#161 Organizational Memory Is the Next Moat: Ashwin Gopinath on Building a Company Brain

Welcome back to the Pre-Vetted Podcast, where we spotlight extraordinary people and remarkable talent reshaping our world. Today, I am joined by Ashwin Gopinath. He's co-founder and CEO of Centra, where he's building organizational memory for what he calls enterprise general intelligence. Before Centra, Ashwin was an assistant professor at MIT, a research scientist at Caltech and Google X, and co-founded PalaMetrics, a proteomic company acquired by SomaLogic for $52.5 million in under 2 years. His career has lived at the intersection of biology, physics, and computation. Ashwin, welcome to the show.

Pleasure to be here.

So for people meeting you for the first time, can you tell us a little bit more about What you're doing today?

Yeah, sure. So the thing that I'm working on right now is asking the question at a high level, you can think of it as how do you make sure that if you have a group of people, how do you make sure that they're all working towards the same goal? How do you make sure that there is least friction between them and to, in some sense, get them to behave as a collective intelligence or like as an entity that is larger than themselves? Like how do you get them to kind of have least friction between them so that if somebody learns something, everybody sort of learns from that experience? How do you get a group of people to think and work towards one single north star with least friction between them? That's what Centra is essentially intended to solve. That's what we end up calling as enterprise general intelligence. You know, more popularly nowadays, people are talking about it more as like company brain. How do you actually make sure that everybody sort of has a single sort of understanding and working towards the same goal.

Right, right. Very interesting. Yes. You, you, you talk about Centra being an enterprise general intelligence, right? And you're kind of describing what, what it's about and what do you think is unique about this, this software?

Yeah, I, I, I wouldn't necessarily think of it as a software. I would think about it more as a tool. tool that plugs into pretty much every piece of information generation tool, that is meetings, messages, emails, whatever other tools that one might be using within a team or an organization, and extracts what is important for each individual, have access control so that people who are not privy to certain information don't get it.

Right.

like surface it as they are working. So I think people are working with agents a whole lot more. People are working with other AI tools all the time nowadays. And I think that is going to just keep continuing. Even otherwise, if people are on a typical day when they are working, they are trying to understand information from different tools and different pieces. We want to reduce the friction so that the information that is necessary for them at that time automatically sort of shows up for them. And there is, and they can continue doing their work without ever having to fall out of, like, go and look for context. So the information that is necessary for them is always available for them.

Right, right. I understand the, I mean, the closest, and probably forgive me if this is not the right comparison, but the closest thing that this reminds me is Confluence, having a wiki, organizational wiki. Wiki for a company. Of course, this is pre-agents, right?

Yeah. I mean, so wiki and all of this information. So people always had systems of record. It is not as if systems of record did not exist. Systems of records always existed. That is, there is a single source of truth where people need to go and look, but somebody needs to maintain it. Like all companies have got documents that gets generated that never gets read. Nobody maintains it. And when you read a document, you are looking for only pieces of that document. You don't read the entire document. There's something relevant for you that you need to go and look at. So now there's a lot of friction. People have like, I think people have done these analysis where like 95 to 97% of all documents that are generated, nobody reads. Okay. So, so, so how do you actually make sure that the right thing gets, gets to you and somebody maintains it and it is actually accurate? All of these things need like that. Like, So Confluence and wikis always exist, but somebody needs to maintain it. Like, what we wanna do is have the system sort of ephemerally exist in all pieces of data that you are working with, all tools that you're working with, and constantly extract the information. So the system knows who is working on what, what ideas have been generated, what ideas didn't get used, how things are transcribing or like transpiring in the organization, you know, and, and, you know, what didn't work, what what worked and who worked on it, what decisions were made, you know, and, and it just exists there. So as you're going about doing your work, it just pops up and it just corrects you or like gives you the information that you need.

Right. And I think that one of the issues we had with Confluence is that it's always outdated, even for a day, an hour, you know, by design, it's always outdated because we, we humans make decisions that we are not so good at going back to the document and putting it back again, right?

Correct.

So we have to kind of remind ourselves, or I have to remind the team, my team to go back and remember to update, right? And that, that was a lot of friction, right? And then we, when we moved to tickets, we used Confluence and the tickets, right? Uh, for tasks to track tasks. We had a lot of documentation there that sometimes was not going back to the Confluence as well, right? So that has been another friction. What we ended up doing at one point is we start doing for onboarding video recordings of, you know, if you are the new person, I'm going to show you how we do things. And that became the new knowledge base, if you like, right?

Mm-hmm.

But I mean, it's imperfect in many ways, but for somebody new, then we can send them to a list of videos to watch, right? It was not very efficient, but it it kept the record of knowledge updated, right? So what I see you're doing with Sentry, you're fixing that problem because you now have agents that can collect that information and summarize it. So you're always keeping that relevant information safely stored, right?

Correct. I would, the only place where I want to correct is it's not summarization, right? So memory is not summarization. I think this is the problem that I think most people have in a— they confuse memory for knowledge. Okay? Memory is not knowledge. And memory is not being able to retrieve anything perfectly. Memory is different. And a good way to understand what memory is and how it's different from knowledge is, let's say you have 3 people looking at the Golden Gate Bridge. Okay? Let's say you have a designer, an engineer, and a biologist, just for example. They're all standing at the same place, same time, looking at the Golden Gate Bridge. Knowledge would be if somebody takes a picture of that, right? Memory is what each of those people took away from that experience. The designer might remember the color of the bridge. The engineer might remember the sort of the cables, the 90,000 miles of cables that were there. And the biologist might completely forget the bridge and might remember like some dolphin or the whale. Now, why is that? That is because, that's because It mattered to them. Memory is part of the knowledge that matters to a system or a person. So, like, from an organizational memory point of view, you don't need to remember everything that was said in a meeting. You need to remember what was important in a meeting. Who attended the meeting? Was the meeting about a particular project? Okay. What changed about the project? What decisions? Why did you change it? Who said what? Those are the things that are important. Everything else is like, you can forget about it. It's like, you know, so, so, so that's the core difference, right? If you're summarizing, you're summarizing also noise, like all those other non-important things. So memory is not just knowledge. Like, memory is not just storing everything in a, in a, in a, in a file system and just forgetting about it. The way to think about it is Memory is what happens when you, it's like a scholar reading a library and understanding things that are important. It's not just the library.

Right, right. I see. It's a, it's a nuanced but powerful distinction, right?

Correct. Correct. See, because, because each person in an organization cares about different things, the salesperson might look at the same piece of data and remember something different than the CEO or a product manager. And it matters. Like otherwise what happens is you, you need to go searching for things. A true memory will bring the information to you and will learn in some sense. The true memory is somewhere, it's not a database, it's not a model, it's somewhere in between. Right. Right.

So this also puts a clear distinction between having, and again, I apologize for the rude comparison, but having a bunch of Markdown files in a folder, right? Because what you have there is just a storage of text and information, right? Which could be more or less relevant, but the difference with Centra is that you're saving the information that is relevant for that particular context. And then you can query it and make, make it much more faster to, for agents to get back to the, to the relevant information they need to make the decisions, right?

It's kind of correct, but I think the way to think about it is it takes the data and then it structures in a way wherein later on, if an agent or an individual queries it, Depending upon what the agent wants, it will extract and create the context that is relevant for them. So a good way to think about it is this, right? Like, and again, example, right? So if you look at a sales complaint, a customer complaint, right? An email, you can just store it there. But then the question is, the system, basically, if a sales associate asks about that customer, it will just tell them what is relevant for the sales associate. It basically says, This is the customer who has an ACV, how much they're spending with you, and why, what, what was wrong with the deal that, that caused them to, that, that, that complaint to occur. But if the same piece of customer complaint was being like how it affects a program manager is the, or the product manager is, the product manager will understand the feature that did not satisfy the customer. They're 2 different things. They're in the same piece of data, but it's relevant. Different parts are relevant for different people because that's what they care about.

I see what you're saying. Yeah. So you see the information from different lenses depending on what's relevant for each. I, I would call it agents, but also humans, right?

Yes. Yes. So, so the way in which we think about it is The memory, basically, depending upon the ontological lens that you project onto it, the memory changes for you. This is, again, another way to think about it is like, I love giving this example. It's like if you are going on a hike, right? A boulder is just a boulder. You might not even remember it. But if you were tired, that boulder becomes a chair. You sit on it. So you will remember it as like a place where you sat. Not a place, you're just not a random piece of boulder. So it, it changes. The same piece of information can change depending upon your perspective.

Right, right. I see, I see what you're saying. It's very interesting.

I, I— And right now there are no tools that does that.

Right, right. Because all of the tools focus on storage and retrieval. Without the analysis.

It's storage and retrieval, but typically they are for a process, for some purpose. Okay? So when you, when you're doing it for a purpose, you're basically selecting what are the aspects of the knowledge that is important for that purpose. But it is not for all possible or like a large number of reasons why a company might need it. Right? So, so, so that, that's the nuanced difference. Okay.

Right, right. And the other question that comes to my mind is, how do you manage access control? I mean, if, because in coming from a more traditional approach, I would have teams having access to different types of information, right? You have different scopes, right? So marketing people would not know exactly the the database, production database, they don't need to, but eventually they do need to have shared information, right? Because if you isolate it, then you can make the wrong decisions, right?

Correct, correct, correct. So the way in which we do the access control is very similar to how— so the core data, like the source of the memory, has access control. So let's say it's from an email or from a meeting, you know, the people who were in the meeting and Whoever owned that meeting can decide what is the scope of that memory. The only difference is, I think it's more a cultural and psychological change wherein right now, when you are having a conversation with somebody or when you're in a meeting, you don't think about it as everybody has access to information that is there here. Okay? So I think the company changes when you start saying, You know, like any conversation on any piece of data that is being generated, a lot of people's, you know, it'll impact them. Okay. And then you can basically change the way in which should it be private, should it be public. And that nuance can be also set up in a way wherein the data itself, in the meeting itself, if you were to say, okay, this is private, okay, then Sentra sort of like flags it and changes it. So think about it this way, right? Like the best way to think about it is Centra is, think of it as Centra is basically sitting in on all pieces of information and think of it as a person that, like that, an individual with infinite bandwidth who can be in all pieces of information, all pieces of data, all meetings, all messages, everything, and understand it.

Right, right. That's why we're thinking about security, because if he has access to everything, it could possibly leak some information, right?

Yeah. So to the extent possible, we are taking all the access controls that are there in file systems and transferring that onto this system. So part of the reason why we have been spending a lot of time developing it is to kind of go through all of these issues.

Right.

And in the several design partnerships and like rollouts that we have been doing, and we have about half, about a dozen of them right now, a dozen teams that are basically using this. The problem never is access control. Like, access control is least of the problem. I think the— it's not even issue, right? It's just things that used to take weeks or days gets collapsed into minutes. So like, if a KPI changes, Okay. In like, not only do you know that the KPI changed, but you can also now say what decisions that somebody specifically made is most likely the reason for this KPI to change. Typically, things that would've taken like days of, to kind of track down gets collapsed into like tens of minutes. As soon as the KPI changes, if you have flagged it, the system basically goes through all the things that happened. and says, this person like Bob or Jack said something, or like there was like some supply chain delay that caused this KPI to change. So the learnings become so much faster.

Because you're not, I, I think you, you, you are exposing a very powerful concept that is all of the systems, I mean, I go back to Confluence because it's what I'm more used to. All of these systems track the decision already made, right? What you're tracking is how decisions are being made.

Yes.

Right? And then from there, you can have traceability towards all the decisions that are being made.

Correct. Correct. You, so you—

And that's much more powerful.

Oh, go ahead. I mean, so one place is like KPI changes. I mean, that has been highly impactful for like one or two clients that we have. Another client that we have wants to use this for, or like are using this for performance review, which in most organizations takes a lot of time every quarter. Okay. Here you can just basically, like the system has seen everybody. Doing everything. They— it is tra— it knows who committed what into GitHub, you, who told, who talked what, discussed what in what meeting, what was discussed in Slack, all of that. So it can just immediately say this change occurred, which was positive for the company. Who exactly did it? Like, why did it exactly happen? Wow.

That it's so powerful.

Exactly. I mean, the reason why we are, we are doing this is because like fundamentally all companies are like, all companies are just a collection of people working with each other. It's, we are in a people business. Okay? So we wanted to actively work on problems that accelerated fundamentally human problems and solve fundamentally human issues. Not really. I mean, yes, it can be used for, you know, speeding up things. It can be used for, you know, reducing token counts. There are a whole bunch of things that one can do, but fundamentally we wanna basically augment and improve teams that are composed of humans. So we wanna solve human problems, fundamentally human problems with AI.

Right, right. That's very interesting. And, uh, I can see how it's, it's basically a Git blame for business decisions.

Yeah, that's, I mean, we call it like Git log of the company in some sense.

Right, right. Yes. Yes. That's very—

But how you use it, how you use it is completely different.

Right, right. And are you tracking decisions being made by humans and agents? I mean, differently.

Yeah. So we have been trying to, yeah. So we treat, so we think about it this way, right? Like we think about everything that happens in a company to have like classes of objects, right? You have actors. Okay. So that will keep, that would be people, teams, companies, including agents. You have interactions. Those are class of things, entities. So interactions would be meetings, messages, like agent. Human conversations. Okay. Then some decisions get made in all of those interactions. Something gets decided. Okay. You will decide to do something, and there is a rationale behind that decision. So the rationale and decisions and other things. Then you have commitments wherein, like, discussions can be there, and then there is commitments to do something. Okay. And then there are value-creating objects. So these are services, products, something. Okay. So these are the classes that are important for the company. So agents are a class of Actors, humans and agents, or agents and agents will interact with each other. Some decisions get made, and that decisions could be just, you know, completely, you know, non-impactful to a value-creating object. Okay? It might never affect anything.

Okay?

You might be just 2 people decide that, you know, they might, you know, share the workload or something. But if it doesn't affect a product or a service, something that gives them money.

Right.

like value-creating objects, then from the company's perspective, it's not that important. So every one of these— so these are the things that we are tracking, like in all the messages, all the emails, all the agent-human traces, agent-agent interactions. We are tracking these things and creating a continuing record of it. So you can always trace back and say, Bob or Bob's Claude session, what were the decisions that were made? What were the discussions? And you can trace back and there's like, you can constant, you, at any given point, you can connect to any one of these classes. Okay. And you can basically make, like, go back, like, what are the effects? So you say this decision, what happened from that decision onwards?

Right, right. That's very interesting. And the, the reason I was thinking about making the distinctions, it was because of value for the business, right? I mean, how, How much value should we put to an agent making a decision versus a human making a decision?

Right? Right. I mean, ultimately you could, if you have the system, one of the things that we want to do over time is, if this is like 6 months or a year from now, as these kind of dozen companies or dozen teams that we are part of, that'll grow, we can go back and ask the questions. You know, did the agents actually affect the bottom line? Or was it like humans that made the decision and agents just acted on it? Okay. You like, so, so in some sense you can think of this as like beginning or like tools like this and capabilities like this. And we are not the only ones who are doing it. Others are also developing it. So I don't wanna say that we are the only ones who are working on it.

Right.

Other ones are like play that we have a certain approach to it that nobody else is taking to our knowledge. But, but others are also in and around this theme. But either way, this is like beginning of things like outcome AI. Like one way to think about it is like you can go back and you can play the tape backwards and say, all these good things that resulted, why? Who was responsible for this? Was it an agent? Was it Claude? Was it ChatGPT? Or was it like somebody in the company that basically made these decisions? You can go back and say ROI of everyone and every decisions within an organization. If it is sitting in the—

Yeah.

If you have that entire data and structured in this way, you can actually start asking those questions.

Right, right. I, in my book, The Invisible Distance, which I'm finishing, almost finishing on the editorial part, I tell a story about a software engineer that built a feature, but was laid off before the feature was launched, right? And the accolades of that feature that had an impact on the business, the accolades was to the team, to the current team. So kind of my, the moral of the story is that the system is designed to reward who remains on the team, right? And, you know, even though this person was, you know, the main contributor to that, she was not able to get the recognition. And By that time, if I send the recognition, you know, personally to her, it was just opening a wound rather than just, you know, acknowledging her contributions to the team, right? Or to the company, right? So, when you, you know, when you were talking about this idea of recording the decisions, remind me of this story, right? Where we're, you know, the current systems are not really good at The recognition, you know, there's too much politics around that. It's a very inaccurate system, if you like, right?

Completely. I completely agree. I mean, it is one of the— this was one of the reasons why one of the folks that we are working with very closely wanted to use this for performance tracking, because they were like, or, or, because typically what happens is the loudest voice gets the credit. You know, there are a lot of people who contribute, but that contribution is completely lost. Because they are not actively pushing it forward. I mean, they might be introverted. They are not writing all of those things in the performance review. So that happens all the time. And what we want is to do that truly at an organizational setting. Like, the good choices that you make, whatever it might be, we want to kind of lean into it. So you can think of it as Right. As the data sort of like collects itself, we can start really thinking about building a model of the organization because that entire trace can be used to build a model of the organization. And then you can start asking even more interesting questions like, do reinforcement learning on the right decisions that you made. Like if you hired the right people, okay, they might not be the, like, like they're not necessarily the loud person, not the most political person, but What are the teams that actually led to the right decision? It might be some quiet person somewhere in the meeting, might not even speak, might be just like sending messages on Slack. Maybe they are the ones that are actually important. You see that all the time in organizations, in teams. You have like this one amazing person who's very, not necessarily very loud. And finally, one of the other things that you can start asking is, is AI actually useful? Like we ask, we go around and have this debate on, you know, what is the impact of AI in organizations? Okay. Things like what we are doing sort of starts answering questions of that nature. You know, after 6 months, after a year, you can ask, you know, was this, you know, was all this money spent on cloud or ChatGPT or whatever other tool, okay, was it actually useful? Did it actually produce something that changed the top line or improved the bottom line? Right.

Right, right. I, I am exploring on building this zero employees company to, to see how, you know, to learn and see how it works and what I'm learning. Uh, and we're on the early stages, so, you know, but what we're learning from the community is that there's all this incredible, you know, uh, zero employees companies or agentic companies that are generating zero revenue. Because they have a great system but haven't actually got into revenue yet, or they haven't figured out how to do that yet. So I see the value of what you're talking about. The other thesis that I describe in my book is this idea that we can have AI arbitrage, we can have labor arbitrage, but the largest leverage that we can have is large context. If we have Humans that have been in the company for many years, they know all the decisions of the business in a much more finer detail than somebody that just joins the company, right? So having a long-tenure team has a much bigger impact in the outcome than any agent could have, right? Now, having said that, if you provide to these people agents that can help on the load, then these people can manage the agents in a much more effective way, right? Which supports your thesis that having those, having the recorded decision provides, and knowing what works and what doesn't work provides much more value for the business, right?

Correct. Correct. I mean, and if I were to be like so bold to basically say, right, it's just sort of, we are, so while I respect and I admire the desire to have like zero employee organizations and all of that, like Like Centra and me personally, I think we are still far away from that. I think the world is too messy and people's desires and because you are ultimately, the value creation is gated by some human somewhere. Like somebody needs to buy or somebody needs to do certain things. The value creation has to be some individual or group of individuals need to basically make a decision as to if something is important or not. It's not an AI that is, there's no There's no objective value creation. Objective is some— somebody says, I will pay this much dollars or this much money for something. Okay? So value creation is fundamentally with humans. I mean, in some sense, and in— because of that, I do believe that humans are the ones, at least for the foreseeable future, going to make decisions. Agents might basically go and execute it, but fundamentally it's gonna be teams of individuals that are going to basically make these decisions and continue to work. So I wanna basically make individuals' ability to work with each other, maximize that rather than replacing them. Because I don't think that replacement is going to happen anytime soon. Just being honest, very, like, I'm being brutally honest with that, right? Because we have tried this and it does it. It's like, gets you about like 90, 95% of the way there. The last 5% is where all the problems begin. So, so, so yeah, I'm fundamentally, somebody needs to make those decisions. And it's for that group of people that Centra is basically being built.

I completely agree. And I'm reaching to the same conclusions with these zero employees companies where it gets to a point where it's running loops on lack of decisions or we get to a point where it says, we need, you know, because I'm acting, we're acting as board members, right? So we're not supposed to be involved in the operation, but then you see how it gets locked and it ask for a decision to the board members, right? So it's kind of, what's the point of building all this automation if it comes back to you for all these little questions, right? Or little decisions, right? What's the point, right? But that's why I call it an experiment. And I arrived to the same conclusion that at the end of the day, the human decision becomes much more important. And actually I can, and that's why my thesis with the longer context is that those decisions, it's what makes the difference between having a human managing agents that has all that context versus a human that doesn't have that context because it's a new hire, doesn't know how to manage those agents. And yes, we can have higher speed, but if you have higher speed and you go in the wrong direction, then you're not moving forward faster, right?

Yeah, completely agree.

Right. And then the other thing that I've been thinking about, this idea of agents and humans is about accountability, right? Which, who has the accountability of the actions of the agents, right? I mean, In my view, it should be the human that supervises, right? Because the agents don't have accountability by themselves, right?

Correct. Correct. Correct. Correct. Correct. So I completely agree, right? Like, I think, I think people are so, so like ultimately when something goes wrong, I don't think the AI companies or the agent companies are going to take responsibility. They're not going to basically, and they're not going to, I mean, in their terms of service, they're going to be like, ultimately whoever bought it is responsible for it. Okay. So, but within an organization, okay, within an organization, then sort of you, you start asking the question, who's liable? Like, who are you going to fire when something goes wrong? Okay.

Right.

Because that, that, I mean, from a management, management perspective, that is what happens. Like ultimately when something goes wrong, like we saw this in that, in Amazon, and we saw it in a few other places wherein you have AI systems that have been rolled out and it causes mistakes. And like AWS goes down or like the system goes down or the system gives a deal to somebody that they can't honor. Okay. Who is responsible? You can't say that an AI tool is responsible. Yes. Then are you going to fire the engineer who built it? Is that the VP who authorized it? Is it the company? And like, who pays? Like if there is monetary loss, Who's responsible for it? Or do you just have like proliferation of AI insurances, sort of like Corgi and others who are basically going to insure these things? And something to keep thinking about here is this, right? And this is the problem that I keep thinking about, right? Like right now we have certain number of decisions that are being made with AI, and there is a certain probability of errors. Let's say just for numbers' sake, you're making 100 decisions and there is 5% probability of error, which means that statistically 5 mistakes are being made. Now, conventionally, people will say that as AI improves, the error goes down. But what you forget is that as the error goes down, the usage goes up.

Okay?

So let's say now, like, the error goes down to 1%, but now you are using— you are making 10,000 decisions with that. So now what happens is you are making, like, percentage-wise, you have improved. But absolute number-wise, you are making a lot more mistakes.

Right.

So, so now the question is, where are, and, and these are complex systems wherein errors sort of propagate, like, like, and, and we see that in, in, in like in, in dynamic systems all the time where like some small variable changes and it has, it sort of like has an outsized impact. So I think that when people worry about like job loss and all of that, I don't think they need to worry so much because ultimately the AI is not going to be responsible. You can't blame an AI and basically say somebody needs to, like, AI is fired, or like Anthropic is now going to pay for this. It's not gonna happen. Okay.

Right.

So ultimately some human needs to sit there and say, I checked the AI's decision and I am going to be the person responsible when This particular decision goes wrong.

Right, right. And the more I learn about, you know, running, you know, implementing automations within organizations, the more I learned that software engineers are going to be a much more relevant role because now you need somebody that can manage all that, right? On the technical side, on the business side, right? And as a software engineer building software, it gives you much more freedom on What you can build, right? Not freedom, but productivity, right? I mean, I used to work on the syntaxes and make sure that it was correct and all that stuff. And now I can think on higher levels. I want to migrate from this technology to this other technology. So let's go and let's plan that. Let's put stages on it. So I can make these higher decisions that it's more of an engineering manager managing a team of agents. That are actually building the software, right? Correct.

Correct. I mean, the, the, the completely agree, but, but I really like to sort of, I wish more people thought about the accountability issue, like who takes accountability for when things go wrong. I mean, you typically think about it only in regulated spaces like meh, like, like medicine or, you know, law and stuff like that. But the reality is this is true in pretty much every area. It's just a question of the liability of when things go wrong, you just don't think about it that way. You don't think about it as, you know, if I do something wrong, like I'm responsible for certain things in a company and the CEO is responsible for it, like, and junior developers are responsible for certain small parts of it. And when they go wrong, you can fire them. But you can't necessarily do that. Like, how do you do that for an AI? Because it's not as if they don't make mistakes. They do make mistakes. They're not, they're not, they're not perfect, and they'll never be perfect. No system is going to be perfect. Okay? So when they go wrong, how, how do you deal with that? And, and the scale of the problem is only going to keep increasing.

Right, right. The, the automation that allow us to do more also allow us to make more mistakes. And we need to have better tools to have traceability of those mistakes, right? And I think that's where your tool actually fits, right?

Yeah. I mean, I, our tool, our tool fits there, not necessarily for pointing out mistakes. That's not necessarily the intention, but it's in general, it's, it's, it's to basically say that humans are going to be part of the system. And humans are, I mean, and, and there are gonna be more and more humans who are going to be needed to do more and more intellectual job of who's deciding, why are they deciding, or like to have the context to basically back up their decisions. And so fundamentally, we wanna solve quintessentially human problems, which is teams of people working together. And this is something that we've been doing for like, since we were apes in some sense. Okay. Like groups of people working together and you can make that better. So like, so that—

I love your analogy. Yeah. Yeah, because at the end of the day, we're still, you know, we're still, uh, you know, imperfect animals in a way, right?

Yeah.

Yeah. Even though we try to, you know, become more, uh, you know, uh, hierarchy higher, but in, at the end of the day, we're still animals with our biases, our instincts, and our, you know, flaws, right?

Sure, sure. Yeah, exactly. Exactly. I mean, so, so, so, so it's sort of like So it's sort of like, let, I mean, and, and, and, and, and I've, at this point I have seen like enough teams, like whether it is in academia, whether it is in outside academia, in like research setting, in company settings, all of that. Ultimately, one of the things that I have walked away from is that you can have, like, I think the team A group of people, a great team can always make up for weak technologies, weak market, all the other problems. If you have a great team, okay, it's a joy to work with them and they can actually like do wonders. But then you can have like individuals who are fantastic on papers, but like really shitty teams. Okay. And they'll basically have all the money in the world, all the things in the world, and they still mess So the question is, how do you actually get people to work together and coordinate and be the best version, not of themselves, but as a team? And that is a problem I think that we can solve. And we see things of this nature, right? In some sense, I think about it as social media is a great example of AI sort of getting people to work together.

Yeah.

Like you have this concept of groupthink and things like that. In some sense, Twitter and Facebook and all of that are sort of bringing these people together and getting them to think in the same way to a certain end. I mean, they're, it's not, it's not, it's not, they're not doing it. They're not doing it purposefully. Okay. However, the algorithms sort of like get grouped them together and like, it's like self-organization that has happened. So now the question for us is. How do we do that internally? How do we make sure that, like, if you are part of a team, how do you make sure that all of them are like working towards the single goal of creating the most beautiful product that the company's building or the best service and like have least friction and like moving towards them, like moving as a single entity, you see? So, so this is not fundamentally impossible. We see this all the time.

Right. And, and coming back to what we're talking about is It's all those little decisions and little or small or big decisions that lead towards making a great product that is successful, right?

Precisely.

Right, right. And I understand your point that Sensio is not designed to find the culprit, who made that mistake particularly, but it's the knowledge of All the decisions that can make difference between achieving the outcome, expected outcome, or wouldn't, right? So being able to find that so you can fine-tune it, right?

Correct.

Correct.

The best way to think about it is even the blame assignment is kind of different, right? Like for instance, if you have a driver and you have like a car with like lane discipline or like lane, you know, when you veer off the lane, it buzzes or whatever, lane assist, right? So the point is, do you see lane assist as blaming you? Like you are not waiting for somebody to fall asleep and crash the car, then you can say it was the driver's fault. But if you had lane assist, as soon as you started drifting, it corrects you. So you don't need to make the mistake before, you know, you correct yourself. So Centra in its perfect form within an organization is if somebody makes a less than ideal choice.

Right.

They get informed and the system corrects you to move. So at that point, you have not even made a mistake. It's just like an autocorrect. It just basically pops in and basically like, oh, like do this thing. I mean, your understanding about the problem is not right. Or like you and somebody else are going orthogonal to each other, probably talk to each other and correct. So all like, it changes the way in which a work, like an organization sort of—

Right, right. I think I told you already this example, right? It's like this movie Brilliant Mind from, you know, with John Travolta, right? Where he becomes smarter out of suddenly and he's able to build, design the crops for his friend's farm, you know, because he's able to see all the connections and everything, right? And what you're describing is the same thing, you know, it's, you have an assistant that tells you, well, if you go that If you go that route, you're going to crash. If you go that route, it's less efficient. So let's go back to where you want to go. You humans are still driving, but you have the assistant that gives you the foresight, right? That's amazing. And then the other thing that we haven't mentioned, and I think it's important to mention, is token efficiency, right? Because now, This is for the humans, but for the agents, you're also providing that reinforcing feedback where you can guide the agent to find the most efficient path, right?

Correct. Correct. Correct. I mean, so the best way to think about it is this, right? Like sometimes you give a lot of information, a lot of context in there. And if you know where the information is located, if you know like what is important for your particular task, then the amount of context that you need to give for the agent comes down dramatically, which means that And it doesn't need to go and search all these different places and construct the context before answering the question. So you're effectively, every single task that you're giving, the amount of tokens needed goes down. Like in our cases, like depending upon the complexity of tasks, like sometimes we see like 12x reduction in token needed for the same task. So if you're going to give the entire context or ask Claude or like ChatGPT or Codex or whatever agentic system that you're using, if you're going to ask it to go construct the context and answer a question, and if you were to kind of use us or like Centra as the memory, then the token usage difference can be as large as like 12x difference, or depending upon like for coding tasks, we are seeing between 20% and 60% reduction in tokens, while the accuracy is the same and sometimes higher on the same benchmarks that like, you know, GPT-5.5 or, you know, Opus 4.8 uses for, you know, showing their coding skills. Like, like we have a, we have like, these are things like TerminalBench and DeepSWE benchmarks. We are able to show that token, like apples to apples without, with and without Centra, everything else being the same.

Right.

We can see easily between 20 to 60% reduction in tokens while the accuracy remains the same or slightly higher. Because, because think about it, right? You're just removing the noise. So it knows exactly what needs to be used. So you can basically go like, things get, things get like improved.

Right, right. Because without memory, the agents don't know. Don't know anything about the business. It needs to look at everything. Yeah.

Yeah. And it's not just business, right? You can point it. So, so we originally started out with the idea of using this for reducing complexity within the organization, within the, within like different systems. So we built a single memory layer that basically understands the, like, it's agnostic. It doesn't have, it doesn't care really about what the data is. So we started pointing it towards coding agents simply because In like repos, like code repos. The reason we did that was our token cost was going through the roof. So about 2 months back, we were like, let's point this to our repo. Let's see if it actually improves. And we started seeing it improves our systems. So we decided to kind of optimize it. And now it's got to a point and we are nowhere near, you know, the best it can be. It can be far better than what it is right now. We are already at like between 20% and 60%, depending upon the complexity. Some of these codebases are very small, so you don't, you don't have that effect. But some of the other ones that are very large, the larger it is, the more complex it is, the more important memory becomes.

Right, right. And what you're describing basically is you allow the agents to find the gradient, what is the most efficient direction they should follow for highest return of, of For maximum return, basically.

I mean, from an analogy point of view, that is totally fine. It's not like technically it is not exactly right. I mean, I don't wanna, I don't wanna say that it is doing some kind of a gradient descent and like learning or something like that. It's not doing that. But from an analogy point of view, yes, that's what you're saying is kind of true.

Right. Yeah. What, what you're doing is providing the, the context and the decision so the agents can make the, the final decision. Right?

Correct. Like one way to kind of think about it is this, right? Like when you have these coding agents, when you're touching one part of the code base, typically they don't, it doesn't automatically know what is a blast radius. What that means is if you make a change at a single point in a particular file, how will it affect all the other things in the, in the, in the repo? That information is typically not there. So what happens with the coding agent is it'll go make a change, then it'll try to run it or compile it or do something with it, and then it'll get a bunch of errors. Okay. Then it'll look at the errors and go and correct it. And then that'll have like another set of effect. So you need to kind of go back and forth. Now, if it already knew what each piece is, what it's supposed to do, what each part of the code is supposed to do, how it affects everything else, then it knows that when I'm touching one place, I need to also change things in all of these other places.

Right. Right. I mean, what I'm doing to work around that is I make changes and then I run audit processes where basically I go through the whole thing. Yeah.

That is token usage. Like if you had infinite tokens, if you had infinite tokens, then that's a different matter altogether, but we are not in that world. So, or you can think about it as an efficiency point of view, right? Like, so structure improves the efficiency.

Right, right. I mean, the reason we're doing that is because when we're building something, we want to make sure that everything works correctly. So we have to go back and go back because it doesn't have all the context to make all the necessary changes to fix everything.

Yeah, exactly. Exactly. But if you have that, everything becomes a lot easier. I mean, and I'm not saying that this will solve all problems, but, and like, and And there's a lot of knobs that we can turn to kind of improve this. We are nowhere near as efficient as we could be.

Right. But as I understand, you have the research done so you can, you know, which direction you need to go to improve the system.

Yeah. Like we have, we have some, we have, we have, we have like, we have a, we have a clear understanding as to what directions we, let's put it this way. I know what directions are wrong. Okay. That is provably wrong.

Okay.

I don't know whether the directions that we are taking is the most optimum one. So we are just not doing a bad— we are not just not— we just, let's, let's, for the time being, let's not make the mistakes that are like obvious. Okay. And, you know, hopefully we'll basically continue to move down that path of like, you know, just don't do the— don't make bad decisions. That's all.

Right, right. Amazing. And what is the future ahead for Centra? What are, where are you planning to To the next, which milestones are you trying to achieve?

So, so, so, so right now we are, we are trying to do this right rather than going fast. We have a bunch of like great investors and like design partners right now that we are working with and trying to kind of answer core enterprise questions as we are sort of scaling up. The reason is that, you know, there are so many enterprise like pilots that are going on and, you know, they all fail because of the fact that, you know, They're not able to show return on investments. They're not able to show the value creation or like do it right with all the bureaucratic details of an enterprise. You can forget about it. Like there's an idea that startups will not think about all of these things. That's all fine. But ultimately, push comes to shove, you need to sell into the enterprise. I mean, that's where the real money is. And these are the large organizations and they have bureaucracies. They exist for a reason and we have to play the game. And we have to kind of change it. If it has to change, it has to change slowly by being in a conversation with them. We can't basically say we are going to do it this way and you need to kind of agree to us. So we are just working with them closely to kind of answer these questions as we are slowly adding on like more design partners and like folks who want to kind of work with us. But, you know, and things once, and we are open to sort of working with more folks as they come along.

Right. Right. Interesting. So are you close to production or are you still working on it?

No, no, no, no, no. Both of them are live. Like, like Core Centra is live. The Core Code Memory is also live in the sense that we're just basically like trying to work with individuals to kind of get them on board one at a time, rather than sort of like open it up for everyone. Because, you know, Memory is a very tricky, like people don't know exactly what memory is, or like there's no consensus on it. People think that knowledge and retrieval is memory. That's not memory. That's only part of it.

Right, right. Yes. And probably the, it's going to be a point where the analogy of memory is going to break down, right? Because we're going to go past what our concept of memory, our, you know, How we process memory is different on how, you know, the organizations and the agents and the humans should, right?

Correct. And ultimately, here's the thing, right? Like memory is some kind of learning. Memory is kind of a learning. Like you remember, it's not learning the way in which the weights are thought of as, you know, you can't say that because somewhere there is a utility function. You might not be able to define it. But some part of you or some part of the system determines that this piece of information is likely going to be useful in the future.

Right?

That is memory. And that's very different from just remembering everything.

Right, right. Very interesting. We're running out of time, Ashwin. I truly appreciate you being here today. Any final remarks before we wrap it up?

Yeah, I think so. We have seen the LLMs sort of converge, like LLMs, the core LLMs, their capabilities converging. We are seeing sort of like the agents sort of converging. Personally, and I think this might be a bit of a, like, I think this might be like us being like ridiculously optimistic, but I think that in the next 18 to 24 months, there will come a time wherein people are going to be more and more excited by memory the way in which I'm describing it. It's closer to continuous learning. People might call it continuous learning. People might call it something slightly different, but the essence is memory is not just remembering something. It's basically filtering it and learning or being able to choose what part of it is important for you in the future. And that system will become more and more important. And that dialogue is going to move towards that as the agentic capabilities sort of saturate, because that's what is going to make one agent better than another agent. And that's only going to get louder and louder over the next several years.

Right. And the, now that I'm hearing you about talking about memory, the other thing that comes to mind is this idea of experience. What is experience? It's all the mistakes we make throughout the years. Right? So when we have a new problem, right, or a situation, having all that experience allows us to avoid those mistakes and we know where to go, right? And that's what you're building.

Precisely. That's a great way to put it, right? Like, that's a great way to put it. It's basically like memory and experiences and all of these things are, they're not what you would think of as learning the same way, but as everything else, but they have aspects of it.

Right, right. And we don't think about it, you know, when we have all that experience, we don't think about every single decision, but at the end of the day, it weights into how we make the next decision.

Right. Precisely. So you don't even, you don't even, so, and this is the hard part, right? Like you can't tell me why you would remember what you remember. Okay. Like it's very hard.

Right.

It's very hard, but like some, somehow you end up like, there is a utility function that you have that causes you to remember it. Like, and now, now that's what is—

We, we call it intuition, but it's actually this undescribable way of, of how we think, right?

Correct. Correct. And, and, and, and, and this is the reason why I don't think memory can be solved for an individual, like, because I cannot, like, like this is why when you are doing Claude or when you're doing ChatGPT, like ChatGPT and Claude doesn't know why you asked the question that you asked. It knows what are the conversations, but you don't know what part of that conversation is important for you. And it doesn't know why you would remember those.

Right.

Unless it has a model of you in itself, it cannot. So, so from a personal point, which is why we are not going down the path of personal memory. But for organizations, I know what is important for the organization. They care about people and their products. That's all. And they wanna maximize their profits. So it's an easier problem.

Right. I think I dare to say that the reason you cannot build a memory system for an individual is because all the decisions happen within our minds. But when But when you have a team, the same decisions that happen within our minds, you know, a solo entrepreneur would talk with sales, would talk with marketing within its mind, right? Their mind, right? But now when you have a team, all those decisions are exposed in the communication between people, right?

Correct, correct, correct. Like the way in which we think about it is it's sort of, we call it internally as chain of thoughts, like conversations between people are chain of thoughts of the organization. And we know how important chain of thoughts are for, like, for these models to kind of reinforce and to kind of know when they make a mistake. You look at the chain of thoughts and you say, this is why it made a mistake. And when you're doing fine-tuning, you go and try to change that. Now, the exact same thing can apply to humans. Now it's just the conversations. That's the chain of thought of the organization. And once you capture all of that, you can learn a lot from that.

That's amazing. Ashwin, I truly appreciate you being here today. I mean, we can continue talking, right?

Yeah, yeah, yeah, yeah.

And I think what you're building at Centra is amazing, and I'm looking forward to where you take it next.

Well, it was a pleasure. It was a pleasure. Yeah. Thanks, Federico.

Thank you, Ashwin.

Yeah.