministic once you train them as a deep learning network.

What it essentially means is that you're getting the same output for the same input, no matter which user and what time you ran this thing. And that's not how LLMs work. But certainly, my mental model states that if the problem is highly nonlinear, the gains are changing all the time, or if it's a truly multi-unit kind of optimization, then I think I would use an AI solution versus considering a legacy approach. We're not the orchestration layer.

And I think that's the point Gil was trying to make earlier, is that we were thinking, even very recently, we should build some agentic capabilities within our platform. And then what we did was we actually tested it ourselves, and we saw what Claude could do with our platform when it connected to it. And we're like, oh, we shouldn't do that. We should go this other route, where we actually enable LLMs, agentic capabilities, to meet you all where your journey is.

We're doing that because of the reason I mentioned, that we don't think we or anybody else or any other application platform is going to build one agent in a box and be the center of the universe. We want you guys to build your own enterprise architecture, with your own LLMs, your own workflows, and interface with us as an application platform. Because really, the LLMs are like a new web browser. That's really what it comes down to.

The biggest learning for me is the roadmap and the MCP that's coming up within the next few months. That's an exciting development, because now we can really start to unearth the power of data and models developed using other platforms and integrate that with the tools that Imubit has to offer. Everything that can be automated, that's instrumented and actuated in closed loop, is going to be, in the next few years, we believe, automated in closed loop. This example that I always use: you want the operator to be able to make the right decision as if they have all the cross-functional team behind them, but on a 2 a.

m. Sunday morning, where there's nobody behind them, nobody around them.