How Devin replaces your junior engineers with infinite AI interns that never sleep | Scott Wu (Cognition CEO)

Devin is async. Once you kick off a Devin session, Devin's gonna start working and looking through the code, but you're not expected to be there with it. It's just as if you gave your intern a project and your intern is going and working on it.

Devin's my favorite intern on my team, and I have infinite of them. Why don't you pick a task that you might bite off for your product and show us how you would work through that end to end?

I'll say, please go research the ChatPRDMCP server. So this will produce a pull request for us. Often you're running a few of these at once, just like a nice way to have multiple tasks going and then check in on each of them.

One of the benefits of this from a How I AI use case is you can multithread a lot with tools like this and set 2, 3, 4, 5, 10 of these going at once on different projects and not feel like you have to sit there and babysit things. Welcome back to How I AI. I'm Claire Vo, product leader and AI obsessive here We're on a mission to help you build better with these new tools. Today is a very special episode for me because we're talking to Scott Wu, CEO and founder of Cognition Labs, and the builder of one of my favorite AI products, Devin. We're going to hear about how Scott uses DeepWiki and Devin to kick off well-scoped tasks to get things done, uses Devin as his favorite and most tagged employee inside of Slack, And how he's making it not weird to bring ChatGPT Voice into your meetings. Let's get to it.

This podcast is supported by Google. Hey everyone, Shreshtha here from Google DeepMind. The Gemini 2.5 family of models is now generally available. 2.5 Pro, our most advanced model, is great for reasoning over complex tasks. 2.5 Flash finds the sweet spot between performance And 2.5 Flashlight is ideal for low-latency, high-volume tasks. Start building in Google AI Studio at ai.dev.

Scott, thanks for joining How I AI as Devin's number one reply guy on X. I am really excited about this conversation and for you to show off how your company uses and you use the product that at least makes me very happy, and I'm sure makes lots of software engineering teams out there very happy. So welcome.

Thank you so much for having me. No, I, I'm, I'm honored to be here. Honestly, I'm a big fan of you guys and, and, and all the work you do. So.

Great.

Well, we wanna get into, we have lots of stuff to talk about, but what we really wanna do is get into how you AI, and in particular how you AI with the products that you've built. And, you know, I think what's really fun as somebody who's building AI products, it's, it's something you get to use every day and get really good at, but also probably show some of our listeners and watchers some tips and tricks about using the tools that you've built that they may not have thought about so far. So we're getting the expert look into how to AI with the Cognition product. So what are you gonna show us first and what are some of your common workflows when you are doing engineering work or trying to move the product forward?

Yeah, for sure. No, for, for us it's definitely, I mean, as a bunch of programming nerds ourselves, you know, building an AI that can code is, has gotta be one of the coolest things that we could probably spend our time on. I wanted to show a couple of flows actually of how we use the Devin stack, because there are a few different pieces involved. There's Slack and Linear, there's the wiki obviously, and then there's like Ask Devin, and then there's, you know, starting Devin sessions and getting pull requests out of it. I think there's some real, um, I think there's some real nuance in like, what are the right flows of like, how do you work with Devin as an employee? Because I think it really is quite different from a lot of the tools out there, which are much more kind of like, an IDE, for example, or like a terminal UI. Like Devin is, is I think first and foremost almost like an engineer on your team.

So, yep, totally. So what are some of the things that you reach for with Devin and the capabilities that you think really make a difference for you as a, a software engineer?

The, the way that we like to describe it is, is Devin is a junior engineer. Um, and so Devin is not gonna go And we're working on getting Devin to senior engineer, obviously, we'll get Devin the promotion and everything, but Devin is not going to go and solve some really hard architectural problem or make some big strategic decision that you're going to make and then execute on for the next month. You probably want to be involved in those as well. Devin can help you with the decision, obviously, by referencing the right things or giving a few things as input. But I think where Devin really shines is One way that we say it also is kind of like tasks, not problems. And so often when you have a very clear, like, here's exactly what we need to go do, and here's the task, and here's all the details of what we need, Devin is really great at going and executing that for you and makes that much faster. And so actually, I think the next question that comes to mind then is like, how do you figure out the spec or the task exactly that you want to do? And so a lot of the other tools like Wiki and Search, you know, really are here for you to be able to kind of like ask the right questions that you want about understanding the codebase or what needs to be done, and then putting a task together. I think in practice, like a lot of the use cases that we see all the time are, you know, probably number one is just crawling through your issue backlog, you know, whenever you have an issue that comes up or, We have a lot of Slack channels where we talk about issues, and then on every single one of them, we just tag Devin as the first pass. And so that's a big one. And so like, someone says, oh, we need to go fix this thing in the front end, or maybe we need to go support this other MCP, for example, which we'll show in a second, things like that. And then for a lot of the other kind of like, I'll say like engineering toil use cases, it also does really, really well. And so often that's like, You know, going and doing a version upgrade or added documentation throughout, you know, your repo or adding unit tests for a specific thing that you have up or responding to, you know, a crash report that just came up and trying to diagnose what went wrong.

Yep. I love that what you said about, you know, Devin's a junior engineer. I say Devin's my favorite intern on my team and I have infinite of them. And then I like this idea of scoping task, not problem. And I do think it's something that people are working with AI and even, you know, other, other AI tools not in the engineering space, really thinking about task-level orientation sets you up for success, or at least a sequence of tasks can be very helpful. And so why don't you pick a task that you might bite off for, for your product and let's, you know, show us how you would Work through that end to end.

Yeah. Yeah, let's do it. So, as you might know, I'm a huge fan actually of ChatGPT. And the natural thing that came to mind for me was we need to integrate into ChatGPT's MCP server. And so I was looking into how to do that with Devin. And so the first thing that I always kind of go to as an initial thing is what we call the deep cookie, which basically for any repo, this is true for public or private repos. You can come in and get a full AI-generated documentation of the repo. And so in this case, there's, you know, this is the Devin web app repo. Hopefully there's nothing too sensitive here, but it's basically, you know, it explains Devin. It's pulling a lot of this information from the README or understanding the system architecture. And, you know, I can search this and pull up different things. And so, you know, if I wanna understand how the MCP marketplace is set up, you know, it'll point out, what particular components there are or what particular files are called here. And I can read up on this and kind of understand exactly how this is set up. And the natural question here that I might ask is, okay, cool, but just show me where the MCP serverless is implemented. And to this, we'll look through our repo. And Devin at this point has done a lot of work in the Devin web app repo. Pretty standard, right? Um, and so, so that helps a lot, which is, you know, Devin builds this representation of the codebase over time. And we can see what's going on here. Um, it has all of this.

And so you're getting both like sort of a natural language explanation of how this server list is implemented. And then you also on the right side of this, for folks that aren't watching, get the actual code snippets and reference files that you can view and really understand the deep layer of the code. So you have like sort of a combination of let me explain, how it works, and then this is the, the nitty-gritty.

Yep. Combination of English and code. I think it's an interesting one where it's like, you know, I, I think someday it'll probably all be English, you know, but, but I think especially now, you know, in this current period, I think we're really in the era where obviously you have to— you, you as the engineer want to be looking at BERT English and code. Um, and you can see here it's giving you kind of the, the answers of what's going on. And in particular, it'll point out, okay, here's, you know, our list of all the different marketplace servers that we have and We have an Atlassian MCP, and there's a HubSpot MCP, and so on, right? And from here, the natural thing that I'll want to do here, which is what we found to be a big flow for folks, is to use this to produce actually a prompt for DevOps. And so the whole idea is, now that we're in this context, you know, we know what the questions were, we know what part of the codebase that we're looking at. It gives a lot for Devin to be able to start from. And if we have an actual task in mind, then we can get that going. So I'll say, please go research the ChatPRD MCP server and add that to our list. And so what this will do, I used, basically construct a Devin prompt from this. And so this has, you know, my prompt here, which I just typed in. Which is not super refined, but it also has all the detail about, you know, the part of the code that we're in and what components we're looking at and so on. And so then it will generate for me this prompt in Devin that I can just go ahead and use immediately. And you can see here, it'll tell, you know, you wanna follow the pattern of existing servers like Atlassian and HubSpot. Here's the exact typediff structure that would be, you know, that's being used here. Here are the functions that you should be looking at. And here's what you should check to make sure that it works.

One of the things that I want to call out for folks in terms of a workflow that they should think about is a lot of people, myself included, sorry, Devin, would have just sent that prompt, which is add, you know, add ChatGPT's MCP server to the list. And I do think that one very short but important loop of take this prompt and turn it into an effective prompt given the context, you know, and then sending that into the task To do just saves you a lot of heartache. And it feels like extra friction at the time, but I think pretty soon is, um, one, gonna be the job to be done of the, the tool itself. So does that like loop become invisible either through these reasoning models or some application layer that manages it? And 2, it's just worthwhile for people to do. So this, you know, when you're thinking about sending a 5-word prompt, think instead saying, here's my 5-word prompt, build me a better prompt, and sending that. that into your system.

Yeah, for sure. And I think it's, you know, it's a great call because, you know, as we said, Devin is async, right? And so from this point onward, the nice thing about this is, you know, once you kick off the Devin session, Devin's going to start working and looking through the code and reading online about ChatGPT, for example, right? Um, and it's going to do all this, but, but you're not expected to be there with it, right? And so, you know, it's going to work on its own. It's just as if you gave the, your intern a project and your intern is going and working on it. And so they can ping you on Slack and ask you if there's questions or something, or you can go kind of like, you can go take a quick look and see how your intern is doing, but you don't have to be sitting there with Devin for every step of the way here. And so one way that we kind of describe it is for a lot of tasks, there's often this sync component, like the synchronous component, and then this asynchronous component, right? And a lot of what search and wiki is for is for doing the synchronous part of the task before you do the async, And so like, if you had an intern, for example, would you just send them a 5-word Slack message and just leave it at that? Maybe sometimes for something that is like, you know, super clear and then you know exactly. Often what you actually would do is you would sit down with them, talk it through for 2 minutes and be like, okay, yeah, like, you know, you know how we have this MCP marketplace and then we go and look at it together. You know, we read the particular line of the code and then you say, okay, yeah, so let's add check PRD to this and, you know, just go take a look at how that MCP server is implemented and, and make sure we add it to the list. And then you kind of hand off there, right? So you kind of have the first 2 minutes of going back and forth with Devin, your intern. And then as soon as you hit go on the Devin prompt, you're kind of expecting it to be more of an asynchronous thing where you don't have to be in the loop.

Well, and one of the things I want to call out for people that are building AI products out there, you know, like you, like me, is in these sync products, latency really matters. People get really frustrated with wait times, but if you set up your product to really be this asynchronous modality, you actually buy yourself a lot of user love on waiting time because there's not that expectation. Just like you would not say, hey intern, okay, now go research this other MCP and do a PR for me and come back when it's ready. You know, just like that would not be, um, something you expect an intern to come back to you immediately. You also, from a product perspective, don't expect Devin to come back immediately. Now, one of the Benefits of this from, from a how I AI use case is you can multi-thread a lot with tools like this and set, you know, 2, 3, 4, 5, 10 of these going at once on different projects and not feel like you have to sit there and, and babysit things. And so I'm, I'm wondering, you know, while this is running, do you go pop off and go to a meeting or get a coffee? What has this sort of like asynchronous workflow enabled for you?

For better or for worse, I'm in meetings for a lot of the day, and it's great to be able to just kind of kick these off, or, you know, you have an issue backlog of, hey, there's these 3 or 4 things I was hoping to look at today, right? And you tick off each one with Devin, and then, you know, these go and work asynchronously, right? And it'll make the pull request for you in GitHub, and it'll kind of show you the diff and what work it went through. If it's like a frontend change or something like that, it'll send you the screenshots. Um, of, of what, uh, uh, of, of the before and after, right? You can see it's going and researching ChatGPT.

Well, I will say just, uh, my, clearly my SEO on my MCP is not good, but Devin did make my MCP homepage. So it's in the top nav.

Yeah.

He designed one for me. So it should know.

Yeah.

Cool.

So this is pretty neat.

So, so, so, so I think for sure, you know, often you're, you're running like a few of these at once. And like you said, it's just like a nice way to be able to kind of have multiple tasks going and then check in on each of them.

Yep. And so what this would do, and maybe we can come back to it later when it's, it's done thinking, what this is going to go do is it's going to go do research. It's going to find my docs page on the MCP server, uh, that Devin did make for us. And then it's going to pull that docs in and then you're going to get actual code out of this. So your goal for this is to get a PR, right?

Yep. So this will produce a pull request for us. Um, and then from there I'll be able to review the pull request, and then if that looks good, then I'll merge it. And then obviously we'll, we'll, we'll have this out in the next DevRel release.

Amazing. And then your prompts are gonna be so much better, and I'm feeling guilty, so I am just going to Slack you, uh, the, the, the MCP homepage, and you can give that to Devin to go see.

Yeah, sure, sure, sure.

I'll, I'll, I'll get this done. You're getting a true live, true live demo here. Yes, yes.

This is when your intern comes back to you and says, hey, I was looking this up and like I couldn't find it. Like, can you point me to where?

Okay, you have it. chatprd.ai/product/MCP.

Okay.

Has code snippets and everything.

Okay, okay, here we go.

Great.

So this, this is a good example of you've done your research, you use that research to create a better prompt, you use that prompt to kick off a task. that task is worked asynchronously as a sort of like more junior engineer would work, including doing research in your code, external to your, your business. And then it's gonna go ahead with the context of your repo and do a PR and ship this feature. And otherwise you would've had to like ask somebody to do this. And I think about, for me, I think about the people. Yeah. That you'd have to involve in something like this. Like you'd have to go find the senior engineer that wrote The MCP server code.

Yeah.

And say like, please explain it to me. You'd have to, uh, you know, get, you take the time to write out that nice spec of this is what you wanna do, and then you'd have to task it to somebody to actually implement. And so I think you can compress that workflow of a team of like, you know, 3, even 3 people's time into, you know, about 10 minutes to get something done.

Yeah, yeah, no, and I think often a lot of the folks who we see who really, really love Deadrend and use it this way especially are folks who are like tech leads or product managers or things like that. It's a great kind of intersection of one is, on the one hand, you're already used to the flow of kind of like figuring out an issue and getting into what is going on there and then handing off something of here's exactly what we need to build, right? And then I think 2 is naturally like the async workflow for people who are in meetings or Who have a lot of back-to-back going on. It's just a great way to kick off and check in on tasks quickly. And so from starting things from the web app or starting things from Slack, for example, is a nice lightweight thing. If you're not in your IDE all the time, you can start tasks from the IDE as well, obviously. But we see this kind of flow a lot with leads and PMs basically who are, you know, who are going back and forth with a lot of things.

Yeah, and one of the things that I've been telling people more and more is as part of your PM onboarding, you should be now giving everybody access to GitHub, which isn't something that, you know, typically happens in a lot of product organizations. Giving access to GitHub, giving access to tools like this, because I think it does enable product managers to do a lot more. So while this is running, what I wanted to talk about is, you know, before we got into the show, Yeah. You and I are saying you're just a little bit busy, you know, over the last month, just doing a few, few interesting things with, with the business. Um, in addition to, I'm sure, wanting to build and spending time with the team. And so, you know, this asynchronous nature and this junior engineer on demand, how do you actually use that day to day to just keep afloat on top of all the stuff that's coming in your team? You know, not, I have a feature I wanna build, let's go build it. We just saw that flow, but like.

Yeah.

The kind of reactive stuff in your company, how are you using AI to, to stay on top of that and keep the velocity high?

For us, a lot of it is just setting the right workflows, um, in our Slack and in our org and so on. And so, um, you know, Devin obviously has, has knowledge, which means it'll, it'll learn your codebase over time as you keep working with it, or you can kind of give it more details about how certain things work. And a lot of things are, it's almost just like institutionalizing Devin as first line of response. Is how I would describe it. And so I could show a few examples. The big thing is to really get to the point where for a lot of these different things that we file, you know, like Devin is the first person that gets tagged on all of these, right? And look, like Devin won't be able to do every single thing, you know, on the, on one shot on the first try, but often you're working back and forth with Devin and Devin puts up a PR. And if there's some slight touch-up that you have to do at the end or that you have to build, Then you're able to do that. And so we have a ton of channels where we go and talk about issues or various things that we need to build or things like that. You know, we have one for all the crashes that come in. We have one for kind of like core infrastructure things that come up. We have one for— this is the one for our web app, which is hopefully a little bit less sensitive. And you can see here, basically every single thing that folks talk about, and remember, we do, You know, it's, it's, we start in Devin's session. And so it's like, hey, you know, can you standardize the font size, spacing, and style for these 3 levels? Right. And then, you know, we just go and start the Devin session and Devin will make the PR. It'll go through the PR. This one gets merged because, because there's some back and forth feedback here. And so, so, so like Devin goes and edits, he'll report this out. Let's see. And so Devin made this PR. There were a couple back and forth edits, and then Dave, our engineer, went in and merged this. And this is often how we work. You know, I tell— this is another good example.

Right.

Hey Devin, could you make it so that when you Command-click on a notification, it takes you to that in a new tab, right? Natural feature, probably one of our users requested it. And you just start a Devin session, and Devin will give you this progress update of, here's what I'm doing so far. Here are the files that I'm looking at, and here's what I see. In this case, by the way, it's actually confidence medium. And then it says, oh, no, no, no, like, you know, you should take a look at this thing instead. One of the cool things I want to point out too is because of this, Devin is a naturally multiplayer experience. And so we will often have a few different folks going back and forth, or if somebody else is looking at this issue, or, you know, if somebody else is the expert on this part of the codebase, they'll go and give their own kind of input here, and Devin will just go back and forth with them as well. And so really it is just a thread where a group of you are communicating and figuring out how to, how to work on this issue. And Devin is just one of the players in the thread, right? And so, you know, Ethan comes into Walden's thread here and says, hey, make sure to use a link element from TanStack Router, and then gives that feedback, right? And then Devin goes and makes that change in the pull request. And so you can say, see, Devin had like an initial thing. Um, and then had some additional commits and it went and did this, uh, uh, link from Tanzu Stack Router instead.

As an AI founder, you're used to sprinting towards product market fit, your next round, or that first enterprise contract. But speed isn't enough for AI startups. Buyers expect security, compliance, and transparency from day one. That's why serious AI startups use Vanta. With deep integrations and automated workflows built for fast-moving AI teams, Vanta gets you audit-ready fast and keeps you secure with continuous monitoring as your models, infra, and customers evolve. AI innovators like LangChain, Rytr, and Cursor scaled faster and closed bigger deals by getting security right early with Vanta. Listeners can claim a Special offer of $1,000 off Vanta at vanta.com/howiai.

You know, one of the things that I like about this, and again, kind of a shout out on our use case for folks that are trying to drive more AI adoption in their teams, is doing this as much as possible in public is really helpful from a learning perspective. So one of the experiences I had running the engineering team at LaunchDarkly Was when we started putting Devin and Devin-like agents in public channels, we saw a lot more adoption and upskilling of our team on how to actually talk to these agents, how to get the right outcomes. And so, you know, I, we were talking earlier and I was saying I DM Devin all the time. That's because I have no employees and no one to talk to. He's my only buddy. Um, but I DM, I DM Devin all the time and we have these sort of like side conversations. He's sort of my intern on the side. But in larger organizations, I was very much a do it in public channels, do it where people can see it, because not only does the work get done and it's nice kind of muscle memory to tag in these tools immediately, but also just learning how you use them. What is an effective prompt? What are the kind of things that it's good at and not good at is really useful for just overall engagement with these tools. And so, um, I think hiding your AI use is kind of the worst thing you can do. You can do it in work. So I say do it all in public.

Yeah, yeah, yeah. And I think there's 2 sides of it that I was gonna say work. One is like the kind of like, uh, because when we talk about these multiplayer experiences, right, I think there are 2 benefits, right? One is this kind of like, um, the knowledge transfer for the agent itself, which I think more and more products are starting to have, which is, you know, one person uses Devin or uses this tool or that tool, right? And that adds to the knowledge of the tool itself so that a week later when somebody else does that session, Devin's like, hey, oh yeah, I just touched this piece of the code last week. I know exactly what you're talking about. Let me go and find that. And then the other side is educating the humans, right? Of showing each other what your experiences are, being able to work with one another in the same flows. And I totally agree. I think Because of both of those, you know, I think we'll see a lot of experiences in AI productivity get more and more multiplayer.

Yeah. Yeah. That's my hope. Okay. Before we move on from, from Devin and your use of it for engineering, I wanna get really specific. So you'll go and then I'll go. What are your top 5, like everybody can reach for them tasks that Devin can do for you? And you, you pick kind of like 5 categories of tasks and I'll pick 5.

Okay, sounds good. Yeah, so, so top 5, I think miscellaneous frontend fixes, it's amazing for, I mean, because often that whole workflow is like, you know, for, for various reasons, like you said, you have to get like 3 different people involved, right? And it's like, here's what we're gonna do. And then you bring in somebody who looks at that code and there's somebody else who's reviewing or something. And now with this, you tag Devin, you explain, here's a screenshot, you know, I, I wanna make this button a little bit more round, or, you know, I, I wanna touch up the design here and I wanna do Amplify.me. Right. And it'll go and do that. It'll find the right parts of the code. It'll do the implementation, but also it'll send you the before and after screenshots as well. Right. And so you can just kind of review it inline there. And that's just like a really, really great use case, both I think because similarly it's verifiable for the agent, but it's also verifiable for the human, right?

To be able to— And while, while you're, you're saying that, I will just pull up an example of this, which is Let me share my screen, which I rarely get to do here. It's very exciting. Um, window. Let's do, always thrilling to share your Slack. As you can see, my only friends are agents. Um, but here's a, here's an example of it I just did very recently, which is I'm working on the ChatPurity homepage and, you know, Devin shoots back to me, here's a new, a new hero image that I like. And I was able to give feedback on, on that. So that's. this is kind of exactly what you're talking about, which is like, let's make changes and then, um, get kind of that immediate feedback back right in your workflow.

Yep. Yep. Fixes, new components, changes that you wanna make in your frontend. Um, it's, it's, it's super, super nice because yeah, as we were saying, it's, you, you can just kind of do this all inside basically.

Yep.

Um, and so that's, that's probably number one for me. I think number 2 that comes to mind is version upgrades, migrations, things like that. Um, and so, you know, like upgrading your Node version or getting onto, you know, the latest packages and so on. So it's a big time saver. You know, we all have to do it, you know, and then, you know, somehow these new packages just come out so quickly. But obviously the devil is in the details of like finding, you know, this new version will say, oh, you know, every instance of this component is, you know, we recommend that you use, you know, this structure instead or something. And Devin will be able to kind of go through that and do the semantic search and find each of the components and make the right changes. Number 3, I'd say, is documentation, big one as well. And so we have our, you know, Devin docs, for example, like our own kind of like docs page, like the external docs page. And I mean, Devin has written like the entire thing, you know. I mean, DeepRookie itself obviously is kind of an extension of that, but, you know, even writing your own docs pages or putting materials together, a lot of what Devin does is go again, processing the codebase and understanding this references that, and, you know, here's what this does, and so on. And so, um, it's, it's a funny one in the sense that it's not strictly a writing code use case, or it isn't always, but, but, but I think it's so closely related to it that a lot of the same capabilities are really valuable there. I think number 4 that I would say is, um, instant response, actually. Um, and so we have this set up so that whenever there's a crash, the first line defender You know, on pager duty basically is Devin. And so Devin gets a page and Devin gets started, goes and, you know, kind of runs a session. And obviously you probably want a human there too, you know, especially for these big incidents to make sure what's going on. But the nice thing is, you know, it's like 4 AM and you're kind of like half asleep and then you get to your computer and Devin has already written a report of like, hey, I looked at it. I think it was this change from like last week that happened or yesterday that happened. You know, here's exactly where, you know, the trace of the error goes. And so we use that a lot. It's a huge lifesaver for us. And then number 5, let's see, I would say adding testing is a big one for us. You know, it's a very common thing where this is especially for kind of like individual engineers as they're going and working on things. You know, you have your whole PR, you built things out, you built a new feature, And always, you know, the last thing that you have to do before you ship it is you have to go and add your own unit tests and make sure your thing works, right? And the nice thing again is like Devin will go and do that. It'll make the tests and then it'll run the tests locally itself and make sure those tests pass. And so it can iterate with you to make sure the lint passes, make sure CI passes and so on. And just kind of like add those for you.

All right. Well, we're very close. My 5 are very close. So I love those too. So to recap, and I'll augment yours with mine. So Number one, frontend fixes. My particular version of frontend fixes is I think these AI tools can really help you do polish, really nice interactive user experiences where you wouldn't normally be able to spend time on them. So any of those like little magical moments that you don't wanna like toil in frontend on, I think it's really good at. Docs, I think is underrated. I actually have a GitHub Action that every PR gets opened, gets reviewed by Devin, gets the PR description rewritten by Devin. And then after the PR is closed, Devin goes and ships, um, our documentation, internal documentation into our repo so that Devin has access to the, to the docs. I think it's like an excellent technical writer. I too have Devin first line of defense for incidents. So Devin actually has a Sentry login and logs in to Sentry and goes through all of our open issues and starts to, to fix stuff for, for us. Um, definitely upgrades. And then the one that I didn't hear you say, but I just think is a, is a more like operational and personal, um, benefit is it's like 24/7 availability, rubber ducking, which is like when you're working on something and you're just like, can you just look at this and see if I'm being crazy? Like if, if this is crazy, you know, Sunday night, Monday night, Saturday morning where you'd like really don't wanna bother a colleague. I just think having something to like sort of rubber duck with is, is really nice. And so those would be, those would be my use cases, very similar. Okay, Scott, we're gonna close with just, uh, one, one really high-level use case outside of the Devin ecosystem, which is voice. And you were telling me a really interesting ChatGPT voice, uh, use case that I hadn't heard before. So do you mind spending a few minutes just telling us about that?

Yeah, for sure. So I'm a big fan of voice. I actually think there are a lot of interesting, you know, we've played around with, you know, we have voice in Windsurf now, actually as of Wave 11 too, and partially because of that. But in short form, the way I would describe it is like, I think, you know, Google itself, like 20, 25 years ago, what was basically a better encyclopedia, right? You know, we have all sorts of things that you want to look up and pull together and so on, right? And it basically, it got you a faster answer and it got it to you, you know, With, with more up-to-date information of what was going on. And I almost think of ChatGPT Voice as like a better Google, you know, like you, you can get an even faster answer. It's fully synchronous. You can do it in the conversation. And then obviously you have all of the detail of it can go and research and do these other things too. What, what, what I'll often do is, you know, if I'm in a meeting and, and we'll, we'll be talking about things, you know, there are always questions that come up. Like yesterday I was in a meeting and we were talking about this, which is, There's so many orgs out there with tons of software engineers. And so we were kind of thinking like, yeah, like what are all the companies that have, let's say, 10,000+ software engineers? And how many are there in the world? Right. Obviously, like the big banks out there have tens of thousands of software engineers, the big tech companies, those are the first couple, maybe the Accenture, Infosys, that category. Those are the first ones that come to mind. But like, what are all these different companies that have it? And, you know, naturally in a meeting, it's kind of rude to just go on your phone and just kind of like, you know, be totally unresponsive for like 2 minutes as you're looking. So instead, what I'll often do is I'll just pull out ChatGPT and go on voice. And it's basically like adding ChatGPT to every conversation, you know? And so then I say, hey, like, you know, can you please like tell us like how many companies out there have 10,000+ software engineers, right? And then, you know, whether it's voice to voice or whether it's, you know, voice and then you kind of get the response in text, like I use both of those modes a lot, but I find it to be like a very natural stepping stone where I just find that voice lowers the friction even further in a way that actually really matters. Like, I was going to say, it's like, you know, in the encyclopedia era, right? If you were going to look something up, it took like, I don't know, 5 minutes or something. So you had to go pull the right, like, letter of the alphabet or something and find this. And then Google got it for like 10 seconds, you know, and like voice is kind of like getting it from like 10 seconds down to like 1 or 2 seconds where you can just get on instantly and just say what you want to say. And that actually matters, I think, um, for, for being able to go back and forth or just like having, you know, very off the cuff, like off the cuff questions that you, uh, that you want to ask.

Yeah, I was going to say, I, you know, you've maybe changed my mind here because I used to think that voice mode was like super slow. Socially disruptive in that it feels so unnatural to like talk during a meeting. But if you flip it on its head and you're like, no, this is just another meeting participant that I'm putting into the room, it actually is, is more socially inclusive. Everybody hears the result, right? You're not like slacking around links and then people are opening them up on their laptop and reading while somebody is talking. Like everybody's sort of like clued into the synchronous nature of this new, new information. So If I had people to be in meetings with, and not to brag, but I have very few meetings, then maybe I will bring ChatGPT into it. Okay, we will do—

Must be nice. Must be nice.

Oh man, it's the dream, man. So quick lightning round questions. We will get you back to your work. First one, it's like picking between your children. I know now. The IDE, the terminal, or the agent. What is gonna be the form factor to rule AI engineering?

I really think of this in the future as, you know, we call it coding agent and like a lot of what this becomes is actually just the next generation of human computer interface. And like the way that I like to say it is, you know, Tony Stark doesn't have a laptop. Like, like you don't need one at some point if you're just, you have your Jarvis plugged in and you're going back and forth with your agent and then go and do these things for you. Right. And you can imagine that building software is just kind of like You're not looking at your code. You're not looking, you know, you're just looking at your own product, right? And you're looking at your own product and you're saying, hey, let's make this button rounder. Look, let me add a new thing over here. Let's save this and, you know, let's, let's ask the user for this and that info, you know, and you're just making the changes in real time in your product and your agent obviously is going and implementing this for you. And so I think it's a, it's, it's certainly very agentic, but, but I think it's almost like we might, whether we call it an IDE or an agent or whatever, it really is basically just like a a different human-computer interface where you are just looking directly at the product rather than having to go through all your code or go through, you know, and so I think that's the future version some years out. I think today I would say, I think a lot of it depends on the cohort. And so I'm, for example, in meetings all the time, unfortunately, you know, not that, but yeah. And because of that, I actually think the Slack agent workflow is a super, super natural one, or like Linear, for example, and tagging Devin from Linear. I think for an engineering IC who gets to code for 8 or 10 hours a day, again, must be nice. But then the IDE is kind of the natural place where a lot of this starts, right? Which is, you'll have these things that run in the background and you'll have these asynchronous processes that are going as you're doing your thing. But the natural place to get started for that is the IDE today, I'd say.

I also just think what's nice about this era is like the form factor can come to you and you can, you can decide what, what the interface is that works best for, for your workflow. Okay. You know, as somebody, Devin is my buddy. I am sure you get lots of chats that would give us very good insight into my closing question, which is when you are frustrated with our sweet, sweet intern Devin. What is, what is your prompting technique? And I know you all monitor this because when I get frustrated, sometimes I get little credits back, little credits back, like, you did that wrong. I get credits back. So I know you see a lot of, um, human language to agents, but what is your strategy? What do you find yourself doing in a moment of, you know, frustration or being blocked?

I can give some advice. I can't say that I've always followed my own advice. But, but, but, but a lot of what it looks like, I'd say for, for an agent especially is, um, I think the agent is a little bit different from, from a chatbot in the sense that like a chatbot, there's less to go off of is kind of like how I want to say it, right? Where with a chatbot, it's like, you know, you ask a question and it gives you the wrong answer and it's like, no, that was the wrong answer. You know? And then that's all you can really say with an agent. Like one of the nice things that you can do is you can go through, uh, and look through all the history of what it was doing. Right. And so like we had an example of that just now where, you know, Devin got stuck of like, you know, I've seen the ChatGPT page, it says they have an MCP server. I'm like trying to find the documentation on this, right? And if we go and scroll through the logs and we'll see like what happened, that it Googled it and it found some other things, right? And that was what the issue was, right? And so from there, it's kind of like you take that information and then you understand, oh, Devin was missing the link to this page. And then you send that.

Right.

And so I think a lot of it actually with agents is just, it's kind of like pair programming or pair debugging with an intern. Like you want to, you know, first you get to go through and see, okay, here's all the steps that you took. Oh, by the way, it's like, you know, I think you missed this one file, which is, you know, the downstream reference of this. And that's why there was the bug or something like that. I think that's the biggest thing that will really move the needle.

Okay, so review the history, figure out where it went wrong, and then, then reinstruct. Okay, Scott, this has been so fun. Thank you for showing us. Where can we find you and how can we be helpful?

Yeah, yeah, perfect. So, so we're, um, Cognition and Devin on Twitter. Um, we officially got the Twitter of /cognition, uh, which is great. Uh, but, and, and then, um, obviously it's, it's, it's devin.ai if you'd like to use the product.

Great.

Well, thank you so much and appreciate you spending the time with us. Cool.

Thank you so much for having me.

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 howiaipod.com. See you next time.