How Coinbase scaled AI to 1,000+ engineers | Chintan Turakhia

28:18Chintan Turakhia:Regular user seems to be like balanced on the tiering. 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 for all the different sort of paths a user can take from light to power. And I'm assuming it's not linear. And let's just see what this cooks up to. okay this is really working hard really opus or five yeah opus is opus is really working hard on this but um yeah let's let's see where it goes well you know it's really interesting i'll give you 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 of times with customer QBRs, is I say, write a Slack post that I can put in my engineering channel on a couple of these stats and how we can get people to move from A to B.

29:24And it'll write me like a short little Slack post. So 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. 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.

29:46Chintan Turakhia:Yeah. You know, that's like kind of the awesome thing is the power of something like a workflow markdown file is huge. It's absolutely huge. And it's exactly like the thing you're describing here. 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.

30:33And the best news, it's already built into Jira, Confluence, and Jira Service Management paid subscriptions, so the power of Rovo is already at your fingertips. Know the feeling when AI turns from tool to teammate? If you Rovo, you know. Discover Rovo, AI that knows your business, powered by Atlassian. Get started at rovo.com. That's R-O-V as in victory, O.com.

31:05Chintan Turakhia:Let's see. Let's see what it came up with, right? And like, you know, 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 of this? Well, your job as a leader is to lead, right? And to make change 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.

31:42Chintan Turakhia:Something very, very simple, something like, wait, try a tab completion flow. I kind of feel like the LLM really wanted to just turn this into a game, like a little quest or something. Yeah, it's gamified a little bit. Yeah, it is a bit gamified. It was kind of fun. All right, so this is cool. It's kind of given me like, this would be my Slack post TLDR. 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. It's dark mode, so the engineers will just love it. Yes, right? It's kind of perfect.

32:20Chintan Turakhia: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 right um cursor just did release bug bots i love bug bot yeah i love i love bug bot agent isn't for hard 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 tab harder okay if cursor is listening i think this is like gonna be your new merch line guys i need a hat that says tab harder yes okay so just to just to recap again we're doing we're doing a free free product work for cursor here we we took you know your ultimate problem was like how do i drive up adoption of these tools and you're like of course i'm gonna use the tool to understand adoption and then figure out ways to drive adoption we did analysis We created a visualization of the data itself.

33:40You identified cohorts and power users, which would have been very tedious to do if you were going to do manually.

33:45Chintan Turakhia:Yeah. And then you created a hosted playbook 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 money. um agent everything tab without thinking bug bot always on iterate prompts love it and this you know again what i think is fun let me talk about what i think is fun about this one 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.

34:35But again, across management, there are actually measurable things you can do about the performance and efficiency of your team.

34:42Chintan Turakhia:Yes. And I think it's 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 do with code. Actually, that is the thing. You can 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 exactly what you're saying right now. 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? Yeah. Come on. Like, no, you can just do things right now. And, and again, it's like not the, I think people underappreciate the velocity creation of a fun task.

35:28Chintan 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 because I got like a little dopamine hit from this dark mode playbook. That's kind of funny. And I think people underappreciate like that iteration speed that can just come with like a fast feedback loop. Yeah. 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 so much more fun to look at than a google doc yeah 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 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're talking about the speed of feedback to feature and you said some fighting words out there.

36:22You're like, we're really compressing the time from feedback to feature. So how does that actually work?

36:28Chintan Turakhia:Those were some fighting words. And, you know, I think you know this, right? 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 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.

37:17Chintan Turakhia:Right. OK. And then there's a whole discussion around. Is this important? Is this not important? OK. 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 we're all preparing for a big launch. 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 using all this AI and just shipping like massive amounts of code.

38:00Chintan Turakhia:And fun fact, like during these surges, we end up shipping like more than three to four X 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 and so we'd invite externals internals etc and we'd 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 your 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 awesome so let's do that it's gonna 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 when they were in real life but for this i'm just gonna like capture some audio and And let's see, what's, what's actually, maybe I can just hear from you like a fun little bug or something of a product that you, you think you want to fix.

39:33Chintan Turakhia:So we're going to start capturing audio. 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. We're going to start capturing audio. Okay, cool. We captured it. It's basically taking the audio. I did a system prompt, sends it to an LLM. And then what we do is the prompt is basically saying, go and identify the bugs. And then I'll create it. I'm going to do one while it's processing. 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 just because it's going through the system but let's look at the second example 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 yep 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 awesome I pop over the ticket is all here the file is there linear is a incredible tool is 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 in-house we call it cloudbot it's actually like using all sorts of underlying models.

41:13Chintan Turakhia:It's not something that is specific to Claude. So Claude bought CreatePR. I know the repo for this is Wallet Mobile. And here's the ticket. Oh, that's not the ticket. The ticket is, boom, here, great. Cool. So I just went from a bug report to a ticket. To a PR. So the PR is cooking. Okay. So I have to pause because if you are new to how I, 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?

42:04video 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 what came out of a research session. Some document being written. Somebody actually making explicit decisions about what to include and not include.

42:48The decision making is gone. Yeah. 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 building the bot?

43:12Chintan Turakhia:So this is like in-house and we built it. You know, it all started around like middle of this year. I created this like, I was just obsessing so much about it. And I was like, 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 Super Builder. And the single job, single most important job of a Super Builder is to create more Super Builders. So we hired our first Super Builder. And we talked about some ideas. And one of the biggest things because most of our company uses Slack.

43:52Chintan Turakhia:We're all in Slack. And Slack, you know, I'm a strong believer. It's just a bunch of humans pretending to be systems. right and the cost of writing that 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 also 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, et cetera, et cetera. We just have different sort of security requirements right now that we just couldn't launch with and that's fine.

44:33So we built this in-house and we have these feedback channels, right?

44:38Chintan Turakhia: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 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 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 one-off 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 cursor's 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.

46:10So like, why is Chintan's app not working right now?

46:20Chintan Turakhia:Chintan.base.es as an example, right? And it has like all the skills, all the MCPs. And so 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 this agent that we built, we added skills and MCPs. So if we can capture context through linear, then we can trigger the agent using all the context from linear. And then it goes off into all the MCPs like Datadog, Sentry, Amplitude, our internal Snowflake databases, et cetera. 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, it's a, it's, it's a super builder.

47:09This is, this is awesome. And so before we move, move on, I think what I want to call it here are a couple of things that I hope people didn't miss. One is right now, if I can give people career advice, you want to be like the, the top three most AI-pilled people in your engineering organization. I'm sorry, I just have to say it. Whenever I pulled an engineering leader aside or someone aside who's maybe a little AI skeptical,

47:36Chintan Turakhia:and I said, 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 super 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 an 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 beeline directly directly to it. I think the other thing, and we've seen this a couple of times, we saw this Amplitude actually did it.

48:18Building 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 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.

48:55Because if you ask somebody to open or learn a new tool, it's just going to create too much friction to move forward.

49:01Chintan Turakhia:I think there's like one super important thing. Like 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 a.m. just pushing this. We got like 200 bucks, right, from this tool I showed you. And I just kicked them all off in like one solid go just to get things cooking. And like it was great. Let's see if a plan came out here. Yeah. So like there's a plan that comes. It actually creates the plan in the linear ticket. Yep. The trick here, why Slack, is because Slack is how things go viral within your company.

49:45Yep, totally.

49:46Chintan Turakhia:If you have pulled out the magic into some separate tool that others can't see, it doesn't happen. And so by getting things into Slack, people are just like, holy shit, this is possible. Let's go. And it's like, it's really cool. 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. Okay, let's go. 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.

50:27Chintan Turakhia:Here are the dates. I've just started taking a picture of it and then throw it into chat GPT and say, create the calendar invites. 100%. 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, I've done like Somalia training, et cetera, et cetera. And I realized like, you know, I went to New York recently with one of my buddies. He's learning about AI, but he's like, 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 was he 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 well 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 spot on 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.

52:17And so, you know, this is like my strongest signal. I love like these wines that

52:22Chintan Turakhia:have very little sugar that are like really rip-roaring 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 specific producer that I wrote amazing buy for and it also called out something i learned in real life which is like i do like pinot meunier 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 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 not like staring at the wine bible you drop it in and boom what it actually comes out with and i think the prompt is 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 to value one and just like want a bunch of bottles go for this like everyone's gonna 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 always 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 call it a day and so like that's the fun thing here for me 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 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 how to describe this, but you are the first person that has reverse engineered their own taste in wines.

55:10And I love this. And now you can pick yummy stuff to get for, you know what? Six bottle cart. I'm going out with you next time. Let's do it.

55:19Chintan Turakhia:I know. We'll celebrate AI adoption or something like that. This has been so great. I have one, 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 spending your time differently? Like how has all this changed how you personally spend your time? My calendar is empty, like almost empty. And the reason why is because the coordination overhead of like, hey, let's prioritize this. Let's change this. Let's change the roadmap. No, you just do things. That's one. Two, I'm writing way more code.

55:56Chintan Turakhia:The team knows like if their contributions fall below mine, like that's, we got to like help on the AI. But like, Look, 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 technical approaches. I am not a replacement for the insane amount of talented, cracked engineers on my team. But I'm able to move things forward much faster and cut through the bullshit. If AI has done anything for us, canceling meetings would be the gift 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?

56:43Chintan Turakhia:It depends on like how many 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 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 gonna stop using you Claude I'm gonna switch to Gemini and then it gets it shipped together I love it I don't know what that says about either parenting or management style but I think it is I think it is effective well this has been great where can we find you your team and how can we be helpful yes um so i'm on twitter at chintan therakia we are building the base app i used to be known as 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 And we think it's like a real big paradigm shift in crypto consumer apps.

57:56Chintan Turakhia:So give us a feedback. Give it a shot. Post. See the magic happen. And we are hiring two cracked front-end, back-end design engineers, ML engineers. Super builders. Super builders. I have two super builders. Happy to bring in a third one. But it is really, really fun to work here on this team. And it'll be awesome. So come join us. Well, thanks for joining us. Thank you. This was such a great way to cap off the week.

58:53howiaipod.com. See you next time.