87. Escape the Ticket Trap: How AI Agents Are Replacing Manual DevOps

Hello, everyone, and welcome to another episode of the security podcast of Silicon Valley. I'm your host, John McLaughlin. I'm joined today with a very special guest, Venkat Thaluvigadam, the founder and CEO of Duplo Cloud. Thanks, Sean.

Yeah, welcome to the show, Venkat. It's great to have you. Looking at your LinkedIn, you've been building Duplo Cloud for a good chunk of time. That's right.

That's right. That's right. May we ask, what inspired your entrepreneurial journey? Yeah, I mean, I'm an accidental entrepreneur, so I didn't really set out to build a company.

I'm a developer by background, so I was working for a much larger company. It was not particularly fun. This was after my time at Microsoft, after we had moved to the Bay Area, and then I thought that I would build a software. And entrepreneurship is not very unnatural also, living where I live, like in the Silicon Valley.

My goal was to build a software, maybe sell it to about like four or five people, five companies, and then make as much as I would make in my job, and then sort of like go from there. But of course, I mean, things turned out to be better. More people wanted the software. And then, you know, the Valley's ecosystem comes and finds you and then pushes you towards entrepreneurship quite naturally.

And then that's where the journey sort of started. Like, so one thing led to another. I found advisors. I found mentors.

I found, you know, investors. And then the business also sort of like kept growing. We built a team. And then, yeah, here we are.

Looking at your website here, for all of our listeners who are just listening, it's AI for your DevOps. That's right. That's right. AI Power DevOps built for today's engineering teams.

Yeah. That sounds really great. Yeah. With outcome-focused workflows and security and compliance, it sounds like just a click away, real-time AI help desk, and comprehensive DevOps automation.

So you were just trying to solve some hard problems. You wanted to do it because you've bumped into that problem over and over again in your time with Microsoft. Yeah, that's right. I joined Microsoft straight out of college.

So I joined this research group as a software developer there. And then that research group went on to become Azure. So, again, another accident that I happened to start my career in what was going to be the future of software, like cloud, back then it was on-prem. So we started with about like 100-dot servers, center in Redmond.

And then before I knew, by 2013, it had already grown to like 5 million virtual machines or something like that. And across the pond, they were like AWS guys. And they were like eight times bigger than all of the rest of the cloud providers put together. So I think that's where I sort of like learned how with a handful of people, these big enterprises manage millions of workloads with latest and greatest security and compliance across the globe.

And I sort of got used to it. I was like, yeah, one engineer, 50, 000 workloads, like such a large infrastructure. This is a norm. This is how life is.

But then when I came to the Valley, that's when I realized that, you know, in mainstream MIT, it's like every 15, 20 engineers, you'll find another DevOps person, you know, who's operating an infrastructure. Security compliance takes like months, if not years. And yet I was like, oh, wow, you know what? I think there's an interesting problem to solve based on what we have learned before.

Why don't we actually do a software for it and try to make a difference? So that's sort of a journey. And you're a solo founder too. I did have help.

I mean, I had help in the very beginning, like I had a friend of mine who helped me bootstrap the company in the first few years, like for the first two, three years, I think gave me a lot of introductions, helped really get this off the ground. And of course, I mean, after that, he went his own way and so forth. But yeah, since maybe the last five, six years, I've largely been on my own. Wow, that's really incredible.

So you helped build Azure. Yeah. And all of that experience you brought down to the Bay Area here in Silicon Valley. And now we've just been hitting the ground running with Duplo Cloud.

Yeah. Yeah. I'm curious. Do you think of yourself as a security person?

I think of myself as a techno-commercial person. This is a term that a good friend of mine uses. Right. So I'm a technical person who can basically put a technology for a good commercial use.

Right. And that commercial use, you could say, is DevOps, security, compliance. So those are the sort of the areas that we operate on. I wouldn't say that I'm necessarily that deep down dealing with, you know, security algorithms and RSA and, you know, the Diffie-Hellman group and stuff like that.

I'm not at that level. Maybe a few levels on top of that. I understand security pretty well because my background is networking. For the much of computer industry, security has been very closely tied to networking.

Hackers, you know, firewalls, flows and stuff like that. And we did sort of like being in the cloud, one of the first distributed architecture for security. I mean, back then it used to be like Palo Alto, Cisco and so on, where you would basically put a box and just send all the flows there. Then we moved it to host-based security with security groups and distributed way of doing security.

So that's what I would basically say I substantially contributed to. And now it's become a standard, like distributed security and so forth. That's sort of my exposure to security. But from in this current business, I would say 97% of our customers are in a regulated industry because compliance is like another world, basically.

Security is like never ending. You can do as much as you like and it may never end. But compliance is more like, okay, there are certain guidelines. You need to meet them.

And then you sort of like make people feel comfortable. So I think I would say as much as security, I've also developed well in the compliance world. Yeah, GRC is important. And I was just glancing at the website there.

You have a SOC 2 type 2 and a bunch of other really great GRC successes. And I imagine that Duplo Cloud will integrate with like all of the standard tools in that space, like the Avantas and the DRADAS and the secure frames and all of that stuff. Pretty much. I mean, we have a couple hundred customers and almost every customer has some GRC tool.

I think the way I would say, so to speak, the value is distributed is that they're a GRC tool whose job is to collect evidence and pipe it to the auditor so that they can do their audit. And our job is to implement those controls, right? So what we tell them is that, you know what, if you use Duplo Cloud, then your Vanta goes green and your data goes green and then you can get all the evidences and so on. So we are the DevSecOps part of it.

We are the DevOps engineer equivalent while they are more closer to the auditor. Duplo Cloud is a little bit closer to where the rubber actually hits the road. That's right. If we do our job, you have your evidences.

I love all of the AI automation, the agentic workflows. That sounds like it just saves a ton of time in that space. But help our listeners understand and appreciate a little bit more of like how Duplo Cloud might accelerate their own DevSecOps or DevOps. Yeah, yeah.

You know, typically like how the industry has always been working on is that there would be engineers or business users. So they would have a requirement that they need from the infrastructure, be it like deploy a microservice or help me debug this particular issue or show me the logs. I want to build out a new application stack and so forth. Give me a database.

So what they would tend to do is that they would tend to write a ticket, be it in Jira, ServiceNow and so on, and describe the problem. And then what the DevOps engineers would do is that they would basically pick up the problem, solve it in the infrastructure and then update the ticket back. And the way they would solve it is that they would have some substantial amount of automation script. But that automation is largely for their use, right?

So they are the consumers of that automation. So it makes them go faster, makes them more efficient. To some extent, that automation might be exposed to the users also in the sense they can do self-service like GitHub Actions and CICD pipelines and stuff. But a lot of it is based on tickets, right?

I mean, you go to any organization, any IT organization, they are like inundated by the number of tickets, right? I mean, ServiceNow is a huge business, Jira is a huge business and so on. So what we are basically saying is that we can up-level the DevOps teams to some extent and also provide a better experience to the business users or developers by making this help desk agentic. So the idea is that the users have the same experience.

They go to a help desk ticket. But in this case, they are not assigning a ticket to a human being. They are assigning a ticket to an AI agent. And they describe their problem.

And the agent synchronously in real time solves the problem right then and there in a fully conversational interface. Very much like, you know, that includes all the black and forth between the DevOps and the developer and so on. So that's sort of the dream. So now what role does a DevOps team play in this particular case?

Their role is to sort of build those agents. Because while we give them some out-of-box agents for a good set of use cases, but after all, they are the subject matter expertise of their own infrastructure. They have their own customizations and so on. And then AI fortunately allows us to build a lot of solutions very quickly.

So we work with the DevOps teams to get them started to write those agents and sort of like go from there. So the DevOps team sort of, so to speak, graduate from writing scripts to building AI agents. And what is the role of the Duplo Cloud Platform? Duplo Cloud Platform, in simplest terms, makes it very easy.

It provides a lot of orchestration in order to do that. Because when you're writing agents, it's not just the business intelligence you have to do. Like, OK, who is the user who's calling? How do you authenticate?

You know, how do you pass context to the agent? And which environment are they talking about? The user will say, hey, tell me why is my application slow? Which environment is this application running?

Can you get access to that environment? What tokens is it available? Is it just in time? And then they may switch from wanting to look at the logs to maybe rebooting something else.

So now the agent need to have all those drivers and API calls to make to, you know, Kubernetes and cloud providers and so on. So there is a rather thick orchestration, which is, so to speak, tying the pieces together. And that's what we provide. And then we get them started with some agents and then they can enhance more and then sort of like take their organization's IT to a new level.

Nice. I love it. Since a lot of folks are very sensitive about their production environments, I imagine, you know, what I've seen out there in the industry is like, I don't want to call it hesitation, but maybe like caution. Caution is a good word to describe this behavior.

People are being very cautious around like connecting production workflows with agents. Do you ever get questions around like, hey, can I run this on-prem? Yeah. How do I make sure the agent doesn't do anything accidentally?

You know? I think there are a few questions over here. First is that, I mean, that's our bread and butter. That's our job to make sure that the agents work, they are safe, they're reliable, they don't do bad things, right?

So that's the value that we bring in, which is what I was using the term orchestration, like orchestration, Godrails, and so on. So first is that people really want their agents to be on-prem. And, you know, even before AI, coincidentally, our software was always on-prem. So we don't really have like something that runs a cloud and so on.

So this software always ran in customers cloud account. Why was that the case? So there's no SaaS. There's no SaaS.

Exactly. Right. And why was that the case? Because we were already dealing with very sensitive infrastructure.

So that problem sort of like goes away. Like we never had that problem to start with. Right. That's one.

Second thing is that one of the value additions in the IP that we have built in is that like, how do you safely bring human in the loop? And a lot of this AI, SRE platforms, because of this specific problem of safety, they end up limiting themselves to read-only use cases. But we, I mean, like historically have always thrived in provisioning right use cases and so on. So it was rather natural for us to build a workflow and a human in the loop experience wherein people can enable agents to do a lot more.

That's amazing. That's spectacular. So what about the LLMs? So the LLMs are driving the agents and they're kind of the brains behind it.

Do they run on-prem too? Everything. Right. And in fact, everything runs on-prem.

Everything runs on-prem, right? And then in fact- So is it like LLM3? Yeah. I mean, it's up to them what LLM they want to use.

In fact, I would basically say RIP is not in our agents, basic, right? We give the agent for free. We give away the code for the agent. They can change the models.

We give them hooks to change the model. They can write their agent, use whatever model that they want to use and so forth. RIP is in the vertical integration and the framework that they would use the agents or they would build the agents. And this is something which is very custom and specialized for DevOps.

And I think that's the wave of software that we are seeing nowadays that people are built like Cursor, Windsor, Ford. They are essentially a vertical for software development, for example. Tesla is a vertical AI application for transportation, right? Self-driving cars, for example.

That's right. Right. So what is special about Tesla, for example? It's not just the AI and the model.

It's like, you know, how it integrates with navigation, with the brakes, with the accelerator, with the engine, with the doors and parking and signals and so on. Right. Like how do they have those sensors to detect that? OK, it's a red signal or a green signal and so on.

Similarly, if you take Cursor, how do they generate PRs? How do they generate commands and so on? Right. And which is not AI effectively.

AI is a reasoning engine that drives all this, but you have to do all these things also. And that's what I'm trying to say is that we can use any reasoning engine that you would like, but we really like the framework around it. Yes. I think what you're saying is AI is a tool, not a product.

AI itself doesn't actually solve anything by itself. It's not going to like make an API call. It's not going to take you from it to drive your car or it's not going to write code for you. It'll just tell you this is the code piece.

You go and put it wherever you want to put and then compile it whichever way or rather I'll tell you the commands. But it's for you to sort of like go and do orchestrate all that. I think that there's a big misconception around AI and all of the hype around AI and that it's an amazing tool and we can use it to organize huge amounts of information. But yeah, yeah.

I think what I probably believe is that those like outlandish applications of AI, they're not as close as people make it out to be potentially. But it's also not as far as the pessimists believe they are. So I would say the answer is somewhere in the middle. So that's that's purely speaking the application and the impact that it is going to make.

Whether the economy around it is sustainable, is it fair? That's a very broader question. First is that where is all this money coming from? All of a sudden, these businesses have gone from a few hundred billion dollars to like several trillions of dollars.

This is a more economy question. OK, where did this money come from? Is it the zero percent interest that we've lived for the last 15 years? Is it that or is it actually real GDP that we sold stuff and then we made that money?

So I think there's a lot of that. So I think definitely potentially we could use some some correction over there. But I think it's a giant bubble. Yeah, it's like Internet.

I mean, dot com was the bubble, right? But it was the dot com part that was the bubble. SaaS was not a bubble. Internet was not a bubble.

Basically, when Internet came, it's like an equivalent of Internet is the models today. And people started building all these dot coms, which really had no differentiator. And then that was a bubble and a lot of people are building such AI applications. But what came out of the bubble was real SaaS software, which became the standard for the next 20 years, for example.

So I think we will come out of this with real AI applications, which would be the future for the next few decades. But I mean, is there an intermediate bubble in the on the way? I don't know. Maybe.

Maybe. That's really elegantly put. I can totally see that. When money is cheap, bubble forms and money has been cheap.

So that's the thing is, right? I mean, the government gave us money. Well, there's money. Money is cheap.

And I think there's a lot of investors out there who are just they they catch wind of like AI and they can see a demo with chat GPT. And they can play with it like on their own computer in private. And then they decide like, oh, my God, I have to get in on this. And then everyone decides that all at the same time.

And all of the money flows. The government gives it to you for really like zero percent interest. Then it goes down. It flows down to the fund.

They have to do something about it. Then it goes down and goes down. So it's a change. So but but yeah, fortunate.

I mean, let's see. Fortunately, unfortunately, it changes things very quickly. But then, you know, when you look at the bottom line of all of these companies and all of the investments, and it's actually quite difficult to build an AI product or an AI service that operates in the green. Right.

That everything is very expensive. I think that part I have no doubt. We as engineers or maybe entrepreneurs, I think our job is to deliver the best possible value with the best possible technology and potentially disrupt things. Now, what is the compensation for that?

I think that depends on the time in the market. You could be in a downturn and you could build an amazing technology, but you might end up selling it for a very low price. But on the other hand, you may build like a so-so technology that gives you so-so value, but you are really at the peak of the market and you will know what you may be able to maybe sell it for like five times or ten times more. So I think as engineers, what we can control is the product and the value that we deliver.

That's true. If you haven't seen the documentary on General Magic, like it's the story of the iPhone before the iPhone was the thing. Anyone that looks at those blueprints or that demo, you'd be like, wow, that's pretty much an iPhone. But it was long before its time.

Yeah. It was just way too early. Yeah. So spoiler alert, I guess, you know.

What's been the proudest day that you've had so far, Venkat, on your journey with Duplo Cloud? I think, I don't know if there is any one day per se. I mean, there are like ups and downs, so to speak. A lot of people think that, oh yeah, entrepreneurship is like so amazing.

You get up every day in the morning and like, yeah, like, you know, that's not how it works. You get up and like, okay, is it going to be a shitty day or is it going to be an okay day or is it going to be a great day? So to that effect, I've had my shitty days, I've had my okay days and I've had my good days. So I think we had some successes.

We've had some failures. But I mean, the good times are when you, let's say you do a round of funding, right? I mean, it's a validation that a lot of smart people are excited. They believe in you and so on.

So those are the positives. Then when you hit your milestones, for example, 1 million, 5 million, 10 million, 15 million, like these are all like very interesting milestones. Then, of course, we are a remote-only company. So we don't really get together often.

We get together once a year in US and once a year in Asia, around India someplace. So, and that's when you sort of like meet this huge team. So those are like good times, for example, right? So then you see that, okay, you've suddenly gone from like one person to, let's say, 150 people and so forth.

And of course, when you win deals, like a customer appreciates you or really likes you or gives you a reference. So these are all like good times. And then, of course, you have your downsides as well. Maybe a customer leaves you.

Maybe you don't really get in terms of the sales where you want it to be, right? So those are like the more challenging times. It's absolutely a roller coaster. To build something new, to build a company and to bring people together, like you have to be prepared for those really high highs and the really low lows.

I really relate to the NVIDIA CEO. And he says, right? I did get a chance to meet him because he had invited a few companies from my investors. And then his thing was that you guys are entrepreneurs.

What's wrong with you? Why did you do this? Right? I mean, I don't know.

I'm like, I don't know, mom. Nowadays, when someone says, yeah, I want to build my own company. I'm like, why? What's wrong with you?

It's very difficult, right? Yeah. Yeah. You have to be a little bit crazy.

There's like an optimal amount of crazy where you're like crazy enough just to pull that trigger, but not so crazy that you fall off the deep end. And yet the chance of success are like so small, right? I mean, they're like minusculely small. And the bad part is that you can fail anytime.

You may be doing great today. And then suddenly a big company releases a feature which is like so close to you. And then like it's free. And that's it.

And that's it, right? You're like, why didn't they just buy my company? Like instead of release that feature. Oops.

Or, you know, there is a technology change. Suddenly it's not relevant anymore. Okay. I mean, you're an on-prem software doing really well.

Suddenly SaaS comes in like maybe three years. Like, you know, you find yourself outdated. Or maybe you're a great SaaS company and suddenly there's an AI native company which raises like $100 million of seed. And you couldn't raise like $100 million till your CDC, for example, right?

So anything can change anytime. That's right. That's right. And to lead other people through that journey, you know, something like that would happen.

And then you have to stand in front of everyone as the founder, as the CEO, and still like describe something positive. Say, here's our path forward. Here's how we're going to win. Right?

Maybe I'm striking too close to home here. Yeah. All entrepreneurs go through that, right? Okay.

It's not just me. Okay. All right. Good.

All right. Well, I was going to ask you like what's the most difficult day has been through your entrepreneurial journey. But like you shared the whole spectrum. So there is no I wouldn't say this was like my best day or I wouldn't say this was like my worst day.

I think the general idea is that you sort of get used to all days, right? And then you just don't remember, right? And yeah, it was like a bad day and then you bounce back after maybe the next day or so and then you move on. And similarly, you may have a good day and then very quickly you'll have a bad day subsequently and then that good day will fade away.

So yeah, I think overall it's been a good journey. Yeah. I think you have to find a way to always like take care of yourself as you go through that journey, those motions, like as long as you can bounce back. Like what I've noticed, like sometimes go to these, you know, events where there are like a lot of founders.

The guys who are happiest are really the young ones, right? They just don't know yet what's coming. It's the ones in their seats and maybe the series A is like, yeah, I built that product. I'm like, yeah, dude, just wait two more years.

And then the and then the other ones are like, yeah, I'm doing this. I'm like, this is a go to market and stuff. So so you can almost like look at somebody and they're like. And their sadness.

Like, yeah, yeah, yeah, yeah. Like wash across their face. Exactly. Exactly.

That's really funny. I mean, we have to laugh about these things. Like you can laugh or you can cry. It looks like you can relate to it very much.

But you know. Absolutely. I've had my first share of like mess ups. Like, yeah, of course.

But I wouldn't have it any other way. You know, it's like it keeps things interesting. It keeps us on our toes. Like we're always learning and we're always growing.

Yeah. Yeah. And it's incredibly risky. You're right.

I kind of equate it to riding a motorcycle. It's just incredibly risky. But it's the perfect expression of freedom. And it's just you on that bike and the road.

And like it's the perfect mind focuser and absolute joy. And I couldn't imagine life without it. So has there been anyone in your life who's been like a mentor, who's like really guided you or that you've really looked up to maybe as a role model? Yeah, I think there's several.

First and foremost, I think I like I'm able to do any of this because of my family, my wife, the way she takes care of everything else. I mean, that's like the unsung hero. I mean, if that she's not there, I mean, I cannot do any of this stuff. Then I think I would say I've been very lucky because the first three years of my journey, I bootstrapped.

So there were like many, many people who sort of like helped out, like I had a mentor, Sri, who sort of like introduced me to his team. And today, 70% of my engineering team is from his previous company that he sold to, for example, Hitachi. Right. And at every stage, he was super helpful and so forth.

Then we had advisors. We had friends who sort of like helped us. I feel I'm incredibly lucky with investors as well. I'd heard bad stories and stuff like that.

But I mean, these guys have been amazing, like all everybody whom I met with. So on. Right. And yeah, I had some challenges with some customers and so on because you operate in startups and small businesses.

They have the economics issues and whatnot and so forth. So those hitbacks were there. But by and large, if I sort of like look back, I think I probably only remember everybody whom I'm grateful to. I don't think I can remember anyone would be like, oh, man, this guy screwed me or something like that.

So at least I mean, I have to think hard. But overall, I think many, many people, especially our investors, my mentors, even the people who work in the company, I think they've been very understanding. So in that sense, I think like we have like very like in engineering, probably in like the last seven and a half years, we lost maybe like two people or three people voluntarily, which has been pretty good. That's an incredible track record and that speaks mountains to your leadership style.

So, yeah, I think to that effect, our CTO, everybody in the team, people who manage customers, sales, marketing, everyone. I think I'm so grateful to our first salesperson, right, who heads our sales, right? And so forth. So everybody has been very, very kind and very helpful.

That's really amazing. And I really feel the strong sense of humility and graciousness around your journey. Yeah. Yeah.

No, I think like I said, right, I was an accidental number. I didn't set out to do this, right? I didn't plan for it or anything, right? It's just one thing led to another and sort of got me here.

So it was largely because of I think a lot of people had a lot of good work. It's really good. It's really positive. If you could go back in time and meet your younger self, would you?

And would you have any advice for your younger self? Yeah. I would basically say I would sort of like at least career-wise, you know, in the last 20 years, I would split it into two parts. One, where I was like a pure developer, where I, for the most part, cared about some specifics of the product or my perspective around that.

And like, how do I convince everybody else about that perspective, so to speak? I didn't have as much of a broader exposure and a broader understanding to that. And then when I actually became an entrepreneur and when I had to sell software to people, so they couldn't care less about my perspective about things. So I had to care about everything about their perspective.

I had to put things in their perspective and sell and so forth and so forth. So maybe I feel that I could have learned that before while I had a job. I mean, I had a decent success. I mean, even in my job, I mean, I did well at Microsoft and so on.

But I think it would have probably, yeah, I mean, that probably is not a very major thing. But yeah, that's something that I could have probably done earlier. Oh, I'm sure you just weren't shared the opportunity in your day job back when you were at Microsoft or whatnot to be able to have that customer-facing exposure, right? Customer-facing is what really taught me this.

But generally speaking, I think this is a culture, a behavior, or a personality trait that you can maintain wherever you are. It could be because maybe you're working with your colleagues, you're working with your seniors, you're working with your team, the people in the other team, and so on. And Microsoft was a pretty large organization. But then Microsoft is also, I would basically say, it doesn't help either.

Your chances of making an impact at a customer level, if you're a developer at Microsoft, is minuscule. Effectively, it's like very, very small. So I think maybe the ecosystem overall is like, okay, do your part and sort of like get promoted, get to the next level, and so on. It's very different than being an entrepreneur.

But having said that, there were like many people in Microsoft. There's like one individual. I learned a lot. He was my colleague and my manager's peer.

I always learned so much just by watching those people. They just wanted to make forward progress, bring the organization forward, and so on. So I think those things are very interesting to learn. Yeah, that's incredible.

You know, it's just a different experience to work in a big company than it is in a startup. You don't think broadly, when you work in a big company, you have to like sort of more fend for yourself in a big company. Well, yeah, and you're a little bit more of a cog in a machine. And it's like a giant apparatus.

And that thing is designed for one thing, and that's just to make money. And like when you have a giant machine that's making money, like rule number one is don't screw up the money machine. So like the risk taking and the risk appetite in those big companies just isn't there. Right.

That's why innovation very rarely actually comes out of big companies. I mean, if you compare Team and Slack, like Slack was so popular because it genuinely was a very innovative software. The way it worked and as an engineer, you would be like super proud of what you have essentially built. Teams is fine.

And nowadays it's gotten much better. But in no time, they had like millions of users. And that is not because it was an engineering marvel or it was a great product. It's simply because Microsoft bundled it in Office and everybody was using Office.

Right. So they cheated. Yeah. Well, I mean, I don't know if it's cheated or not.

It's just a go to market, go to market strategy. It's a go to market strategy. But now imagine yourself as an engineer who works in Slack versus an engineer who works in Teams, for example. Right.

So the Teams management may not particularly care about maybe technical purity, for example. Right. They're like, OK, guys, just get it out. I know I can sell.

I don't really need this level of feature set or a quality or something. So then your behavior over there can substantially be different than behavior of an engineer who is maybe building a small startup and growing up from the grassroots levels over there because they don't cannot afford this. They have to show real value to the customer. So again, there's nothing.

They're the greatest company in the world, in my opinion. And I think I am incredibly indebted for, you know, being there, my time there. So much I've learned. But all I'm saying is that for the same job profile, your motivations and your behaviors can be different depending on where you are.

Yeah, that's really insightful. You know, there's a lot of entrepreneurs that do listen to this show. And so this is a little bit of a leading question. But is there anything that a tool out there or a service that you just wish someone would grab onto and build?

And if there was a great solution for it, you would pay to have it solved? And it's just something maybe you don't have the time or the expertise. No, I think that comes up every time. It depends on which day you ask me.

Like, for example, today you asked me, like, I'm deeply involved in dealing with some sort of agent chaining where then like messages have to be passed across like multiple agents and so on. They have to be authenticated. Permissions have to be done. Also, the messages have to be reliable and so on.

So I'm thinking, oh, man, I have to build all this my own. Can I actually have some sort of a next generation? Like Kafka, wherein I can throw in a bunch of agent and then basically say that just send the message from this agent to that agent and then deal with everybody in intermediate in a reliable way. All right.

Just do it for me and so on. I don't know. Maybe it exists and maybe it doesn't exist. So this is an example I'm saying.

Right. So what I would basically say is that in software, I think there are so many solutions. There are like so many needs and stuff. So it depends on the on the day and what you're really trying to do.

But but yeah, I mean, it's an interesting world that we live in. And yeah. And I think maybe in the coding perspective, right, I think people are very excited about like the AI coding tools and so on. But you know what?

They don't work for existing code base. I mean, I can tell you. Right. I mean, really?

They don't work for existing code bases. So they're good if you're writing something new. Right. But give it your code.

Yeah. But you can't ship that code. You can't. Yeah.

You can't put vibes into production. Like, like. I mean, I guess you could if you're crazy about it. I think people say that, oh, I can replace a lot of developers.

Yeah, probably you can replace the developers or writing like fresh code and so on. You can make the existing guys like productive and so on. But it's not like I can wake up in the morning then say that, OK, these are the 15 tickets that I need to do or 15 features that I'll give it to Windsurf and it's done and I can just go to sleep or something like that. Right.

It's not like that. So so maybe someday when we can get there, that would be something really great. This has been absolutely spectacular. Huge thank you for all of the shares, you know, the vulnerable moments with us.

It's it's been an honor. Yes. Have our conversation to get to know each other a little bit more and a huge thank you. Yeah.

Thank you. I'm so grateful that there are smart people solving all of these hard problems and are building a better future where we don't have to like grind through the DevOps pieces and we can connect like well-built and function specific agents to solve a lot of these hard problems for us. So, yeah, all the gratitude in the world. Thank you.

And a huge thank you to all of our listeners for tuning in to another episode of the security podcast of Silicon Valley. I'm John McLaughlin, the host, and we were joined today by Venkat, the founder and CEO of Duplo Cloud. So please stay tuned for another episode. Comment and like if you find so compelling and share with your friends.

So huge thank you, everyone.