Is your AI strategy built for speed or stability? | Qodo’s Itamar Friedman

0:05Welcome to Dev Interrupted. I'm your host, Andrew Ziegler. And today, we have a special guest with us because my normal co-host, Ben, isn't joining us for today's news segment. But instead, I brought along one of my close friends in the DevRel world. I'd like to introduce you to my pal, Rizal. Rizal, why don't you introduce yourself to our listeners? Hey, y 'all. Like you said, my name is Rizal, and I'm a tech lead at Block, focused on open source, particularly focused on an AI agent slash MCP client called Goose. Um, and I'm so happy you have me here. Oh, we're excited to have you here. We talk a lot about Goose on Dev Interrupted.

0:44That's not the first time our listeners have heard. So definitely be sure to check out Rizelle's work after you listen to this podcast. Rizelle's publishing stuff constantly on Goose, and I'm learning from her all the time. But today, Rizelle is locked in with me. We're doing the news segment together. So we're going to cover some of this week's news. We're going to go ahead and dive in, Rizelle, okay? I'm ready. All right. So first up, we're talking about the acquisition of Windsurf. This is an interesting saga that hit the news in the last week about the next chapter of Windsurf. And this comes after Windsurf acquisition, as you might have recently heard.

1:23They were going to get purchased. But then there was like a second purchase. There was another agreement. And to be honest, Rizal, I had a hard time following this news story in terms of who got what from WindSurf and what was left and what's the deal. So what's your read on this? Yeah, first of all, like you, I'm confused because I didn't. First off, WindSurf is a hot commodity. First, I remember Microsoft or OpenAI wanted them. Then Microsoft came in and was like, nah, I don't know about that. And then we got Google. Google, I heard that they got they acquired them. And then this week they're talking about cognition got them.

2:03So I'm very confused on like who got what. And this is just not like the traditional type of acquisition. I'm wondering if more acquisitions will look like this in the future, too. Yeah, I kind of think it's becoming the norm of like you get this talent that's acquired. We're going to talk a little bit more about talent acquisition later. There's a new segment on that as well. But there's there's just something to be said here about the like founders and these early product leaders like getting acquired or like more like an acquire, right? From these larger companies who want their brains of how they organized and built this application.

2:36Some cases you see them immediately turn around and leave or then go to another organization. It becomes this new norm where people are kind of ping-ponging between these huge players and the tech world. And so this Windsurf, this Windsurf acquisition by Cognition, who you may recognize as creating Devon, you know, that's going to be an interesting new chapter in terms of how they're going to combine. Devon itself is a loaded brand name in like AI agents and AI code review in general. So I think that they're probably going to get a lot of mileage out of the Windsurf name in IP. That was probably a huge part of the acquisition.

3:12But definitely go check out the LinkedIn video from the founders talking about together. We're going to make sure that gets linked for y 'all. We'd love to hear what you think because I'm kind of left scratching my head a little bit like Rizal. And like you just said, But I do think it'll kind of impact Devin's brand because I think Devin's real enterprise-y right now and Winsurf is less so. Yeah, I think it'll be interesting to see how they kind of mold together. So diving into this next article, this is a note from a past guest on Devin's Rupted, someone that we know and love very much here, Brigida Boakler at ThoughtWorks.

3:44And she has been covering how teams are working with agentic AI. There's another article from her on this topic, and it's called, I Still Care About the Code. And I loved this article, and that's why I'm definitely going to include it in our show notes and why we're talking about it now. Ever since, you know, Coding Assistant kind of came on the scene, there's a lot of people that have been saying, like, oh, since AI can generate it for me, like, you know, I don't really care about the code anymore. But Brigitte takes a really strong stance on why caring about that code matters more than ever.

4:16and what it really means to care about that code, what that means from beginning to end in creating it, but also understanding the purpose of it. This is like a really salient article. It's not super long. It captures the idea perfectly. So I really recommend you check it out. Rizal, what do you think of this one? Yeah, I loved it, especially the part where she called out being on call. When you're on call, you got to move fast. You want to be a responsible developer and solve these problems. Sometimes just relying on AI alone isn't the best idea. I've always been an advocate for if you're going to vibe code, do it responsibly.

4:55Use version control. Still use critical thinking. Just because we're using AI to code or any type of AI-assisted coding doesn't mean we just shut off our brains and just let AI do all of it. I couldn't agree more. It's like by carrying out the code, you build your domain expertise in it. and you can also both of those existences can can coexist you can not create all of the code and still care about it because you can care about the intentions of the code and where that code came from so i think that's a really important distinction and one that brigida draws here so be sure to check this out and moving on now to our next article uh so this is an interesting one i'm gonna just i'm as a result i'm just gonna read the title and i think it's gonna pretty much summarize for everyone what happened here and then we're going to talk about it.

5:43So here's the title from Wired. McDonald's AI hiring bot exposed millions of applicants data to hackers who tried the password one, two, three, four, five, six. There's so much to unpack. There's so much to unpack. So first off, this is like whoever whoever mastercrafted this title over at Wired. Bravo. This is a great one. So let's unpack the beginning. So McDonald's has an AI hiring bot. This is interesting. You actually read a lot of stories about their hiring bot independent of this article and how frustrating applicants have found it for actually applying for jobs because it creates a barrier for folks trying to get hired at any McDonald's location.

6:28So that's an interesting use case of AI that I'm not sure has been a lot of success. Now, on top of this, the AI hiring bot, having collected all of those applicants, it seems like there's a hacker that was able to access it by just using the password 123456. So someone, unfortunately, on the McDonald's team deployed this system and left an insecure password on it. So it became a perfect storm. We're talking about McDonald's, one of the largest employers of people in the United States. It's one of the biggest, in fact, one of the biggest fast food chains on the globe. I would say that if you think of fast food, McDonald's is one of the first that come to mind.

7:04So this is a big problem for them because they have a lot of people's data. And so they could be culpable for a lot here. Rizal, what do you think of this one? Yeah, I'm concerned. Why are we making passwords be 123456? like this is like like basic knowledge that even if you're not a developer you know this is not like a secure pattern that you should do like the everyday person knows this as well and i am concerned about like what data do they have like you said this is a global company there's mcdonald's in jamaica in japan and like is it good too oh my gosh do the hackers have that information too like oh my gosh like i there's definitely maybe somewhere to learn about how widespread this is, but this is just a good reminder to everybody to use a secure password and follow best practices for your password.

7:57That practice will never, ever go out of style. Well, until we become totally passwordless, but until then, you know, buckle up. Yeah. Until we have that. Until we have that. So moving on to our next story here. All I can do is start this one with a sigh. So For the last several weeks, we've been covering this saga, this absolute epic here on Dev Interrupted about AI leaders poaching talent from each other. And we're not talking about, oh, you hire the product leader or you hire whatever. We're talking about ripping out entire heads of labs and entire established machine learning teams within some of the largest companies in tech.

8:40And this has been happening between Meta and OpenAI and Apple and Google, really anybody who has access to huge amounts of capital and has a huge need and incentive to build AI as fast as possible with the brightest minds on the planet. And here at Dev Interrupted, it's exhausting to cover what happens on all of these poaching wars from week to week. Folks who tune in, they know this from me. What are they going to get this week? They're going to get another news segment on the AI poaching war. So here we go. A meta has taken another AI talent. This is from OpenAI. They've actually taken two lead researchers now from OpenAI.

9:19So I think now if we were to tally it, that takes the number of scientists taken from OpenAI by Meta to 10 at least. And we're talking about million-dollar compensation and signing bonuses to bring all of them over. So this is another interesting development in the superintelligence labs coming from Meta. Rizal, have you been following this story? What's your take on it? my take on it jokingly is hire me i'm available for a million oh you're so right what am i doing poach me guys poach me poach me yeah poach us poach us rizal and i rizal and i will split the salary even we're cheaper yeah we're cheaper we'll we'll take it uh gladly divide and conquer on that one so mark hit us up i know you're listening mark because like you're i know you're tuning in.

10:12He's still doing this podcast. But yeah, so it's like this has been going on for weeks now. You've been seeing it, right? Yeah, I have. I have. And on a serious note, I'm curious on like, has this really been benefiting them as much or is it really like maybe like more of like a scare tactic for other companies? Like, yeah, we got the best. Get your get your stuff together. I don't know. I'm curious of the mentality. Oh, no, that's a great way of striking. And in fact, there's a lot of emotion involved in these conversations. When I read these articles that have quotes from these founders, they use language along the lines of being robbed.

10:50And one of them even used the terminology, it's like someone came into our home. And so there's definitely very personal feelings, I think, between these AI company leaders about the acquisitions of these hires from right underneath each other. I do think that because of that, there's some level of intimidation involved. When we think of AI and the hyper-scaling wars and all these companies trying to get as big as possible and how much capital it takes to do that, you want to be the loudest drum and you want to be beating the hardest. And so it makes sense that they're going to, you know, between these leaders in this space, there might be a lot of like posturing and like kind of mental games going on with these aqua hires, right?

11:32It's kind of crazy. but I do think that there's something to your to your hypothesis there I'm curious to see the end result and when will they stop hiring I don't know hopefully not before they hire us hopefully we scoot in there and then when we come back next time people tune in it would be Ben doing this new segment he can cover the AI poaching wars and he can talk about how we got acquired

12:00that'd be great and don't worry listeners we would bring you along for the ride as well. And, you know, before we start wrapping up our news segment, this has been a lot of fun. We're going to have more of these like this where we bring in other folks to share their opinions on the news. But before we move on a little bit, I just wanted to plug something happening at the end of the month. You see my friend Rizelle here. She is the host of The Great Goose Off, which if you've not watched it, is one of the best new emerging game shows for engineers. Not like it's a vibrant category, but she's definitely dominating it.

12:31And so on the great Goose Off, you have folks go head to head using Goose Coding Agent on wacky projects on a real time live stream. It's a totally fun experience. And Rizal, why don't you tell us a little bit about it? Yeah, I mean, you really described it well. The next one that people should tune in, we'll have you on July 29th. But I basically have two people going head to head and I'll tell them something crazy like build a login form that you can't log into. and we'll see who can make the most chaotic. Yeah. Okay, so you're going to break my brain is what I'm hearing. So definitely be tuning into that.

13:11That'll be at the end of the month. I will make sure the link gets included so that y 'all can go check it out. Now that I've had Rizal here for a news segment, now she's going to put me to the test in a live vibe coding challenge. So be sure to come check it out. It's going to be a ton of fun. And let us know as well what you thought about today's news segment so we can be doing more like these. And now that we're coming towards the end of our new segment, I do want to intro our upcoming guest. I'm going to be sitting down with Edomar Friedman of Codo. We're going to be talking about how you can tailor your team's AI strategy.

13:43Whether you're a fast-moving startup or a high-stakes enterprise, we're going to talk about what it means to go from vibe coding to grounded coding to building structured workflows and beyond. So this is a little more of a technical dive about how to reinvent your engineering team in the world of AI. Be sure to stick around for a listen.

14:04What if you could cut code migration time in half, just like Google did? Discover how Google used AI to automate 75 % of their migration changes recently, boosting developer productivity by 50%. Our DevEx guide to AI-driven software development breaks down Google's real-world strategy and gives you the frameworks to adopt AI thoughtfully across your SDLC. Don't settle for the hype. Learn how to do it the best. Download the guide today and lead your team into the future of AI-powered development. Boy, I'm really excited, Itamar, to have you here today because, you know, you have so much insight on how technology is evolving right now and how teams are using AI.

14:48And for our listeners, you know, Itamar Friedman, he's the co-founder and CEO of Kodo. It's a company tackling AI-driven been software development, and it's tackling it heads on. Itamar works with teams that are figuring out these challenges in our industry right now, and what separates an engineering team that thrives with AI from those that are just kind of experimenting with it. As a guest, Itamar has been on Dev Interrupted before, and has actually talked about AI back before, and a lot of people on here were talking about AI. So we're kind of revisiting a source of some of initial thoughts that we had on the show.

15:21And specifically, we're talking about how teams are transforming how they work to build high-quality software that is safe and reliable and scales. So Itamar, welcome back to the show. It's really a pleasure to come back here. Really high-quality episodes, and it's also fun. I like the way you conduct the discussion. Thank you for having me here. Amazing. I love to hear that. Thank you. Well, I look forward to having a blast with you today. And we're going to kick things off with, I like to kind of ask this of folks who come going to talk about AI, kind of like setting the stage initially about how teams right now are actually implementing these tools because everyone is under some sort of mandate or pressure to start implementing them.

16:03But that looks different for everybody. And to kick things off, what would you say is the minimum bar for a team to say, you know, we're using AI effectively right now? I don't want to complicate my answer, but I do think it's important to put it on a table that there's a very big difference between a startup with a team of three people like a company with 200 developers which for some might sound like a lot for some it will be small and with a fortune 500 with 10 000 developers like there's so many different things about what matters there what is the cost of a mistake for example probably the cost of moving slow is much bigger for the team of three people, rather the cost of, sorry, f***ing up, if you're a bank, is really, really high.

16:54So I think that also leads to the manager's or even the developer's decision on, for example, what to adopt first and what to adopt second, and how do they measure success of actually implementing AI, etc. For example, let's say that one AI tool will help you write much more code faster. Let's say that there is a metric for that. Let's assume that there are going to be the same amount of bugs per line of code. So it means that you're going to also get much more bugs, right? So, but still, if you're a small startup or a beginning startup, you want to just move faster. I'll move fast and break things.

17:36And the first thing you probably want to see is like, let's say speed. I'm intentionally not using the word velocity for a second. Like you just want to see that you're moving really fast. Probably also vide coding like actually works pretty well for you. If you are like an enterprise, for example, then what you want to see successfully happening, in my opinion, is untangling bottlenecks. That's so different than what I just said on the first part. Like, it could be that your bottleneck is how quickly you write your code. But it might not be. I just came back. I really apologize. I'm going to say it in front of everyone.

18:20And I was like three minutes late to this meeting because I talked to someone that he pitched me. He has like hundreds of developers that actually senior developers care very little about writing code. That's almost easy for them. What they care about is thinking about the right engineering and the right best practices and how to do things right. And then actually how to use AI to do that is a question. But I think like if you ask me how people these days that are thoughtful looking on it is basically via the bottleneck. Where is my bottleneck that I can entangle? So splitting it then into two camps of you have, you know, teams that maybe just care more about that speed aspect.

19:02And then teams that worry about the bottlenecks and the engineering complexity of what they're working on. and understanding that their needs for starting with a tool like AI are very different. What are some ways that teams can identify where they fall on that spectrum and help identify what actions they should take? Is it just based on size or is it based upon the complex, like your industry? Are those like the main ones that you're alluding to? So the reason I didn't use speed before where I said that startups want speed is because I think you can find something in common between all of them.

19:42Everyone wants velocity. But the difference between velocity and speed is that velocity has a direction. And I think it's a really good question to ask what velocity means for you. For example, how to measure it could be how quickly am I releasing features. okay for others how quickly i'm releasing features and i'm not creating tech depth how quickly i'm releasing features without additions of bugs and issues for others it could be how quickly i'm doing new frameworks versioning or how quickly i respond to rca like to root code analysis or you know so like like basically i think like the first thing to think of is what's most important for me as a dev team, what's expected.

20:34I think for everyone, like it's maximum value and minimum time. But this is like so generic. It is, I think, the most generic framework for engineering, maximum value, minimum time. But then you have to think, what is the value expected for me? And it will be different. And I think there is correlation between how big is the business and how much risk it could suffer and then there's collation to how many developers but that's the first thing like meta a meta facebook i think even when they were big like relatively big uh i think they still had this motto move fast and break things and they even had some accidents quite a lot like just a few years ago and they were already huge right while if you're a spacex for example you probably are not advocating for move fast and break things.

21:29Also, again, not if you're a bank. So I think that differentiation is more like, I do agree with what you say. That's like, what's your application? And I don't want to bash, like say anything wrong about anyone. So please take what I'm thinking with a grain of salt. But I did hear from a company, very known company in the observability, cloud observability. They said, Hey, if we're 15 minutes down, it's okay. Right. It might sound wrong because, hey, observability helps others not to have that downtime. But if they have the 15 minutes, they feel relatively OK. Well, if you ask a bank, are you OK with 15 minutes downtime?

22:07Just an example, then not. OK, so extracting what's important for you and then you can point out what velocity means for you, what you need to think of. So once a team identifies this, you know, let's let's zoom in a bit on the playbook. There's lots of ways that teams can bring in AI to either increase their speed or to reduce bottlenecks. But along the way, how do you think teams are like, how should they best measure the impact of those things and prove it to their own organization? They're like, hey, we're implementing AI, not just because it's AI, but because it gives us this and this. How do you see successful leaders navigate that?

22:50yeah so look let's let's admit it i think in most cases right now or maybe in early 2025 late 2024 the main metric is look my developers are much happier they're asking for it etc i think that was true until just recently like early 2025 but i think like i'm not the only one saying what i'm what i said right now like think about your what what matters for you and then this is how you measure. And if you want me to be more specific, it could be, for example, time to close open PR and how many critical bugs are being introduced per PR retrospectively. How much of your work is repeatedly, the percentage of work that you're doing to fix bugs and issues.

23:41For example, you're starting a sprint, right? You're starting a sprint and now you have used, like let's say you're using the framework for story points. How many story points are taken to develop new features and how many are to fix bugs or refactor, et cetera. It takes some time. Sometimes it's hard to really map, but over time, if you observe it over a week to five, two, three, four months using ai tools you can be you are able to map these and then and then see if what you want to do is verify that you're developing a feature but in high quality that in addition to you will mix and match like a few of these metrics like how many features are how many prs and features are how many features are coming up and how fast it is from a jira ticket or figma until it's out and to the customers, but you also check, for example, how many, the percentage of user stories that are done on new features over time and not fixing bugs that are because of vibe coding or something like that.

24:45This is specific, but I do come back to my main point before that it's very important that you sit down and think you match those metrics because there could be quite a lot, those that are fitting what you define as velocity. Yeah, that's really great insight for those listening too, to know that like for larger companies and companies that are maybe in those more sensitive industries for sure, they want to be tracking and showing the success of this. And part of tracking and showing the success is, you know, getting everyone on board. You know, there's a saying like it takes a village to raise a child.

25:21And similarly, it takes a team to implement AI. And so, Itamar, in your opinion, who owns the success or failure of a rollout? And it obviously depends on the organization, but what are some typical patterns you see? I feel that we're already like 15 minutes or so into, and I didn't give like a futuristic prediction. So let me give you one, and then I'll connect it to your question. Perfect. Your question, okay? Yeah. So let's assume that in five years, I'm not saying if it will happen or not, just assume that in five years, we get to a point where agents are writing and reviewing and verifying most of our code.

26:07Who is going to be there at the dev organization? My guess, it's the dev platform team. They're the one, those that I see, it's not like that for all companies is like that, but the majority of that, like the organization that gets the responsibility to implement AI, like you said, take a village, take a team, that gets the ownership of implementing AI is the dev platform team. In some smaller companies, it could be just one or two, three, five people. In some organizations, it could be five, 10, 15 or more. It's actually a growing department because of what I'm seeing. Like in some companies we've seen, like it grew in one year from five to 25 in a big company of 10 ,000 developers.

26:57So back to my point, like I claim that that organization is going to be the zookeeper, if you like, or the agent keeper, the manager of all those agents. They are going to be in charge of steering, verifying, approving. I'm talking about like, not necessarily just the targets actually credentials and things like that. In addition to steering other things, I just wanted to give that as an example. So assuming that's the future, and maybe you can claim that only they will exist in five years from now. There's just not going to be five people, there's going to be much more. I actually see this already, signs of it happening right now.