Claire Bell: People are skeptical that large established, highly technical, highly capable engineering organizations can deploy AI at scale and get any effect. But I think you've proven it's possible.

Chintan Turakhia: It's not only possible, it's adapt or die. It's just been such a huge superpower for the team.

Claire Bell: How many engineers are we talking about here?

Chintan Turakhia: A thousand plus.

Claire Bell: So we're not messing around here.

Chintan Turakhia: The company tried to adopt other AI tools and we saw this uptick in adoption. People opened it up, checked the box, did kind of like a hello world thing, but it didn't stick. My biggest thing is, how do I make this damn thing stick? Because there's something here.

Claire Bell: I do think that it's really important when you're doing this organizational transformation that you have a single person with incredible conviction at the leadership level who is also hands on the metal.

Chintan Turakhia: Show the engineers, not just tell. And the worst thing any leader could do is just be like, I decree you must use AI. Come on, no one's going to listen to you.

Claire Bell: Welcome back to How I AI. I'm Claire Bell, product leader and AI obsessive here on a mission to help you build better with these new tools. Today we have Chinten Therakia, senior director of engineering at Coinbase. And he's going to show us, yes, it is possible to drive AI adoption and higher velocity in an engineering organization of thousands of engineers. He's also going to show us the new expectations for engineering managers and engineering leaders, which is less meetings and more code. Let's get to it. This episode is brought to you by Work OS. AI has already changed how we work. Tools are helping teams write better code, analyze customer data, and even handle support tickets automatically. But there's a catch. These tools only work well when they have deep access to company systems. Your co-pilot needs to see your entire codebase. Your chatbot needs to search across internal docs. And for enterprise buyers, that raises serious security concerns. That's why these apps face intense IT scrutiny from day one. To pass, they need secure authentication, access controls, audit logs, the whole suite of enterprise features. Building all that from scratch, it's a massive lift. That's where Work OS comes in. Work OS gives you drop-in APIs for enterprise features so your app can become enterprise ready and scale up market faster. Think of it like Stripe for enterprise features. OpenAI, Perplexity, and Cursor are already using Work OS to move faster and meet enterprise demands. Join them and hundreds of other industry leaders at workos.com. Start building today. Chinton, thank you so much for joining. What I love about what we're going to talk about today is we spend so much time talking about the individual vibe coder or the non-technical person becoming a software engineer and still people are skeptical that large established highly technical, highly capable engineering organizations can deploy AI at scale and get any effect. There's still so much skepticism, but I think you've proven it's possible and you're hopefully going to show us the way.

Chintan Turakhia: I I think it's uh not only possible, it's, you know, adapt or die. Um like it it's uh it's just been such a huge superpower for the team and we've gotten so much efficiency out it and and there's just like ways to approach it. Um, I was I think I was reading a tweet yesterday uh just about a very very long story at Microsoft and or someone like pulling co-pilot in to their organization and it was like just a fun tweet of just like yep we're going to make graph go up and to the right but like the actual adoption wasn't good and and so like I've been spending the last year just absolutely obsessing about it and you can do it people can do it. So, how how can you do it? Because, you know, how many engineers are we we talking about here?

Claire Bell: A thousand plus.

Chintan Turakhia: Yeah. So, we're not we're not messing around here. This is messing around. This is a real this is a real team working on real products who know what they're doing, who have built great software. And so, where did you start either culturally, from a product perspective, from a tools perspective?

Chintan Turakhia: So, I think a lot of it actually just started around this time last year. um we had some changes uh to align like the product I'm responsible for and a big part of that was effectively like rewriting the entire product from scratch uh from uh turning it from a self-custody wallet to actually a social consumer app that just happens to use crypto and you know we're using React Native um but we made a lot of decisions for a self-custody wallet but to become a consumer app you got to like rethink everything that was one, two, we needed to do it in like 6 to9 months. So, we were going headto-head with like the big social players out there that have multi,000 person teams uh that have a 10-year head start. And we were really trying to just do something big and new and crazy, like absolutely just crazy. And and uh a big part of this is like how do we rewrite the app so that it is the best possible app out there like consumer grade and do it in this insane timeline. And the team is cracked. They're amazing. But like you know we we be we became a smaller team as a result of of some of these changes. And so I started just looking at like ways to accelerate and and you know like I don't know my my team knows me well and if if you know me like I obsess about efficiency uh and I think that's like so critical to like make teams accelerate their velocity um but in in in ways that make sense uh for tool and using the tool so around this time I think cursor had come out with their sort of initial release it was around like November of last year we we all tried it right 2020 24 and it kind of sucked. And it it's not like I love cursor. I love cursor. Uh the models weren't there. The just the models weren't there. Like they the models couldn't even you know really write a unit test. Right. Well, and you know you're an engineer. Um and you understand like once once an engineer tries a tool and and they're like h this is not so good like it's very quickly and very easy to write it off, right? It happens. And so we we kind of went through this like trough of sorrow of just like okay god damn it AI tools are not here the models aren't ready what are we going to do and you know for even a year prior to this event like the company tried to adopt other AI tools like GitHub copilot and we saw this like uptick in adoption like people opened it up checked the box did kind of like a hello world thing but it didn't stick, right? And and like my my biggest thing is how do I make this damn thing stick, right? Because there's something here, right? And my mental model was just always the models will the foundational LLM will always get better and it's like going to the gym. You need to go and build your reps and try it and that's okay. And the cost of doing it is like nothing. It's just a little bit of waste of time. We're not worried about compute right now because it's so early. And so like from basically January all the way to like March or April of 2025, I just changed the the mindset and the mentality. I I was like in cursor every single day, every single hour of the day. And I was like, how do I make this work, right? Like you know, it was great because I was writing code again. It was great because you know it was unlocking all these like use cases like we were doing interviews like interviewing candidates and and just like I don't want to necessarily write up all the notes right that takes a long time but I intuitively I like I know I've assessed right so I would use it for like tactical day-to-day paperwork kind of things to accelerate me uh but also from like a coding perspective just pick up bugs and be like hey let's try this right what's going to happen what can I learn what are the tips and tricks to like show the engineers, not just tell. And the worst thing any leader could do is just be like, I decree you must use AI. Like come on, no one's going to listen to you. I have to empathize with this because I also running a large like multiund person engineering organization you know was experiencing even early versions of these tools and had such innate conviction

Claire Bell: that it would of course transform how we did work like that was very obvious to me I don't know it's obvious because of experience or obvious because it was just obvious but

Chintan Turakhia: but then you know you just had these experiences as leaders especially in the you know maybe 12 months ago, one engineer tries it, doesn't work. It's not just that engineer throws it away. It's everybody else says, "Well, I think, you know, I trust their opinion and if they say it's not going to work,

Claire Bell: it's not going to work for me." And I do think that it's really important when you're doing this organizational transformation that you have a single person with incredible conviction at the leadership level who is also hands on the metal. Because until you can say, "Well, I understand it didn't work for that, but it worked for these three things." Or I actually figured out how to make it work for that because we tried A, B, and C. I think it's just the only way. You cannot be in philosophy. You cannot be in, you know, someday in the future you figure it out. You have to actually get back to it. And then I think like bonus points, so many of us in engineering leadership have like been pushed away from from coding.

Chintan Turakhia: I know. I have to get back in it. And I'm like, I just want to code again. Like, give me some joy. Give me some time.

Claire Bell: Yeah. And so I think that's a benefit as well.

Chintan Turakhia: And you you have to show not tell. And and so I did. And like I think what I learned very quickly is like, okay, there's something here. There's there's a there, right? And then we just started picking off like one or two use cases and and the best way to get to an engineer is just give them the tools so they stop doing the work and so that they can build the stuff they love. Right. Right. And so like we would just like pick off unit tests. We'd pick off like linting, all these like little things that just like paper cut and suck the soul out of you as a builder, but the engineers and you know like the team just wants to move faster. The team wants to build better things. And so we started leaning into like cursor rules for some of these things. Even the simplest thing I I remember like I think I remember my aha moment which was like popping in some bug report working through it and then I didn't think about it. I just did it. I was like just create a draft PR. Here's the ticket. Here's kind of the PR like and you know here's the PR description I want. And I just did it and I was like I never need to remember get status get rebase. Like why is anyone doing this anymore? like what are we doing? And it took the funny thing is it took some convincing of me to the the team like guys just type create draft a PR like create a draft PR and it'll be done for you and like like well you know I kind of have my workflow. It's like cool cool I get your workflow you can modify you can use cursor rules it's okay.

Claire Bell: Like no one's getting bonus points for memorizing git commands.

Chintan Turakhia: Exactly. Exactly. And and so like we chipped away and we put in a bunch of rules like cursor rules and that that helps so much. And then like we had I I was like sensing I was like okay I have I have enough like folks on the team that are like yep this is unlocking stuff. And they would post in the team channel like look what we had literally a channel called cursor wins. And like everyone was just posting in the channel like I just did like you know 20 unit tests and then went and had a coffee. This was great. like I love it. And so people started seeing it in action and then we hit this like point. I was like, "Okay, how do I speedrun now the whole team? There's a there's a little bit of conviction here." So I just and I remember this like I think I had landed I was going to the east coast. I landed um for my flight, got into an Uber, hopped on like an entire team all hands like speedrun we call it. It was like basically cursor speedrun. And I was in the Uber using cursor putting up a PR. And the goal of the speedrun was every single person would just pick up the most trivial thing. It could be like copy change, a bug, whatever, and just put up the PR. And we ended up, I think in 15 minutes, I think a 100 people had joined. In 15 minutes, we ended up putting up like 70 PRs. And we broke GitHub, too, which was cool because we learned like our infrastructure needed improvement. So I want to I want to pause real quick because again how I AI a little bit about tactical techniques and you've used a couple that I have used which is like one high conviction leader with hands on the metal that just says like we just got to do this access to tools focus on toil and is very important. You called out linting you called out tests. Another one I would call out is like design debt where you know front end engineers or designers have just lived with parts of the app they hate.

Chintan Turakhia: Yes. Um, that is another really great one. But and then and then a a shared Slack channel. And one like, you know, riff I would make on your cursor wins channel is we made ours wins and losses. And so we were very clear like just post what you did and when it worked and when it didn't

Claire Bell: because when it didn't, people would be like, "Oh yeah, but you could try XYZ or I have a cursor rule for you or whatever." But what I haven't heard that I want people to just like perk their ears on and pay attention to is this like idea of a PR speedrun which is like do a time down time everybody boot up whatever tool and just speedrun some fixes because how much conviction does an or have to get going from look I've been there like the the doldrums of like quarterly planning and this will be in four months and blah blah blah blah blah to just like we just got 70 PRs that we've sitting on out out the door in in 30 minutes. I just that has to be such a transformational moment for an edge team.

Chintan Turakhia: You know, there was a success rate on those on uh merging those PRs and like it was just like this is possible there like everyone's eyes lit up

Claire Bell: and it was really sort of a death to status updates long live building moment,

Chintan Turakhia: right?

Claire Bell: Yeah. And and this is the other thing I want to call out because I think you all have a really special culture there. But so often we in product engineering design orgs get like really wrapped around the axle on like the rules of engagement like well I'm not allowed to build it unless the product manager says it's important or like I can't really make that decision about what color that button is because design hasn't weighed in. And like I do think these moments where you just break all the rules and you're like guess what remember you can just

Chintan Turakhia: ship code. who can just

Claire Bell: you can just ship them both like put AI aside. AI maybe enables it and makes it like a much less costly you know um expense but like just doing that is so powerful for velocity and for I also think for quality like people just take more radical ownership of things. Um so I'm going to 100% steal this.

Chintan Turakhia: You I mean I want everyone to steal it like you know I I really like the way you just put it right. This is a moment where we should be breaking the rules because AI is breaking the rules for us and if we don't adapt to how like we can use it, we're toast, right? And and we is like a very collective like whoever's not adapting is going to fall behind kind of thing, right? And what all of this like ends up unlocking is is like the reduction in coordination overhead. So like one thing I've been obsessing about a lot, it's like, okay, cool, great, good job on the speedrun. Yes, we got a lot of stuff done. We started then seeing those wins more and more people adopted. Brian then, you know, you were sharing some information with Brian like how adoption is going and then we just did a companywide speedrun. And at that moment, like there were like 800 engineers on the call and we ended up pushing up for like 3 400 PRs in 30 minutes. And yes, again, we broke GitHub and that's fine. That's good. Like this is pressure testing. We should be designing ourselves to break the rules, right? But the thing I've been obsessing about is like how do you how do you measure any of this like in terms of output, right? There's there's this like tension where okay the more AI we use well does that count as a replacement for people and like I'm in the camp of absolutely not. AI is an accelerant, right? AI is an accelerant because there will always be more work to like to do, right? And so the way I think about it, at least for for my team and and what I'm pushing across the board is really like time from ticket to when the change lands to the user. Like that actually encompasses every single piece you need, right? And today like even if you go from like ticket backlogs and stuff like that, like there's oh do I should I like like you said, should I prioritize this? Is this important? Let me ask my PM or let me ask the pro the pro program product manager, project manager, whatever. And now the whole team like fast forward from back then to now, we just see someone give us feedback and literally within like seconds we're like clock like we built this internal bot. I'm excited to show you. And within seconds like the PR is being authored, right? an agent picks it up and within seconds that feedback is like acted on. And so we crunch the time to action, the time then from ticket to the the PR being ready for review. Then the review time like all my dubs complain review times take too long. We found some solutions actually. I think we were doing average of like 150 hours like was the cycle time for a PR review because there was so much. We reduced it by 10x down to like 15 hours or so roughly. And then the last piece is like from that merge, how do you do like that OTAA update and you squeeze that whole cycle again and then the team is like just literally unlocked with sheer velocity.

Claire Bell: Yeah.

Chintan Turakhia: And then you get stuff in front of customers. Yes.

Claire Bell: And then you have the velocity of like actual market ideas.

Chintan Turakhia: Yes. And you get that feedback and like the the we're obsessing also about how fast can we take like in real life feedback.

Claire Bell: Yeah.

Chintan Turakhia: And then actually just fix it right then and there. I think I think there was another aha moment. I was on a call with with like a user of our product, right? And they're like, "Hey, it'd be cool if you like changed X, Y, and Z." And like literally while I was on the call, I just put up a PR and pushed it. And they're like before the call ended, it was 30 minutes. I was like just you know reload it's fixed.

Claire Bell: Okay before we quer this into an hour of you know like two two end product leaders being like just ship really fast we'll go into the merits of reducing PR cycle time all that fun stuff. Let's actually show a couple things you built because I think the kind of meta commentary on like you can do this in engineering organizations. There are steps to it. There are measures you can take I think are things that everyone can learn from but you also have been building. So let's talk about how you used actually cursor to drive how you drove this into the organization and understand adoption of AI.

Chintan Turakhia: Yeah, for sure. Um, I think a lot of it just comes like from honest curiosity and figuring out um, where the bottlenecks are like why aren't folks adopting, how are people using it, etc., etc. I want to show you like I think the the kind of crazy thing I'm about to walk you through is like I just got this hairbrained idea. Cursor has like great analytics, right? And so you go to the admin panel, you look at the analytics and a you know awesomely they let you download it into CSV. I was like, what if I just use cursor to figure out what my team is doing in terms of using cursor but not in just like from a vanity metric point of view of like lines of code committed by AI. I think that's like kind of misleading actually digging more into um how they're using cursor and how do we sort of like replicate power users. So let's see uh we have some some data. It's in this file here. Uh, and it's just like a standard CSV from Cursor that you can like download from their their site. Um, like your admin panel. And then there's also here a bunch of different sort of fields. Um, so like accepted lines, chat lines, chat lines deleted, um, various like data elements. But you know, one thing like I just sort of started with I want to understand the usage of cursor, right?

Chintan Turakhia: And I already know um we have like light users all the way to power users. And one of the things I really wanted to figure out was like what are the natural clusters of usage? Can you find them across the team? What is the best way to cohort them?

Chintan Turakhia: Right? And I'm just going to pick up the standard analytics file here. Maybe pop in another one here. And then I love Opus High. I also love plan mode because it gives you a chance to like see what it's thinking through. So we can let this cook and see what it comes back with. And what I want to call out here for engineering managers or engineering leaders is this is the kind of quantitative analysis that we would all have loved to be able to do across a bunch of engineering metrics at at some point, right? Like how often do we get asked by the board or our boss like what's velocity, what cycle time, which of our engineers are super, you know, like our are really on the far edge of the curve in terms of efficiency, how are our junior engineers ramping into the repo, all that kind of stuff. And that kind of analysis is actually really ownorous and hard to get at because of the structure of the data and the nature of the analysis. And so what I love about just LLMs in general and in particular using something like cursor is you can get to really nuanced cohorting analysis on human behavior and human analytics as a manager in a way that I think has been really challenging to do before.

Claire Bell: Yeah, I totally agree. And like the beautiful thing is now with MCPs with data accessibility

Chintan Turakhia: like I think of tools like cursor as just my daily operating system. If I have a question, it doesn't matter if it's technical or not. I just go into cursor and ask it. Um, and so it's like super super powerful that way. Okay, so it's asking me a little bit about like what outputs do I want? I do want to enrich CSV. Um, just it makes it easier. I do want a static dashboard just for fun. Like I'm not really trying to create a brand new dashboard right now. But my main goal here is just honestly honestly like find natural cohorts, right? Um, and so it's going to kind of try to do light, moderate, active, power, super user. It's going to look at line suggested, so volume, sophistication, agent mode, model preference, acceptance rate, and breath. What features are they using? I'll spit out, you know, a CSV dashboard. It'll likely generate a Python script, too, that I can reuse. So, I'm just going to kick off build mode. While that's cooking, I do want to just maybe bop over to like it's going to create all this stuff in Python, create the scripts for me. Awesome. But we can look here at some of the the information, right? So like this is all sort of random made up data. It's like sample data. But what it did was in a previous run it looked at all the data, generated the Python script, which is great, super simple. And it sort of just did some like highlevel status metrics like AI code percentage again on all this madeup data, AI lines per week, composer lines. This is when you're using the agent mode in cursor or tab lines, right? When you're hitting tab. Uh one one of my team members actually got the cool cursor tab award, which is which is great. Great. And so it sort of breaks all this down. And then what it really segmented around was like agentheavy users, which is folks who really lean into agent usage. There's also tab heavy users. This is like a different cohort. they just lean into tab usage and they they maybe want really just a bit more control and maybe haven't gotten yet used to like how to let go with an agent. Uh you have balance users that try both and then you have sort of like maybe cursor curious or maybe not cursor pill or you know llm pled right now and so I generated this whole script. It's great. And now let me show you sort of a bit more analysis I want to do here. So let's do this. Run the analysis on I have um a sample user set and generate the HTML as well and let's we're actually like this is sort of the output of the analysis script that was generated in Python which is already cooking in parallel.

Claire Bell: Got it. So what you've done here is you've taken some raw data from cursor. you've asked one kind of agent to do a cohort-based analysis and generate a enriched CSV essentially with some data and then you're kicking off another agent to actually do the analysis on that and generate sort of an HTML view of it so you can visualize the data.

Chintan Turakhia: That's right. That's right. What it did was the Python script that was generated, right? It found these natural cohorts, these natural cohorts of super user, regular user, power user, light inactive. Again, this is just honestly sample data um but based on like real information, real schema, real cursor um data fields. And it came up with like 70% are agent heavy in the sample data, 20% are minimal, 4% are balanced. We have some room to improve here on the sample, right? Like not enough people are using it. Um, and so it does a bit of a breakdown which I kind of like, you know, kind of a recap of metrics. Yeah, we have a lot of lines of code in this data. We have 520 power users. Again, madeup names, but like this person is crushing it. I want to know what this madeup person, Gabriel Diaz, is doing, right? Awesome thing here. It generated a little uh visual dashboard. Nothing fancy. something just really simple to look at, right? Total lines, composer lines, tap completion, a little bit of breakdown, some structuring on the tiers and usage, right? But what I really kind of want to understand is like what is Gabriel Diaz doing, right? This madeup user who's just like crushing it.

Claire Bell: Yep. How about based on the data generate guidance for each user cohort what you know they should do to advance and graduate to super user I'm looking for explicit guidance effectively like I want to turn this into some type of playbook right so let's let this cook and then in parallel what I also want to do is I like visuals and there's something intuitive here where like as we look at the data itself

Claire Bell: right We we know that the like the path to this super user over here. It's it's not like you go inactive to light to regular to power to super. We know it's not linear like that. Right. Right. There may be like forks from light to straight to power user. Regular user seems to be like balanced on the taring, but what I want to know is like what are the special things these folks are doing and how do I sort of shift the curve, right? And so I'm also going to throw another question in parallel like create a mermaid diagram uh for all the different sort of paths a user can take from light to power. And it's I'm assuming it's not linear. And let's just see what this cooks up to. Okay. This is really working hard. Really working hard.

Chintan Turakhia: Opus 4 five.

Claire Bell: Yeah. Opus is Opus is really working hard on this. But um yeah, let's let's see where it goes. Well, you know what's really interesting? I'll give you a a a shorter hack on this one. So, I think what this is generating is like an HTML playbook that you could share out that has has things. I will tell you what I would do in this use case and I've done this a couple times um with c like customer QBRs is I say write a slack post that I can put in my engineering channel on a couple of these stats and you know how we can get people to move from A to B and it'll write me like a a short little Slack post. So, I I love this idea of going from something like a CSV to a really deep analysis to an HTML like visualization to like three bullet points I can send in Slack. Yeah.

Chintan Turakhia: And as a manager, each one of those steps would have taken just forever to do. And now you can get them all done in cursor.

Claire Bell: Yeah. You know, that is that's like kind of the awesome thing is the power of something like a workflow markdown file.

Chintan Turakhia: Yeah.

Chintan Turakhia: Is huge. It's absolutely huge. And it ex it's exactly like the thing you're describing here.

Claire Bell: Meet Rovo, your AI teammate, connecting knowledge, people, and workflows so teams can work smarter and move faster. It helps people find answers, make decisions, and automate work securely and with context through search, chat, agents, and studio. Rovo runs on the teamwork graph, Atlassian's intelligent layer that unifies data across your first and third party apps, so no knowledge gets left behind. And you always get personalized AI insights from day one. And the best news, it's already built into Jira Confluence and Jira Service Management paid subscriptions. So the power of Robo is already at your fingertips. Know the feeling when AI turns from tool to teammate? If you robo, you know. Discover Robo. AI that knows your business. Powered by Atlassian. Get started at rovo.com. That's rov as in victory o.com.

Chintan Turakhia: Let's see. Let's see what it came up with. Right. And like you know the the thing is like no one should expect all this information is going to be perfect. Like if anyone is thinking oh wow what is going to be my job as a leader if cursor can do all all of this it's like well your job as a leader is to lead right and to make change and and impact and this accelerates them so inactive users like yeah kind of true you haven't installed you haven't really used AI features yet the hardest part is getting started so I kind of like this it gives like just some very simple prompts try the agent mode for your next task something very very simple. Something like wait try a tab completion flow. I kind of feel like the the LLM really wanted to just turn this into a game like a little like a little quest or something.

Claire Bell: Yeah, it's gified a little bit.

Chintan Turakhia: Yeah, it is. It is a bit gified and it's kind of fun.

Claire Bell: All right, so this is cool. It's kind of given me like this would be my Slack post. TLDDR

Chintan Turakhia: 16x more AI line super users versus other users. Let me zoom in just a bit more. More agent requests for super users. I love this. Stop typing. Start shipping.

Claire Bell: It's dark mode, so the engineers will just love it.

Chintan Turakhia: Yes. Right. Um, it's kind of perfect. And then you installed cursor, but you haven't used AI yet. We talked about this. That's cool. Light mode. Okay. I, you know, this like resonates. Stop saying fix this bug. Actually like talk to it like you would maybe a junior engineer,

Claire Bell: right?

Chintan Turakhia: Um, cursor just did release bug bots. I love Bugbot.

Claire Bell: Cursor. I love I love Bugbot.

Chintan Turakhia: Agent isn't for heart stuff, it's for everything. These are like motivational quotes now, but I think like we should just make posters for and put them up on the wall. Um, write unit tests, actually read the comments. Okay, cool. Now, power users, you're good to be great, think bigger, and to have harder.

Claire Bell: Okay, there. If cursor is listening, I think this is like gonna be your new merch line, guys.

Chintan Turakhia: I need a hat that says tab harder.

Claire Bell: Yes. Okay. So, just to just to recap again, we're doing we're doing uh free free product work for cursor here. We we took you know your ultimate problem was like how do I drive up adoption in these tools? And you're like of course I'm going to use the tool to understand adoption and then figure out ways to drive drive adoption. We did analysis. We created a visualization of the um the data itself. You identified cohorts and power users which would have been very tedious to do if you were going to do manually.

Chintan Turakhia: Yeah.

Claire Bell: And then you created a hosted playbook. Um, as well as a series of motivational statements which we can either give to our friends at Cursor for free or trademark right now and make a little a little money. Um, agent everything tab without thinking bugbot always on iterate prompts. Love it.

Chintan Turakhia: And this, you know, again what I think is fun, let me talk about what I think is fun about this one.

Chintan Turakhia: Everybody who has been in engineering leadership knows this is the kind of stuff you get asked to put in a board meeting. You get asked by your boss like what percentage of our engineers are using cursor? Do we have power users? Are we actually getting value? And we're talking about an AI use case right now. But again across management there are actually measurable things you can do about the performance and efficiency of your team.

Claire Bell: Yes. And

Chintan Turakhia: I think it been so impossible to get before. Two, it would be no fun if you didn't get to do it with code, which you get to you get to do with code.

Claire Bell: Actually, that is solve problems with just code now, right? You can just do things. I I you know, you're so right. Like I I think this I underappreciated what exactly what you're saying right now and and I just want to repeat it because normally you would be asked this and then you would have to go pull an IC to do that and like what what

Chintan Turakhia: like come on like no you can just do things right now.

Claire Bell: Well and and again it's like not I I I think people underappreciate the velocity creation of a fun task.

Chintan Turakhia: Yeah. which is like at the end of the day like this is silly but also the like little fun bits of it you're like great I want to go to the next level cuz I got like a little dopamine hit from this dark mode playbook that's kind of funny and I I think people underappreciate like that iteration speed that can just come with like a fast feedback loop

Claire Bell: when you're building something and the fast feedback loop when you're building something that has high quality against it which like something designed like this does is so much more fun to look at than a Google doc. Yeah.

Chintan Turakhia: Or a spreadsheet or a dashboard. So, we we did it. We did it. We again, you and I are twin stars, I think, here. And so, we can probably go all day on the things that we find fun. But, let's go to a second use case that I think people are going to see. And let's see how fast we can do this use case, which is you were talking about the speed of feedback to feature. And you you said some fighting words out there. You're like, we're really compressing the time from feedback to feature. So, how does that actually work?

Chintan Turakhia: Those were those were some fighting words. Um, and you know, I think you know this, right? You want you want to build this for your users, right? And you want to create the best damn product out there as fast as possible. And the way to like make that cycle work really well is genuinely how fast you can move on feedback. Okay. But I want to start from how does like feedback even normally come in, right? So you you know normal like teams and and culturally like you'll have dog fooding or bug bash sessions, right? You'll get on a meet or get in a room, keep using the product, blah blah blah, all that jazz and then someone has to like collect the bugs in a Google doc and then take those bugs in a Google doc and put them into a ticket system, right?

Claire Bell: Uh okay. And then there's a whole discussion around is this important, is this not important? Okay, should we pick it up in this sprint? Should we wait for another sprint? And by that time, your user has turned out. They're like, you guys didn't fix this. I kind of hate it. Moving on, right? Everyone's attention is like so so so short. And right now, like the whole team, uh, we're all preparing for a big launch. Um and we wanted to get together and do this thing called a surge. And this is where we like just bring the team together and we do very very long days um using all this AI and just shipping like massive amounts of code. Uh and fun fact like during these surges we end up shipping like more than three to 4x more PR volume in the same time. But the other thing we wanted to do was bring people into the office and we set up this thing called like a feedback cafe. So we'd invite externals, internals, etc. And we dog food with them and we'd show them the app and like here's just like a couple seconds of, you know, what it looks like. We're just standing there collecting information doing all this like live dog fooding. And the hard part though is especially in real life. How do you actually capture that information? Because it's voice, it's video. How do you translate it into a system? Okay. So, I just spent like half a weekend and built a tool to capture feedback live. Let's just pick something. I'm gonna pick I'm gonna I'm gonna pick a new thing. How I AI testing with Claire.

Chintan Turakhia: Awesome. So, let's do that. It's going to create a little session. Perfect. Very simple. And we have two modes. You can like you can use this on your mobile phone. That's what the team did uh when they were in real life. But for this, I'm just going to like capture some audio. And let's see what's what's actually maybe I can just hear from you like a fun little bug or something uh of a product that you you think you want to fix. So we're going to start capturing audio.

Claire Bell: There is a AI chatbot that I use where my account when switched to business account forces me to clear all my chats. And I think we should fix that bug so that I can access my existing chats.

Chintan Turakhia: We're gonna start capturing audio. We're gonna Okay, cool. We captured it. It's basically taking the audio.

Claire Bell: I did a system prompt. Sends it to an LLM. Um, and then what we do is it the prompt is basically saying go and identify the bugs. Yep.

Chintan Turakhia: Right. And then it'll create it. I'm going to do one while it's processing.

Claire Bell: Right now, I'm using the app. I'm on the trade tab and I'm clicking the from field and I'm typing in numbers, but the numbers are not showing up. So that's not letting me make a trade. So I think in our first example, the audio is a little hard to capture through the system. But let's look at the second example.

Chintan Turakhia: It calls it out really clearly. On trade tab, typing into from field does not display enter numbers. User cannot initiate a trade. Cool. Really, really clean.

Claire Bell: Yep.

Chintan Turakhia: I hit create linear ticket. It even gives like a suggested title. The user journey I care about for this is trade. Boom. I create the ticket itself.

Chintan Turakhia: Awesome. I hop over. The ticket is all here. The file is there. Linear is a incredible tool. It's doing some triaging. But the thing I want to now hop over to is we're going to just create the PR. So we have this tool we built inhouse. We call it Cloudbot. It's actually like using all sorts of underlying models. Uh it's not something that is specific to to to Claude. Um, so Cloudbot create PR. I know the repo for this is wallet mobile. And here's the ticket.

Claire Bell: Oh, that's not the ticket.

Chintan Turakhia: The ticket is boom. Here. Great. Cool. So, I just went from a bug report to ticket

Claire Bell: to a PR

Chintan Turakhia: to the PR is cooking.

Claire Bell: Okay. So, I have to pause because if you um are new to how I AI, you have not seen my signature move when I really love something, which is this. And I was doing this because I was just thinking about this this little micro app that you have on the left side, which is, you know, live user feedback, totally unstructured, right? Video or audio. Run a little baby LLM on it. get not only a summary of the issue but a good recommendation on how you might fix it. Very quick beep boop to linear. We love our friends at linear. I think it's a great platform for agents. And then a little custom agent in your Slack that can read those linear tickets and just execute on them. And again so traumatized by the past maybe which is like this process would have been you know somebody manually summarizing

Chintan Turakhia: Yep.

Claire Bell: what came out of a research session. Y some document being written somebody actually making explicit decisions about what to include and not include. I think

Chintan Turakhia: the decision making is gone.

Claire Bell: Yeah.

Chintan Turakhia: Like no filter anymore. You don't get that like, well, you know, if I make this five pages long, no one's going to read it. So, I'm really going to focus on the top 10 things. It's like, let's capture everything and then just burn through it. And then I have to ask you, why did you all build your own little bot to do this? What was the advantage of of building the bot?

Chintan Turakhia: So, this this is like in-house. Um, and we built it, you know, it all started um around like middle of this year. I created this like I I was just obsessing so much about AI and I was like how do I how do I create better tooling for the team for the company so everyone can be accelerated. So I invented actually like I put a call out on Twitter I invented this role called superb builder and the single job single most important job of a superb builder is to create more superb builders. So we we hired our first superb builder and they um we we talked about some ideas and one of the biggest things because most of our company uses Slack. We're all in Slack and Slack, you know, I'm like strong believer it's just a bunch of humans pretending to be systems, right? And the cost of writing something in Slack is zero, but the cost of answering something in Slack is enormous and most of it is noise, right? And so one of the things was just like how do we bring the workflows that we are all so used to um and how do we like sort of capture that and then add AI on top of it. So we had like various reasons we know like lots of companies have background agents cursor etc etc. Uh we just have like different sort of security requirements right now that we just couldn't launch with it and that's fine. So we we built this in house and we have these like feedback channels, right? Hey, there's a bug here, there's a bug here. And so now all we just do is like cloudbot go and do something with that. Or if someone is um like, hey, we just got out of this meeting. Here's a summarized transcript. We're like, awesome at linear agent, go break this down into tickets. Then just like you know, you know the look you you showed like right like everyone is just doing that emoji of like the head exploding, right? Because then now we have like 20 tickets and then we do fun things like this which is just go like bonkers where we just fire off tons and tons of calls right to just and so we we built this plan mode. So, this bot has a create PR, which I'm it's cooking. Um, it has a and also the cool thing about create PR is when it's done, it will respond back, it will show you a link to like the cursor branch using cursors deep link. And when then the oneoff build is ready, it will show the QR code. So, you can just scan and start playing with the fix, right? There's a plan mode which is very much like cursors plan mode. It just comes up with like a plan. And then we also have um explain as well where it's like oh I want to debug something. So like um why is Chinten's app not working right now? Um Chintton.base. As an example, right? and it has like all the skills all the MCPS and so the thing the thing I realized is context is the most important thing. So the place where we capture all of our context is linear and then you this agent that we built um we added skills and MCPS. So if we can capture context through linear then we can trigger the agent uh using all the context from linear and then it goes off into all the MCPS like DataDog Sentry Amplitude um our internal Snowflake databases etc and it has the ability to pull context from the rest of the company and it can work across multiple code bases and then boom like it's it's like a it's a it's it's a superb builder.

Claire Bell: This is this is awesome. And so before we move move on, I think what I want to call it here are a couple things that I hope people didn't miss. One is right now if I can give people career advice.

Chintan Turakhia: You want to be like the the top three most AI pill in your engineering organization. I'm sorry. I just have to say it like I you know I whenever I you know pulled an engineering leader aside or someone aside who's like maybe a little AI skeptical and I said like I want you to lead this. I wasn't doing it. Yes, of course I want to do it because I think it has high impact on the company, but I felt like I was doing people a career favor by giving them this role. And so, if you can find companies that are hiring superb builders that will put you in the role of driving AI across an organization where you can learn these skills, I tell you it is a incredible benefit to your overall career. And I don't think people appreciate how much that is pretty still rare right now. So if you can find it, I would just beline directly directly to it. I think the other thing and we've seen this a couple times. We saw this Amplitude actually did it. Building your own agents is not impossible for organizations. And so if you do have security compliance, data access restrictions, you can't use cloud agents, you can't use these things, it is not impossible to build these things yourself. And there are lots of like really great SDKs out there too that you can use um to do so. And then you know three like I do think some of these platforms linear and slack are just friction reducers to access to AI. And so if you are thinking about driving AI adoption in your organization like figure out how you can get the right platforms in place that can unlock access to agents because if you ask somebody to open or learn a new tool it's just going to create too much friction um to to move forward. I think there's like one super important thing like this. This is a channel where we call Cloudbot Playground. And I'm scrolling through fast just to show you like how much people are using. This was one night. I was up at like 1:00 a.m. just pushing this. We got like 200 bugs, right, from this tool I showed you.

Claire Bell: And I just kicked them all off in like one solid go just to get things cooking. And like it was great. Uh let's see if a plan came out here. Yeah. So like there's a there's a plan that comes it actually creates the plan in the linear ticket.

Chintan Turakhia: Yep.

Claire Bell: This the trick here. Why Slack is because Slack is how things go viral within your company.

Chintan Turakhia: Totally.

Claire Bell: If you have pulled out the magic into some separate tool that others can't see.

Chintan Turakhia: Yep.

Claire Bell: It doesn't happen. And so by getting things into Slack, people just like, "Holy this is possible. Let's go. And it's like it's really cool.

Chintan Turakhia: I I completely agree. Okay. So, we have just seen about everything I wanted to see from the engineering side. But before we get out of here, I want you to spend just a couple minutes on a personal use case.

Chintan Turakhia: Okay, let's go. I I think the one that resonates probably for everyone is getting if you have kids, getting the school emails that it's like, oh, here are 50 events that are about to land. Uh here are the dates. I've just started taking a picture of it and then throw it into chat GPD and say create the calendar invites

Claire Bell: 100%.

Chintan Turakhia: Right. It's like it's the dumbest thing, but oh my god. And then the shared calendar dance happens and it's like it's so great. Another thing though, like I love food and wine. I really do. And like um I've done like Somalia training, etc., etc. And I and I realized like, you know, I went to New York recently with my one of my buddies. He's uh he's learning about AI, but he's like what what are some of the real use cases that would resonate with me? And I was like, well, like one of the biggest sort of anxieties people have is when they go to a restaurant, they're handed the wine menu, right? And they're like, what do I pick? What if I pick the wrong thing? So, uh, with my friend in New York, we went to some, uh, like champagne tasting. And so, like, I just took notes. There's like this whole notebook, right? I just did this like an hour ago. And I was like, "Oh, here's a great producer. Single star means like, yeah, it's good." And then here's another one. Oh, see I wrote amazing by like this is someone I've actually never tried before, but I loved loved their champagne. Let's see. It was just super yummy. Here's another one. Right. Effectively, then I just like popped this right in and I said, "Here are a bunch of champagnes that I tasted. Figure out from my notes like what are my taste preferences."

Chintan Turakhia: Really simple. Because you know like when I when I did like Somalia classes the biggest thing that it teaches you is the vocabulary to describe the stuff you like right and then so I just took the images it figured out the producers and this is actually like spoton the fun thing I did with my friend while I was in New York was like we were just he was he's he actually is the real life version of chat GPT and it's it's what inspired me to do this which is he's always trying to figure out my taste preferences and so you know this is like my strongest signal. I I love like these wines that have very little sugar that are like really ripering acidic. I love some aging. I love growers, right? Grower champagne, not like the big houses that are like very sweet. It even went into like a certain subcategory of like, you know, the chalky style. This is specific producer that I wrote amazing by for. And it also called out something I learned in real life, which is like I do like Pinoet, but only like with this sort of characteristic, right? Kind of crazy. All right, fine. And so then it came up with like a little bit of like a champagne profile.

Chintan Turakhia: Cool. And if I'm buying stuff, you know, here's here's what I would buy. All of that's fine. Okay. Like why on earth would anyone do this, right? Like like people must be listening and be like, "Okay, maybe just drink a little less champagne, dude." But like the fun thing is let's say you took you went to a restaurant, right? And I just did this for this like example here. And you just like dropped in took a picture of uh the wine menu, right? And it's like a big old menu. Some of them are like size of a dictionary. Some of them are simple, but like you don't want to make a choice, especially you just want to be with like talking to the company that's in front of you and not like staring at the wine bible. You drop it in and boom, what it actually comes out with. And and I think the prompt I asked is what would I like from this list? What are good values? And it kind of just went through this really fast based on my preferences like and it's right like I would love this. I have I have had it and it's great and it's fun. It shares the price. Absolute no-brainer. Another example. Another example. And then it kind of gets into a bit more detail like categorically like look if you want a value one and just like want a bunch of bottles go for this. Like everyone's going to love it. If you want something a bit like more splurgy, try these, right? Um and very much like it kind of talks about what why you'll like it. What I love the most though says this is the stuff just to stay away from, right? And you know if it's a big night then just go get these six bottles and and call it a day. And so like that's the fun thing here for me.

Claire Bell: So what I have to call out for folks is we've actually seen not this particular use case but this flow before which is like how do you reverse engineer your own taste. So we saw Hillary at Whoop show how to reverse engineer her own taste on slides. Um we saw I forget somebody else reverse engineered photographic styles. um Ravi uh reverse engineered photographic styles and said like here's a photo like tell me explain to me how to how to describe this but you are the first person that has reverse engineered their own taste in wines and I love this and now you can

Chintan Turakhia: pick yummy stuff to get for and you know what six bottle cart I'm going out with you next time

Claire Bell: I know we'll we'll we'll celebrate AI adoption or something like that

Claire Bell: this has been so great I have one uh two lightning round questions for you. We'll keep them very short and then we'll get you out of here. My first one is if you look back two years ago to now at work, how are you how are you spending your time differently? Like how has all this changed how you personally spend your time?

Chintan Turakhia: My calendar is empty. Like almost empty. And the reason why is cuz the coordination overhead of like, hey, let's prioritize this, let's change this, let's change the road map. No, you just do things. That's one. two, I'm writing way more code. The team knows like uh if their contributions fall below mine, like that's that's we we got to like help on the AI, but like look like I'm also jumping in. The team is doing incredibly hard work. I am spending way more time in the code base, fixing bugs, trying things, coming up with like technical approaches. I am not a replacement for like the insane amount of talented cracked engineers on my team, but I'm able to move things forward much faster and cut through the

Claire Bell: If if AI has done anything for us, cancelling meetings would be would be the gift that that I want. Okay, my last question is when AI is not listening to you, when it gives you a really dumb playbook for your engineers, what is your prompting technique? It depends on like how many tries times I've tried to convince it. But generally, it's like, okay, one, you're clearly not listening to me. This is what I said. Two, yeah, I know I'm absolutely right, but like, stop being stupid. I need your help. And three, I I like the nuclear option is I threaten it and I say, um, Claude, if I'm using like Claude Opus 4.5 High, like, okay, I'm going to stop using you, Claude, and going to switch to Gemini. And then it gets its together.

Chintan Turakhia: I love it. I don't know what that says about either parenting or management style, but I think that is I think it is effective. Well, this has been great. Where can we find you, your team, and how can we be helpful?

Claire Bell: Yes. Um, so I'm on Twitter, Chintanakia. We are building the base app. It used to be known as uh Coinbase wallet. And I think by the time that when this uh episode airs, it will be live to the general public. Use it. It is a consumer social app that happens to use crypto and it's enabling creators to earn and be valued. Um, and we're excited to launch it and we think it's like a real big paradigm shift in crypto consumer apps. So give us a feedback, give it a shot, post uh see the magic happen. And we are hiring two uh cracked frontend backend design engineers ML engineers builders

Chintan Turakhia: super builders I have two super builders happy to bring in a third one but like it is it is really really fun uh to work here on this team and and it it it'll be it'll be awesome. So come

Claire Bell: well thanks for joining us.

Chintan Turakhia: Thank you. This um this was such a a great way to cap off the week.

Claire Bell: Thanks so much for watching. If you enjoyed this show, please like and subscribe here on YouTube, or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiipod.com. See you next time.