What Engineers Actually Do Now That AI Writes the Code

Your CEO said that more than half of Freshworks code is now written by AI. So you own that engineering organization. I want to hear your reaction to this. Is this the industry norm you're seeing?

I wouldn't say 100% because there's always code that is more than 50% in some cases more than 70%. For newer things it's more than 70% of code is being written using AI. Normally engineers write like thousand lines of code. Now you're writing 10,000 lines of code a day. So for example, we are encouraging our engineers to commits much sooner. Don't commit more than 500 lines of code. Anything more than 500 lines of code is hard for somebody to read up. Our bar is to get to can I get to 90% accuracy. There was a time that we were running at 40% accuracy and now we've systematically increased the deflection rate from low 40s to now high 70s and that's a ongoing journey. Ideally the number of AI agent should be more than the number of employees.

That's what we see. Everybody has a digital AI worker that's working for you or more than one digital AI worker that's working for you. Always invite AI to your table and learn to know its limits. Be the human in the loop. You don't blindly trust its output and assume that this is the worst AI that you'll ever use. The technology is getting exponentially better. Be ready to change.

Today I have Murali. Murali is the CTO of Freshworks. Everyone today is racing to build AI from a blank page. But he is doing the harder thing, rebuilding a 15-year-old public company for the agentic era. So today he's going to teach us the thinking behind the rebuilding a plane while it's still flying. Welcome, Murali.

Thank you Angelina. I think we are not just rebuilding, we're redefining our products of how they can use the power of AI to provide better experience for our customers.

Can you share a little bit about yourself that we cannot find with AI or on LinkedIn?

I'm an engineer by education. I've migrated from India about 30 years back to US and I've lived in the Bay Area since and working for small, big, large companies. Some some successful, some not successful, some public, some private. So I've I've seen the world through different lenses and it's it's been a journey before AI. I started in the in the pre-internet era and then I've seen the internet era evolve and then I've seen from moving from a client server to a SaaS-based products growth and then you're seeing the AI growth. So every every generation takes a new set of things. So I've been in I would say a good or bad I've been in each of those redefining moments for tech. And each and each section of that generation of products have taught me something that has changed how I think about software how I think about building how I think about kind of bringing new products to market using that technology that's available.

Things you've seen at all. If I were to ask you one grand takeaways like what it what would that be?

It is just the curiosity to learn. Each defining technology has something that you want to leverage and then it takes a finite amount of time for that technology to settle down and for people to start using it to understand how it really works and then how it can be put to use how it can scale how it can be made secure how it can be made extensible. Right? So that's what we've seen with the SaaS era. It took 10 plus years for the SaaS companies to evolve into something that really can scale and somebody can scale and perform and be secure. And even for the customers the same thing it took a generation for customers to accept that on premise is gone and now we need to rely on cloud-based software to get things to run their business. That transformation did not happen overnight. It took customers many customers 5 to 10 years to do those things. So I think that's a reality. Check.

I'm really curious about your product and I did some homework before this. So I pulled your homepage from the internet archive. So in the last four months, your hero line actually changed three times. You probably aware of it. Enterprise grade without enterprise complexity. So this is April this year.

Yep.

Can you see this one? So this is one. This is this is July. So last month it you're calling yourself United service operations for the AI era. So I can see the AI era becoming one of the part of the tagline. This is the newest one. Of course this is saying turning operation operational complexity into coordinated action. It sounds like it's alluding to agents taking actions. And this August change looks like a full visual relaunch as well. So it's not just a copy swap. I'm really curious did the actual center of gravity of the product actually move underneath those lines?

I think as you're seeing we have evolved from being yeah if you go back in time Freshworks is a AI powered unified service operations platform and that's faster deploy intuitive use and enables every employee to be more productive. So that's our tagline right. So as we have evolved we have evolved our product from being a chatbot based interface into LLM power to the agentic era and then from the agentic era it's all about trying to help humans be more productive in the sense that we support self-service use cases as well as human in the loop use cases for agents to resolve their tickets much faster and the intent is that any any repeatable operations can now automated end to end.

That way our goal is to make sure that for repeatable operations that are trusted by the humans, we want to automate it end to end and that's how we're looking at it. And then it's not just tickets, we're also looking at other operational aspects of running your business. So when it comes to employee experience, you're looking at how your IT is set up, how your services are running, how you request for software, how you request for software needs to be updated. If you need to set password change, it automatically does the password change. The site goes on, it automatically informs people and triages and then the right people are involved in order to troubleshoot the problem to get it fixed. So we're moving from not just somebody logging a ticket and somebody looking at it. Can I proactively start identifying issues so that I can resolve them before even it happens? That's the journey we are in.

Is the is the main customer-facing interface through a chat interface?

It is one of them. So we offer multiple because there is no one one solution that fits all. So we are offering if you are a agent that means a person who's actually receiving tickets and solving they're using a web interface to solve those tickets. But if you are an employee which is in a company, you use whatever is a chat interface and the chat interface could be through the web, could be through a Teams or a Slack or any of those channels to get things done. And if you are a customer service agent and you are you have an issue with your with customer support for one of the products you bought through the website, then use a web chat as an interface to interface or you can use a WhatsApp or a Apple messenger to interface.

So we have multi points of entry but all of them lead to the same set of conversation based experience for you to directly talk to the bots and to resolve the issue as quickly as possible and some of time it's not just answering questions is also taking action to make sure that oh you ask for a refund it actually processes a refund for you instead of you waiting for a human agent to come online to take the information and process. So our goal is how can you do it without in a frictionless approach without having to loop in too many people and how do you reduce the number of hops and get it done in a few number of steps.

I know that you had Freshdesk which is a ticketing center for many years. So which parts of the product suite did you actually have to rebuild from ground up or which parts are just AI layered on top of what was already there?

Lot of the products that the source of truth or we call it the source of record which is the that is standard right how we store tickets how you how the tickets are linked to users how those tickets are linked to products to services the structure the data data schema all that stuff continues to be the same right because end of the day whatever you do you have to store it somewhere so that you can then report off of that information and then you can act on that information. So none of that structural schema is changing and our product was always API enabled from the get-go. So we either customers could do it through the UI or they could do it through API, right? We always had that interface open with the evolution of AI. We have MCP enabled some of our interfaces. That way a third party AI tool can actually interface with it because working with an API is little harder for AI based tools. But with an MCP it's a lot more decorated.

So it's much easier for it's coming from Claude or OpenAI you can directly interface and do reads and writes into our system right so that's so that's so we have added that layering on top from an agentic perspective it's more of we already had a fully working workflow engine that did deterministic flows right you it means that exactly know you can you can you can map out the flow to say when this happens do this and this happens do that and you have decisions loops, all of that stuff. So, some of that stuff doesn't change, right? If you're trying to reset a password, the steps to reset a password doesn't change, but in order to make the decision that should I reset the password or not is where the agentic AI comes into play because you don't know what the user's real problem is.

So, where the AI layering is on top is to first understand what the user is trying to do. Is a user having an issue logging in? If he's logging in, is it because the person for forgot the password or is it because the person is in a wrong page or the person is using a wrong ID? So, you need to first investigate what's going on or help understand the issue. Once you understand the issue, then it's easy for you to take action and that's where you call a reset password action and that'll reset it. So that's the thing that's the facading that we have to do is where we have to collect as much information as possible from the user through conversation and based on the responses you can direct the user to the right solution or outcome. And that's what we have done as part of the product. And so that means that it doesn't change how we were operating within the product. It changes how we interface with our users and how we leverage data to make decisions for on behalf of the users.

The automation happens with in the past a human has to do it changing the passwords. You as an employee I have to talk to the IT person or something maybe if I got logged out and I couldn't log back in anymore. But now basically yeah agents can take over that downstream pipeline of actions and then do all those things without a human supervision. That's what a value add that you're you're building on top.

That's right. So some of these workflows can be automated because you can generate those actions by looking at a pattern. You can generate those actions into the agentic workflow for the for the AI bot to automatically perform. Right? You don't have to codify every single thing, right? That's what the agentic stuff is like. It makes decisions based on the patterns. It makes decisions based on the inputs and the answers given by the user. It kind of you don't have to think about all parts. Normally in a normal workflow, you would say I have to anticipate all scenarios and then build a workflow and it might handle 80 whatever nine out of 10 scenarios but might still miss out some scenarios. Here there is a high probability of it figures out based on the need and then it connects the dots and then creates the right workflow for the person to perform their operation.

Yeah. And that's through runtime, right? Figuring out the best path of solving a problem.

Exactly. A lot of it is not design time. A lot of is runtime. But you empower the person. It's like similar to you have a handyman. He has a toolbox with a set of tools. And now the handyman, we empowering the handyman to have all the tools on their hands so that now they can use all the tools to figure out how do I fix it a leak on a tap or how do I put a doorknob in place. So they need to know what tool to use when. So that's what the agentic framework makes that decision at runtime.

Yeah, I want to double click on the MCP part. I interviewed another founder and he told me that most public MCP servers are basically unusable. It's untested and a very few tools and probably have bad authorization. So I'm curious about your MCP gateway. So you must have to connect with all the third party tools like Zoom or Workday whatever it is. So are you relying on those vendors official MCP servers or are you building them yourselves and harden your own version of them?

So we have two sets of MCP servers right we call it one is we call it the inbound MCP servers and the outbound MCP servers. Inbound MCP servers are nothing but how somebody interfaces with our Freshservice product. That means they can push information or get information, right? We call it that means that MCP server has been built by us.

What do you think is the real value add of MCP servers letting you do today versus maybe last year still relying a lot of the API calls?

APIs need to be coded and right now MCPs are a little more discoverable in the sense that like I said it's runtime configuration, right? At runtime using MCP I can now discover all the tools that a I can use to talk to a system of action and then I can that way it's much more descriptive and it's written in a form where I can I can interpret it. The other advantage of MCP is the AI tools have become lot more savvy in interpreting how to use MCP in an interoperable way. Right? If I if I don't have to be able to say use this API, this API based on it's like I'm exposing a rolodex of all the things and it goes and looks at okay this API makes sense based on the description. Let me use this API let me connect it. So I don't have to link same thing I don't have to manually wire one API to the other. If I expose both MCP servers to it, the AI engine is smart enough to introspect that MCP server for the tools that it supports, figure out which tools are can be mapped to which other tools and then make the right API call.

So that chaining becomes easier and chaining happens at runtime. It's not again a design time. So that's what I think that's the flexibility that MCP has and it's it's getting a lot more useful right now because everybody's trying to get data from multiple sources and it's it's so convenient if it's instead of trying to go somebody go run a query against a database if it if there's an MCP interface that's available you can use that MCP interface to query that data source. I do that all the time in some of the work that I'm doing. I don't I no longer go to a static dashboard. I no longer go to a database and run queries. I operate using the MCP servers that have been exposed through those data sources.

And your agent product that's called Freddy, right? How old is Freddy?

Freddy has been around since 2018, but we started in an era much before the whole the GenAI evolutions happened, right? So GenAI evolution happened back in 2022. So we started with the whole AI ML models because some of those things that was the that was the norm of how you build AI ML solutions before was to use those traditional BERT models and traditional classification clustering and other regression models to solve for use cases that required data scientists to look at the data understand it run trainings patterns and all of that. So it was a very methodical way of doing it but it took time and then it and you the only way to know whether it's working or not is to actually try it on a customer data and then figure out it's working or not. So we have yeah we have gone past that.

So as part of the whole moving to the generative most of our use cases are now based on these frontier models. We don't leverage the traditional models as much, but there are some use cases that still need access to look at customer data patterns and then make those decisions, right? We can't just make decisions without looking at customer patterns. Like in our case, a simple example is we have a ticket suggest which means that ticket field suggest. So when you're logging a ticket, how does it know that you should be assigned to this particular team? It should be assigned to this particular priority. It should be assigned to this particular type of issue. All of those things are derived based on historically how those tickets have been created. So some of those things are better done using AI ML models than using these frontier models. So there are still continue to be some use cases which require traditional AI models but for the most part 90% of use cases can be achieved using the frontier models.

Is the reason for that being hallucination could still be a problem that in like high stake decision making pseudo agentic process so you're not using a LLM as a judge to make that call like this is the path to go or the other ones instead you know the history anyway so you use ML makes more sense

Yes I think some of it is hallucination some of it is also the patterns of like how you're trying to use the GenAI models here so some of it requires a lot for looking at data patterns and coming up with you don't want to pass all the data to the LLM as well right you don't want to be like normal way is people say I'm going to pass a context to the LLM and then through RAG-based search I'm going to let the LLM interpret the data I can't I can't push millions of records into LLM and say now you tell me what should the field be right so that's why I think sometimes you cannot use a you have to know what to use you can't use a Ferrari to go to the grocery shop, right? You have to be able to use the right tool for the right right purpose. I think that's where it's it's a cost versus benefit. So certain models I think it's more effective to use a traditional model because that use case does not scale if you suddenly are trying to operate at a much larger data set.

Do you have any heuristics of like making that kind of decision? What kind of things you need to rely on opening up the context window and give just that to the LLM who make decisions versus where do you do you make decisions using a more deterministic way

Exactly I think that's where the experimentation comes in we do have a group of data scientists who are constantly looking at they're looking at model evaluations and understanding what is accuracy of data what is and where is it where is the tipping point for it again that says that okay it works for x number of records but the moment it goes to y number of records it doesn't right or the accuracy drops or it takes longer time to get that outcomes right so you want to and how many tokens are you consuming in the process so we looking at all of these patterns and then trying to determine the best approach for a certain problem so certain times for simple use cases for example like oh I'm I give a block of text and I say summarize I'm not going to use a model I'm just going to use a the GenAI frontier model to summarize it for because there's not much logic to be applied other than processing a bunch of text.

But when I'm passing something a little more structured, structurally rich with context of what that ticket means and it has access to other things that it needs to look at before it makes a determination. In those scenarios, either you do the pre-compute and then let the LLM model make the final kind of it can help you summarize or can maybe order stuff or it can make the final call. But instead of doing that you can doing do this end to end using a traditional ML model practice deterministic model practice. So I think each each use case has to go through the same journey and that's part of the experimentation phase that we put through whenever there's a requirement we say okay let's try through all these approaches and then whatever gives you the best outcomes is what we'll go pick and then it also has to not just the best outcomes it also has to be scalable and it has to be from a cost-benefit perspective it has to be beneficial as well

I'm curious what is the single hardest technical problem your team actually had to solve to make Freddy agents work in production.

Single largest just problem that we need to solve. I think as an engineer, there are many such problems that we tackle on a regular basis. I think one of the things that we had to solve is definitely the hallucination was accuracy of data right how much deflection can you achieve for your tickets. So we have we have constantly have we our bar is to get to can I get to 90% accuracy right can I get to so there was a time that we were running at 40% accuracy and now we've systematically done a lot of work through model evaluations looking at training data looking at patterns of data to then looking at feedback looking at positive conversations tweaking our instructions tweaking our how We leverage these models to systematically increase the deflection rate from low 40s to now high 70s. So and that's a ongoing journey go we have not stopped. We're continuing to now figure out how do I get from high 70s to high 80s to high 90s. So this is just one of the many things that we look at on a regular basis.

Are you doing some guardrails or preventative measures for especially things related to agents potentially going rogue or doing something irreversible, right? Like messing up someone's payroll because the model still hallucinate and you're saying your accuracy is around 70%. So how do you prevent that from happening?

Yeah, I think that's why we still have human in the loop for some of these things, right? Wherever you don't have high confidence, you come back and say this is what I found out.

And we let the human make the final call to say okay from a confidence perspective if the confidence is below 50% we will we will make sure to not provide that kind of outcome back to the user or we will make a suggestion to say this is what I found can you tell me what's the right path to take and then we let the human make the judgment and then we learn from that interaction so that next time a similar pattern appears we are now say oh this was somebody already said this is the right path to take and let we take the right path right the confidence improves with actions right the more you use the more the system gets better and that's where the trust improves the trust is the very common pattern for all AI based solution is the more you use it and the more people give feedback or implicit feedback or explicit feedback the trust builds up that means that next time it's going to do it's going to say oh this is a proven path let me do it confidence similar to how we do driving right the more the more you drive the better you get that's exactly what you see in the AI world as well.

You're covering several different aspects. Customer service, IT side of things, human resource management, all in one platform. I want to ask you like why why why should I think about buying a whole bundle of things instead of the potentially a one vertical tool for each one of my problem. There's a cost to unify all those data across different departments where in a business all of those information could be needed for one for one agentic loop, right? Especially if it has a long pipeline then it's going to be cross department single vertical doing one thing right

Yeah the larger the company the more complex it becomes right so you have you have like if you have 10 employees a certain set of complexity if there is no real separation of roles the moment you go from 10 to 100 to thousand to 10,000 there is separation of roles and separation of departments that means you cannot just randomly work with HR you have to go through a certain protocol to work with HR that means the any automation that you have put put in place. Any AI agents you put in place have to respect the same protocol. Just because you're using an AI agent doesn't mean I can just skip the mark. You if you have to send somebody something to somebody for an approval before you process it, you have to follow that same protocol.

How are you pricing your AI agents? I'm curious. I heard that you recently announced a session-based pricing.

Yeah, we've again the pricing is a is a science by itself and it's evolving as we speak and we are we've always supported session-based pricing for our chatbots and so we have we have desired to open up the same similar kind of session-based pricing for our AI agents too which is slightly different from how our other competitors have priced their some of their their AI agents in our case if you're using a web-based AI agent one session is equal equivalent to the conversation you can have within a 24-hour period. So, we give you a lot more coverage. It's not like you send a message, somebody responds, and it consumes a session. No, it's it's sessions that are consumed over a longer period of time. Similarly, we have email AI agents where that's something which is very common in our Freshdesk customer service use case where customers are emailing the customer support help desk and they get tens and thousands of emails there. It's we these sessions run for 72 hours.

That means I can do I can I can send a message, the bot responds back, the person responds back again, the bot responds back again and they can go on for 72 hours and we still count it as one session because the it's not like something that you just sometimes you get an answer right away. Sometimes the person is not happy with the answer so you have to respond back again. And so depending on the type of interaction, we kind of make our sessions extendable for that particular scenario. Again, this is just an evolution. Pricing is still evolving. People are looking at resolution based pricing, credit pricing. So right now we have a combination of hybrid pricing in the sense that you do buy seats for the people that are solving tickets and then you do offer sessions for employees who are actually interacting with those AI agents and then so it's a combination of both. If you have more employees then you may use more sessions. If you have less employees you might use less sessions. So depending on the company and depending on the need the pricing is adapted to their business needs.

It doesn't seem like there is a there's the industry has come to a one single conclusion like how SaaS was designed right and versus today AI agents has so many variations of how we can how we can price it.

I know I think there is a there's a little bit of that variation to customers don't want to pay a running bill as well. So what we are seeing is people are looking for predictable pricing to some extent. Even though we are saying sessions, we are expecting customers to or we will work with customers to anticipate the number of sessions that they might consume based on their historic volumes and then they would buy those session packs. That way they have they don't have to keep coming and buying more.

So it's more usage based.

Yeah, it's like more usage based, right? That means they have they have they anticipate that I'm going to get 10,000 tickets and they buy sessions equivalent to those supporting those 10,000 tickets. That way they don't have to keep budgeting for it because customers also work with a defined budget. I've allocated x amount of money for my IT, x amount of money for my customer service. So you want to be able to make sure that they are able to operate within those norms too. That's where the whole token maxing and some other stuff became a problem because there's no unlimited budget. There's always a limit to the budget and we want to make sure that we work within those boundaries

And people wants to see outcomes. It's not just like a predictable budget but also they want to see the real outcomes that I'm spending this much money. I want to know that what I what's the ROI on them.

That is true because if you're if you're doing something and if you don't get it's similar to anywhere like you ask something for some you ask somebody for a favor and you expect that person to give you an answer. You're not expecting person to not dodge the question, right? That means you so similarly when you're using an AI agent for a certain purpose, you're expecting that AI agent to solve give you a solution to that problem or solve that problem for right either way.

Let me switch gear to like the people side of the questions for the 2026 version. Your CEO said on one of the earning calls that more than half of Freshworks code is now written by AI. So you own that engineering organization. I want to hear your reaction to this. It is this the industry norm you're seeing?

It is. I think we are more and more for code. All all our engineers have access to multiple coding tools and those coding tools are used by our engineers to build new code and naturally a lot of that new code that we're adding is generated by AI. It does require to us to put a lot more gates and make sure that the code that's being written is tested, reviewed and deployed in the most secure manner. So we have increased some of that governance there but it is true that a lot of the code is that is getting generated or all the code is being written is by leveraging AI and it's it's that means the experimentation is getting faster. We are able to make sure that okay we can if somebody thinks about an idea it's easy to build a prototype that you can iterate over and then when you agree on what's the right product to build then you go ahead

Did did you say 100% is actually not 50%?

No I wouldn't say 100% thing because there's always code that is the human it's not like the code is automatically being written more than 50%, of course. I would say in some cases more than 70%. For newer things it's more than 70% code is being written using AI that for existing code where you are marrying you're making changes to an existing code base and you're adding new things there's a lot of AI it's a blend of human knowledge and AI which needs to write the code for you right so depending on the use case a new product lot more AI code existing product at least 50% of the code is AI that's all we

Did you notice that when we're using so much AI in our day-to-day work it's not just engineering team probably our PM and team does the same thing. AI is very verbose, right? So you tend to have like a much longer PR to review. So it's the work becomes not writing the code but as actually becoming reviewing the code and reviewing the PR and e even a PRD it's the same thing, right? You probably have a nicely done PRD you're looking at but it's really really long. Are you seeing that how are you tackling that problem within your organization?

Very true. I think we seeing we saw the same patterns emerging where whenever somebody is writing a document it's a large document n number of it's like 20 page documents or 30 page slides the codes people are generating normally humans used to write engineers write like 1000 lines of code. Yeah. Now you're writing 10,000 lines of code a day because of amount of code you're checking in. So what we are encouraging people to do is we've come up with best practices of how people should use some of these products.

So for example, code, we are encouraging our engineers to do commits much sooner right we are asking to say okay don't commit more than 500 lines of don't commit in less than 500 lines of code that way it goes through those checks quickly and it's and we have used AI reviewer tools and then we have human reviewers as well as an ad hoc basis not every code gets reviewed by humans but those checks and balances are there where some sub subset of code gets reviewed by humans too and we want them to view code which is palatable right so anything more than 500 lines of code is hard for somebody to read up right so that's why we are we have we have put that checks in place for to kind of set those guardrails. Same for PRDs, it's more of how much information are you gathering so we have we have started adopting something called AI PDLC, AI product life cycle, where from a single page abstract we are able to generate a multi-page PRD and which takes the information looks at oh looks at the feature looks at the code looks at customer reported issues looks at documentation looks at UI and then fills the blanks for you right so it's filling the page full of it but the intent is the after generating it the product manager has to review it make sure that they correct things that are not right in and fix it before they pass it to the next stage of generating code or generating a technical design doc.

So we have checks and balance in place where it's not like we take something and directly put it in. The person has to review it, make sure that the content that has been generated is good before they pass it to the next stage.

What about promotion? Because of AI, we're probably doing more than we can do in the past. But does it mean that doing more will get us promoted now or does that come the new baseline? How are you making making decisions around that?

I think yeah it's all efficiency is what I think it's not about the amount of code you're writing it's amount of efficient how are you leveraging your time to do more more things it's it's are you doing more with less or are you working on producing code but a lot of people write do a lot of experimentation but if that code doesn't really get into the product it's not of much use right so that's why we see outcome again outcome based rewards is what we have. If somebody has contributed to a product that got released and that released product is generating revenue, then naturally the people who worked on it get a lot more credit for it. Instead of somebody who is just experimenting and producing a lot of prototypes and mocks, but it's never seen the light of the day, right? Then that is not yes, they're producing a lot of experimental stuff, but nothing has seen light of the day. That means the outcomes have not been met. They are rated differently. With somebody who's attributed to a product that actually shipped and used by customers.

You as a leader doesn't mean that you're hearing a lot of pitches these days for experiments and people probably are having tons of ideas, you know, but you'll probably have to think like what's worth doing and are you allowing these these creative budgets on how employees are spending their time on like 20% you can explore but 80% you have to stick to our road map or things like that.

Yeah, we are again we don't we don't have that kind of 20% 80%. We are just letting them experiment lot. If somebody's really curious, they go and experiment in either they finish their work and experiment or they find time to do it outside their working hours or weekends or something. I think so the curious learners will always do it wherever you are, right? And good thing about AI is it's opening the doors for many. So many people who thought they couldn't do it are now able to do it because AI lets them do it faster and AI lets them try it out. So we are allowing people to experiment all the time, right? Independent of whatever they have primary tasks are. And then we do hackathons, we do some of these idea gathering sessions and teams get to experiment. So we have this thing where between when you're moving from one stage of the project next project, we do create a little bit of room for people to go experiment and build tools and do things. We're always encouraging people to build new skills, new tools to make engineering productivity better.

Right. So that is something that happens. There's a product track and there is experimentation track and there's a productivity path. So people are always switching gears. If somebody's bored of building something, they'll go back and build a tool or somebody says, "Oh, I'm doing this over and over again. Let me go build it and automate it." And they go build something and contribute back. So we encourage people to share new ideas, encourage people to build new tools that other people can benefit.

Has AI changed how do you think about how big your team needs to be

In a way, yes. It's true that you have to understand how you what kind of skills do you want on your team. I think that's the way I think that things have changed. Before when you're building a product, you'll say I need a front-end person, I need a backend person, I need somebody who understands this technology versus that technology. With AI you don't need as many specialists you need a few unless it's a really really complex thing that requires a certain person's domain expertise you can any person can do anybody's job that's that's that's becoming a little bit of norm and then you don't need a developer and a tester and a designer and a sometimes all all of it could be the same person who's doing the work right so that's what you're seeing so it's not the team itself it's the number of roles that are involved in a project could be depending on the size of the project.

If you're running a big massive project, yes, you may still have designers, you may still have testers, you may still have product managers, but if you're working on a small size project, you could be playing the same role. Yeah, you are the developer, you are the designer, you are the tester, you are the security guy who is doing all these faces as part of your development. That's what we say.

The problem is this is not how we grow grew up. This isn't how we were educated, right? Even people with past experience are probably set in one single row and they haven't seen the whole pipeline how things are done. So are you seeing how do what kind of people are you seeing are becoming more successful in this in this new way of how you organize the team. It sounds like you're expecting your team members to wear multiple hats.

I think the people are people are open to change. People are open to learn. People are open to be creative. I think those those are the ones that are succeeding a lot more than others because they are willing to experiment, they're willing to learn, they're willing to change how they operate if something else is better, right? So they're not settling for less, right? They're always constantly saying, "Oh, there's a new technology. Let me experiment with it. I used to do it this way. Let me do it the better way." Right? Whoever is willing to embrace change, they are the ones who are actually succeeding.

If somebody's trying to say I'm I've done this the way and I'll always be doing it that way there'll always be some work that they could do but it'll be very hard for them to break through because the kinds of things they would do is getting are there fewer and fewer things that are happening for those kind of people right for the majority of the people is all about oh I'm learning something new I'm building something new and every single day there's a new technology that something is getting better than the previous day right So the more curious you are, the better you are as a engineer.

Are you changing your team structure to enable these kind of creativities in a sense? Let's say if I'm on your team and can I just come to you one day and just say I have this like great idea and I pull some data and did some market analysis and ICP analysis. I can tell you this potential have great impact and if I convince you will I be able to build something like that being the PM and being the data scientist being the engineer who can actually make it happen

Definitely yes because I think that's that's one thing that's where this the teams are no longer becoming rigid you have the opportunity to be a team of one or a team of two or a team of five right you can form your own teams with like-minded people and you don't you're not no longer thinking about it as I'm operating in sprints where you have to have defined work that needs to be planned and done. People are people have a lift of task, people pull it, get it done, move on. And so the ways of working are changing with how people are operating, right? Some of it if it's planned work and we know exactly what we have to build, then yes, it's a group of people are on it and they're building it. But for a lot of unplanned things, people are coming up with ideas to say, I know how to do it. Let me come up, let me pick up the task. Let me come up with a design. Let me do it end to end without having to rely on somebody else.

So we see both kinds of both kinds of play. So there is no rigid team. I think we talked about oh do you have to set and say this group only works on this for the next six months. No I think there's a lot of flexibility that's happening right now where teams are saying okay I don't need as many people to get something done or they are pulling the right person for the right need at that time but then the person goes back to their original team. Right?

There are a lot more free forming teams right now because we can we can we can bring in people with the right mindset and then get the job done because like I said there's no requirement that oh I need to know this technology better than that technology generating code is the easiest part what you want to generate code the designing the right designing the solution for the problem is where the most of the brains are being spent right now am I solving it the right way is it working the right way I do I understand the problem do I Have I designed it in a way where it is going to look solve the problem and then also not just work for this the this use case it's going to work for other use cases beyond the problem right can I anticipate what could go wrong and build it with that in mind those are ways I think people are spending more time not writing that code because writing the code is become become easier that's why the planning agent the design agent those are becoming a lot more important the coding agent is the step where people can generate code in any language they want and then push it through.

Does it mean that your managers are essentially shifting to do different things? I imagine when I was a manager, I managed my team. I have a set of projects I need to do and I just make sure the team do a good job on finishing up. But now it sounds like managers has to be investors, right? They kind of have to take a investor perspective on what to invest on, what to spend the time on and listen to the team members to pitch, right? And each layer and eventually reach to you and you decide what worth investing and then so that the fluidness of team forming up like a squad team working on something can be realized.

That's right. Yeah. Manage like I like the word investors that you were I think exactly that managers cannot be just pure people. Managers are they have to be techno-functional. They need to be able to roll up the sleeves and support the team. They need they should continue to experiment themselves as well. So we are expecting managers to be lot more hands-on to do things because there is no barrier to entry right now right anybody could do any task and if you're a manager who has got some sort of experience doing some things then you may be able to contribute to a design much more easily and build it you don't have to say I didn't code before because coding is not the coding part of it is the easier part of right because before you say I've coded two years back or I've coded 10 years back I cannot code anymore that is not an excuse anymore, right? You can still leverage your experience to generate the code. So that experience is what matters here because you built something a system at scale. Now let's use the same experience to design a new system that can operate at scale.

Are you also thinking of flatten the team structure a little bit more to have more agency around the team members or

We have done some of that stuff as well where we have we have we have created Yeah. So we it's not like we need again for the larger the company you do need some of these structures because it's very hard you need to keep the employee connection going but we have done some intentional flattening of our structures to make sure that each layer is adding value to the system right if we if somebody's is a team manager they're adding a certain sort of value to the system and they're not just managing people

Do you have kids?

I do I do

Can I ask how old are

Okay, I have one son. He's a biomedical engineer and so he's building he's part of a surgical robotics company. So they're using AI in a very different way, right? They're using AI a surgical robot to actually perform surgeries. Yeah.

Have you had a conversation with him about his career like what to study and I know he ended up doing the robot engineering but have you had that conversation even today?

I think yeah one conversation we always have is being a pure software guy is it good enough or you want something where you can use your hands to do something right so he's he works on electromechanical and software as well so he's saying okay he's a lot more marketable because there are certain things that cannot be replaced with AI he still has to work on a circuit board he still has to do certain things where he has to wire things up and he has to do certain things which again there are robots which do them some of that as well but there is a little bit of human aspect to it right there are certain things he has to physically go into the office into a lab to actually work with his the surgical robots he can't do it from home right so like we all being a software engineer I can I can work from home I can do everything independently so he feels that his job has got more job security than anybody else yeah again time will tell but the key thing is he's also learning He's also doing a lot of things on the side using Claude and other coding tools to keep himself up to date, right?

So he realizes that there is a lot of things that he can do without having to wait for to happen at his workplace.

So for the for the all the engineers and builder audience I have watching this now, do you have any suggestion for us to make us more irreplaceable for the future?

Irreplaceable for the future. No, I don't think we should think about it that way. I think Yeah, that's that's an interesting game, right? I wish we are immortal and it's like similar to being immortal, right? I don't think we want to be immortal. So, it's good to have somebody who is challenging it. That's how human race has evolved, right? When somebody challenges you take it up as a challenge and you make it better and that's how we have conquered different things, right? So I think we should continue to have problems only makes it better, right? I we don't want to solve everything that with nothing else to solve. Then there is nothing then people don't know what to do with their time. So I like having problems and challenges that we can solve and we can look forward to coming up with a solution to solve them better.

Right? That's how the human race is evolve. So whatever we used to do 20 years back now we're doing it better and now we moved on to bigger problems and solving those problems and there are any number of problems in the world. So and we should continue to challenge ourselves to solve those problems.

Are you fundamentally optimistic or pessimistic about the future of AI and why?

I'm I'm optimistic in the fact that okay there is so much that's that can be uncovered using AI if you use it the right way from a I want to make sure that use AI responsibly is something I believe in. So I'm optimistic about AI but using it responsibly is something I want I believe.

Can you teach me one thing to make me a better technical leader you today?

Teach me one thing to make a technical leader today. How do you use AI right now in your in what you do right now? How do you use AI?

I have the same question for you. I use I use I use Claude Code all the time.

Oh, you use Claude Code all the time. Have you tried trying out other tools like experimented with something that's built on Claude and then you try to build the same thing on Codex or Cursor and see how it compare and contrast? It'll be good. It would be good to put things to test because we always trust one thing but it always good to experiment with different tools because the way some of the tools the models the models that are being used in with Codex and the models that are used in Claude are slightly different. So you might get different outcomes. So you may want to see how the compare and contrast are the same results but built using two different coding tools. And that might be a good way to test whether whatever you're thinking is working or not. Right? So which one is doing it better if any?

Yeah. If I don't compare then I wouldn't know. I wouldn't know.

You wouldn't know. Exactly. I would say that's why I'm saying don't trust one system. I think one thing that AI has also taught us is biasing. You don't want to get biased to using one single tool because it only knows what it knows. So unless that's why whenever you are doing evaluations and stuff like that you evaluate with different LLM models and that just that way you are able to compare and contrast like similar to how you run an idea by four people you want to be able to evaluate using different different AI tools as well.

That's why I'm talking with so many founders and I found like so everybody has different opinion. There's a school of thought about only vertical AI will survive and there's another school of thoughts of the future is about horizontal AI that solves everything solves all the problems.

I think everybody will survive just that there'll be a race. It's a race, right? Today one one tool is better than other tool tomorrow other tool is better. So it's like it's like driving on a highway. We all drive at different speeds and eventually everybody gets to the finish line, right? Some people who drive fast maybe are ahead but they get they meet an accident and this slows them down right so it's a we are on a highway of AI and it's a constant journey and we're all going to reach that end whatever end point just that some people may reach faster than others because they've tried something that's working better for them but eventually everybody will catch up

You know because we are both in Silicon Valley I wonder do you think we're in a bubble right now?

In the Silicon Valley technically yes I think there is a little bit of higher confidence or higher anybody you talk to I don't know anybody in Silicon Valley who would consider themselves pessimist for AI right so Silicon Valley always has been on the leading edge that means we believe in things even before it becomes real right certain things that's how Silicon Valley evolved like all these companies that have come over 30 years the companies that I've seen come and gone they all believed in something they built something they made it big and then if they kept experimenting then they've gotten better right so the apples of the world have continue Google's will continue to evolve and become better than that.

So I think yes in that sense we are a bubble because we're always challenging the status quo. The so most important thing again is same thing what works in Silicon Valley may not work for the rest of the world. So you have to be able to try out solutions that work in other places too right? So if you build something that works in for companies in tech in Silicon Valley you may want to try it out and see whether it works for companies that are in Midwest for a for a company that is not tech first and see whether the same solution is able to work for them. So that's my that's my take on being in the Silicon.

It's interesting. My last guest actually have a question for you and he didn't know it's going to be you but I'll ask the question because I think it's relevant. He wants to know do you know how many AI agents do you have in your organization?

My IT wants to know so that they can put they can put some guardrails around. It's like I'm sure there are hundreds of AI agents that are that are there like even I myself run a few AI agents on my machine which are doing different things. So each one has their own threshold. So it's very hard to give me a give a number. Ideally the number of AI agents should be more than the number of employees in the right. That's what we saying at some point we the number of AI agents will be a lot more. That means everybody has a digital AI worker that's working for you or more than one digital AI worker that's working for you. That means that we should be able to leverage the power of AI to do the work for you, right?

You know, the interesting thing is as a as a company leader, you kind of know how many employees you have in your organization roughly or you can look it up. My last guest is doing auditability, observability on AI agents. So that's why he asked that question. Do you think this is just a matter of time that we would we would treat AI agents just like how we treat our employees? So they're going to have their IDs and we'll know how many of them we have and how they cut on everything.

It is exactly I think that is exactly where we're going because we want to it's more than anything it's mostly to make sure that they're doing the right thing, right? We don't want any rogue AI agents. We don't want any AI agents that are doing I know IT has access to the information of how many AI agents are running. We do have a little bit of observability in place just that I'm not the IT guy so I don't see that data but IT sees a lot of that. Because anything anytime you're using some of these AI tools it goes through our SSO that means that it's getting locked somewhere that we know exactly who is using AI where right so we do have that information are we putting checks around like what should you do and not do yes the larger the corporate there are some checks to say you cannot access certain tools we only give you access certain other tools so there is a little bit of balancing that happens but it is important that they will be similar to humans the non-human AI agents is getting, the number of non-human AI agents is growing.

So naturally as a company they should be able to say oh I have x number of non-human agents and they're doing x y and z. Similar to having a company to say I have we have 4,500 employees out of which x number of people are in engineering x number of people in HR x number of people in finance. Similarly you should be able to classify and say I have x number of non-human AI agents doing these functions. Some working in IT some working in HR some working in finance and doing different things. And that way you can like you can turn off access to employees when they go away. Similarly, you should be able to turn off turn on and off access to these AI agents too. Depending on what they are doing and what they are not doing. So this is where the technology is evolving to make sure that you have visibility you're monitoring and you have control over those actions. That way if something goes wrong, you're able to turn everything off, right? So this is where all the technologies that are being built are evolving towards.

Yeah, it's it's definitely scary. It's it's almost feels like the digital agents, the digital employees can actually become, you know, everywhere in our in our daily life. It's in a sense sci-fi and in a sense scary.

That's why that's why it's important important to you cannot just deploy any agents any everything should be backed by proper authentication and authorization. That means you cannot set up any agent which does not have access controls which does not have role-based access. That way you ensure that it's limited by the powers of what it can do. You don't want to have an agent which has superpowers and does anything it wants. Right? You want agents that if you're act you're creating an agent for yourself, the agent should have similar powers or limited powers. It cannot have superpowers because you don't want to give that. Yeah. So that's where that's where the companies have to manage their IT controls really well. The there's a lot more work for our infosec teams and IT teams within the companies right now because they're constantly looking at oh what is what is somebody doing that they're not supposed to be

Yeah that's that calls back to earlier what we were discussing the adoption curve this year we're making mistakes like open call right these we're seeing those and then we're fixing those along the way so

Exactly exactly yeah exactly that's where we are right now we're making all those mistakes and we're finding those mistakes are expensive and we're fixing them along the Okay. And it's going to go through that cycle and in a matter of months and years, it's going to get better and then it's going to get more content. You're going to get lot more content.

Okay. I close every conversation with this. If you could recommend me and my audience and your audience to a book, what would that be?

Yeah. So, I've been reading a lot of books, but I think this one book which is which is interesting. Again, it came out a little a year back. It's called Co-Intelligence by Ethan Mollick. I don't know whether you've heard of it. You heard of it. It's like living and working with AI. And that is where Ethan talks about he's from Wharton. He talks about how AI framing of AI is not just another technology but something that we increasingly work alongside and that's what we're seeing right now right all the agents that are building is working you're working alongside those agents and we just talked about all these new the digital AI workers that are doing your work. So the key thing is always invite AI to your table, right? Use it for everything that you everything that you want to use for and learn to know its limits. Be the human in the loop so that you can you don't blindly trust its output.

Always review it and then treat AI like a person. That means give it a persona, give it a background, give it a constraint to get the best results and assume that this is the worst AI that we'll ever use. That means that technology is getting exponentially better. So build habits that will make you change how you're doing what you're doing. So don't just believe that okay this is the best AI it's going to get better. So be ready to change.

Thank you Murali so much for the conversation. It's really fun to chat with you and understanding what you're building and things you said that really resonate with like the looking for challenges right is the right way of moving forward. Just not thinking we shouldn't be maybe thinking about how to become irreplaceable even though it's in our head, right? But because because this ongoing anxiety of there's no more job security. So as engineers and the builders, it's in our head or maybe this is true for everybody, but you talked about how you're adapting to this day and age on organizing and structuring not just your product but also your teams and you are sharing that intelligence and insight with us as well. How we should become more adaptable to this day and age and make us more not maybe not irreplaceable but more adaptive and more comfortable. I mean in this time