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

Scott Wu is the co-founder and CEO of Cognition Labs, the creators of Devin, an AI agent designed to function as a junior engineer on software development teams. In this conversation, Scott demonstrates how his team uses their own product to accelerate development workflows, reduce engineering toil, and handle routine tasks asynchronously. Scott walks us through real examples of how Devin integrates into Cognition’s daily operations—from researching and implementing new features to responding to crashes and handling frontend fixes. He explains how Devin differs from traditional AI coding assistants by functioning more like a team member than a tool, allowing engineers to delegate well-scoped tasks while focusing on higher-level problems. What you’ll learn: 1. How to use DeepWiki to research your codebase and generate better prompts for AI engineering tasks 2. A workflow for treating AI agents as asynchronous junior engineers who can handle multiple tasks while you attend meetings 3. Why public channels create better learning environments for both humans and AI when implementing engineering solutions 4. The top five engineering tasks AI excels at: frontend fixes, version upgrades, documentation, incident response, and testing 5. How to implement a “first line of defense” system where AI agents analyze crashes before humans need to intervene 6. A technique for bringing voice AI into meetings as an additional participant to answer questions without disrupting flow — Brought to you by: Google Gemini https://ai.dev/—Your everyday AI assistant Vanta https://www.vanta.com/howiai—Automate compliance. Simplify security. — Where to find Scott Wu: X: https://x.com/ScottWu46 LinkedIn: https://www.linkedin.com/in/scott-wu-8b94ab96/ — Where to find Claire Vo: ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo — In this episode, we cover: (00:00) Introduction to Scott Wu and Devin (03:53) Where Devin excels (06:08) Using DeepWiki to research codebases and create better prompts (10:27) Prompting tips (11:24) The asynchronous nature of working with Devin (13:38) Multithreading tasks (14:43) Using Devin to implement an MCP server integration (18:38) Setting up workflows in Slack for first-line responses (23:22) Encouraging AI adoption in public Slack channels (25:50) Top five engineering tasks for Devin (32:17) Using ChatGPT voice as a meeting participant (35:57) Lightning round — Tools referenced: • Devin: https://devin.ai/ • DeepWiki: https://deepwiki.org/ • ChatGPT: https://chat.openai.com/ • Windsurf: https://windsurf.ai/ • Slack: https://slack.com/ • Linear: https://linear.app/ • GitHub: https://github.com/ — Other references: • MCP (model context protocol): https://www.anthropic.com/news/model-context-protocol • TanStack Router: https://tanstack.com/router/ — Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Speaker 00

  Devin is async. Once you kick off a Devin session, Devin's going to 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.

• 0:10Claire Vo?

  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.

• 0:20Speaker 00

  I'll say, please go research the chat PRD MCP server. 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.

• 0:32Claire Vo?

  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 two, three, four, five, 10 of these going at once on different projects and not feel like you have to sit there and babysit things.

• 0:50Claire Vo?

  Welcome back to How I AI. I'm Claire Vow, product leader and AI obsessive here 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-scope 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.

• 1:26Speaker 02

  This podcast is supported by Google. Hey, everyone. Shreeta 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 price. And 2.5 Flashlight is ideal for low-latency, high-volume tasks. Start building in Google AI Studio at ai.dev.

• 1:56Claire Vo?

  Scott, thanks for joining How I AI as Devon'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.

• 2:17Speaker 00

  Thank you so much for having me. Now, I'm honored to be here, honestly. I'm a big fan of you guys and all the work you do, so.

• 2:24Claire Vo?

  Great. Well, we want to get into, we have lots of stuff to talk about, but what we really want to 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 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 going to show us first? And what are some of your common workflows when you're doing engineering work or trying to move the product forward?

• 3:07Speaker 00

  Yeah, for sure. No, for us, it's definitely, I mean, as a bunch of programmers ourselves, you know, building an AI that can code is, has got to 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 Devon stack, because there are a few different pieces involved with Slack and Linear. There's the Wiki, obviously, and then there's like Ask Devon, and then there's, you know, starting Devon sessions and getting call requests out of it. I think there's some real, I think there's some real neants and like, what are the right flows of like, how do you work with Devon 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 NIDE, for example, or like a terminal UI, or like Devon is, I think, first and foremost, almost like an engineer on your team, so.

• 3:52Claire Vo?

  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 software engineer?

• 4:04Speaker 00

  The way that we like to describe it is Devin is a junior engineer. And so Devin is not going to go, and you know, we're working on getting Devin to senior engineer. Obviously, you know, we'll get Devin to promotion and everything, but, but, but like Devin is not going to go and, and, and solve some, you know, really hard architectural problem or make some big strategic decision that you, you know, you're going to make and then kind of like execute on for the next month. Like you probably want to be involved in those as well. Devin can help you with the decision, obviously, by, by kind of like referencing the right things or, or, or giving a few things as an input. But I think where Devin really shines is one way that we say also is, 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.

• 4:48Speaker 00

  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, you know, the, the, or, you know, the, the task exactly that, that you want to do. And so a lot of the other tools like Wiki and search, you know, really are, are here for you to be able to kind of like ask the right questions that you want about how Shannon, the code base or, or what needs to be done and then putting a task together. I think in practice, a lot of the, 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, whenever you have an issue that comes up or, you know, 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.

• 5:33Speaker 00

  And so that's a big one. And so like, you know, someone says, oh, you know, we need to go fix this thing in the front end or, you know, maybe we need to go support this other, you know, 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, I'll say like engineer and 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, could have your, your, 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.

• 6:09Claire Vo?

  Yep. I, I, I love that, what you said about, you know, Devin's a, a junior engineer. I say Devin's my favorite intern on my team and, 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.

• 6:48Speaker 00

  Yeah, yeah, let's do it. So as you might know, I'm a huge fan, actually, of ChatPurity. And the natural thing that came to mind for me was we need to integrate into ChatPurity's MCP server. And so I was looking into how to do that with Dev. And so the first thing that I always kind of go to as an initial thing is what we call the deep lookie, 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, this is the, this is the Dev and Web App repo. Appropriately, there's nothing too sensitive here, but it's basically, you know, it explains Dev. It's pulling a lot of information from Readme or understanding the system architecture.

• 7:33Speaker 00

  And I can, I can search this and pull up different things. And so, you know, I'll understand how the MCP marketplace is set up. And 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 server list is implemented. And so this will look through our repo. And Devon, at this point, has done a lot of work in the Dev and Web App repo for standard. And so that helps a lot, which is, you know, Devon builds this representation of the code base over time. And we can see what's going on here. It has all this.

• 8:15Claire Vo?

  And so you're getting both like sort of a natural language explanation of how the 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, 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.

• 8:40Speaker 00

  Yep, a combination of English and code. I think it's an interesting one where it's like, you know, someday it'll probably all be English, you know, but I think especially now, you know, in this current period, I think we're really in the era where obviously you have the, you as the engineer want to be looking at BERT, English and code. And you can see here, it's giving you kind of 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 here's a HubSpot, 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 flaw for folks, is to use this to produce actually a prompt for Devon.

• 9:22Speaker 00

  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 Devon to be able to start from, and if we have an app for a task in mind, then we can get that going. So I'll say, please go research the chat PRD MCP server and add that into this. And so what this will do, I use, basically, construct a Devon prompt from this. And so this has, you know, my prompts here, which I just typed in, which is not super refined, but it also has on the detail about, you know, the part of the code that we're in and what components we're looking at and so on.

• 10:08Speaker 00

  And so then it will generate for me this prompt in Devon that I can just go ahead and use in media. And you can see here, it'll tell, you know, you want to follow the pattern of existing servers like Atlassian and HubSpot. Here's the exact tight dip structure that would be, you know, that's being used here. Here are the functions that you should be working at. And here's what you should check to make sure that it works.

• 10:27Claire Vo?

  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 Devon, would have just sent that prompt, which is add, you know, add chat PRD's MCP server to the list. And I do think that one very short but important loop of

• 10:48Claire Vo?

  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, one, going to be the job to be done of the tool itself. So does that like loop become invisible either through these reasoning models or some application layer that manages it? And two, it's just worthwhile for people to do. So this, you know, when you're thinking about sending a five-word prompt, think instead saying, here's my five-word prompt, build me a better prompt and sending that into your system.

• 11:24Speaker 00

  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 a Devin session, Devin's going to start working and looking through the code and reading online about chat P O D, for example, right? 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, you know, 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, you know, 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, you know, for, for a lot of tasks, there's

• 12:06Speaker 00

  often this sync component, like this synchronous component, and then 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, right? And so like, if you had an intern, for example, would you just send them the five-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 two minutes and be like, okay, yeah, like, you know, you know how we have this M C P marketplace? And then we go and look at it together, you know, we read the pushing arrow line of the code. And then you say, okay, yeah, so, so let's, let's add chat P R B to this and, you know, just go take a look at how that M C P server is implemented and, and make sure we add it to the list. And then you kind of hand off there, right?

• 12:49Speaker 00

  So you kind of have the first two 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.

• 13:01Claire Vo?

  Well, and one of the things I want to call out for people that are building A I 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 something you expect an intern to come back to immediately. You also, from a product perspective,

• 13:40Claire Vo?

  don't expect Devin to come back immediately. Now, one of the benefits of this from a how I AI use case is you can multi-thread a lot with tools like this and set, you know, two, three, four, five, 10 of these going at once on different projects and not feel like you have to sit there and babysit things. And so 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?

• 14:10Speaker 00

  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, or hey, there's these three or four things I was hoping to look at today, right? And you click off each one with Devin. And then, you know, these go and work asynchronously. And it will 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 crone change or something like that, it'll send you the screenshots of what, of the before and after, right? You'd see it's going and researching chat P R G.

• 14:43Claire Vo?

  Well, I will say, just my, clearly my S E L and the MCP is not good, but Devin did make my MCP homepage. So it's in the top nav. Yeah.

• 14:53Speaker 00

  That's funny.

• 14:54Claire Vo?

  It's a one for me, so it should know.

• 14:56Speaker 00

  Yeah.

• 14:58Claire Vo?

  Cool.

• 14:59Speaker 00

  So I think for sure, you know, often 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.

• 15:09Claire Vo?

  Yep. And so what this would do, and maybe we can come back to it later when 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 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. Your goal for this is to get a PR, right?

• 15:31Speaker 00

  Yep. This will produce a pull request for us. 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 have this out in the next step.

• 15:41Claire Vo?

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

• 15:54Speaker 00

  Yeah, sure.

• 15:56Claire Vo?

  You're getting a true live, true live demo here.

• 15:59Speaker 00

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

• 16:06Claire Vo?

  Okay, you have it. chatprd.ai/products/mcp.

• 16:11Speaker 00

  Okay.

• 16:13Claire Vo?

  Has code snippets and everything.

• 16:15Speaker 00

  Okay, okay, here we go.

• 16:16Claire Vo?

  Great. So this, this is a good example of you've done, 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 going to go ahead with the context of your repo and do a PR and ship this feature. And otherwise, you would have had to like, ask somebody to do this. And I think about, for me, I think about the people 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.

• 16:57Speaker 00

  Yeah.

• 16:57Claire Vo?

  And say, like, please explain it to me. You'd have to, you know, get, you take the time to write out that nice spec of this is what you want to 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, three, even three people's time into, you know, about 10 minutes to get something done.

• 17:21Speaker 00

  Yeah, yeah. No, I think often, a lot of the folks who we see who really, really love data and, and use it this way especially, are, you know, folks who are like tech reads or product managers, or, or things like that. You know, it's, 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 two is naturally like the async workflow for people who are in meetings or have a lot of back-to-back going on is 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.

• 18:05Speaker 00

  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 going back and forth with a lot of things.

• 18:17Claire Vo?

  Yeah, 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 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, before we got into the show, you and I are saying you're just a little bit busy over the last month, just doing a few interesting things with the business, in addition to, I'm sure, wanting to build and spending time with the team. And so this asynchronous nature and this junior engineer on demand, how do you actually

• 19:01Claire Vo?

  use that day-to-day to just keep afloat on top of all the stuff that's coming in your team? Not, I have a feature I want to build, let's go build it, we just saw that flow, but like the kind of reactive stuff in your company, how are you using AI to stay on top of that and keep the velocity high?

• 19:19Speaker 00

  For us, a lot of it is just setting the right workflows in our Slack and in our org and so on. And so Devin obviously has knowledge, which means it'll learn your code basically with time as we keep working with it, or you can kind of give it more details about how certain things work. And a lot of it is 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, Sid, to really get to the point where...

• 19:48Speaker 00

  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 Devin, 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 you need to build, or, or, or things like that. You know, we have one for all the crashes that come in. We have one for a kind of like core infrastructure things that, that come up. We have one for, this, this is the one for our web app, um, which is hopefully a little bit less sensitive.

• 20:27Speaker 00

  And you, and you could see here, basically every single thing that folks talk about and whatever we do, you know, it's, it's, we, we start in Devon's session. And so it's like, hey, you know, um, can you standardize, uh, the, the font size spacing and style for these three levels, right? Um, and then, you know, we just go and start the Devon session and Devon will make the PR. Uh, it'll go through the PR, um, this one gets merged, uh, because, uh, because there's some back and forth feedback here. Um, and so, so, so like Devin goes and edits, you can see.

• 21:00Speaker 00

  Um, and so Devin made this PR, there were a couple of back and forth edits. And then, uh, Dave, our engineer went in and, and merged this. And this is often how it works, you know, it's how, this is another good example. Hey, Devin, can 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 started Devon's 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. Um, in this case, by the way, it's actually competence medium. Uh, and then Walden says, oh, no, no, no, like, you know, you should take a look at this thing instead. Um, one of the cool things I want to point out too, is because of this, Devon is a naturally multiplayer experience.

• 21:43Speaker 00

  Um, and so we will often have a few different folks going back and forth. There, if somebody else is looking at this issue, or, you know, if somebody else is the expert on this part of the code base. Um, they'll go and give their own kind of input here and Devon 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 Devon 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 Tansac router and then give that feedback, right? And then Devin goes and makes that change in the pull request. And so you can see Devin had like an initial thing and then had some additional commits and it went and did this link from Tansac

• 22:28Speaker 00

  router instead.

• 22:30Claire Vo?

  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, Ryder, and Cursor scaled faster and closed bigger deals by getting security right early with Vanta.

• 23:13Claire Vo?

  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

• 23:54Claire Vo?

  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. It's because I have no one to talk to. He's my only buddy. But I DM, I DM Devin all the time and we had these sort of like side conversations. He's sort of my intern on the side.

• 24:22Claire Vo?

  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 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.

• 24:56Speaker 00

  Yeah, yeah. And I think there's two sides of it that I was gonna say, one is like the kind of like, when we talk about these multiplayer experiences, right? I think there are two benefits, right? One is this kind of like, 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, you know, 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. Like, I know exactly what you're talking about. Let me go and find that. And then the other side is kind of like educating the humans, right? Of like, you're showing each other what your experiences are, you're being able to work with one another in the same

• 25:39Speaker 00

  clothes. And I totally agree. I think because of both of those, you know, we'll see a lot of experiences in AI productivity get more and more multiplayer.

• 25:49Claire Vo?

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

• 26:09Speaker 00

  Okay, sounds good. Yeah, so the top five, I think miscellaneous front-end fixes, it's amazing for. I mean, because often that whole workload is like, you know, for various reasons, like you said, you have to get like three 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 that, you explain, here's a screenshot. You know, I want to make this button a little bit more round, or I want to touch up the design here, and I want to do X, Y, and Z, 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 in line there. And that's just like a really, really great use case, both I think because similarly,

• 26:54Speaker 00

  it's verifiable for the agent, but it's also verifiable for the human, right?

• 26:57Claire Vo?

  Yeah, and while 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 a very exciting window, let's do, always thrilling to share your Slack. As you can see, my only friends are agents. But here's an example of it I just did very recently, which is I'm working on the chat PRT homepage, and you know, Devin shoots back to me, here's a new hero image that I like, and I was able to give feedback on that. So this is kind of exactly what you're talking about, which is like, let's make changes, and then get kind of that immediate feedback back right in your workflow.

• 27:41Speaker 00

  Yep, yep, fixes, new components, changes that you want to make in your front end. It's super, super nice, because yeah, as we're saying, you can just kind of do this all inside, basically. And so that's probably number one for me. And then number two that comes to mind is version upgrades, migrations, things like that. And so, you know, like upgrading your node version, or getting on to, you know, the latest packages and so on. So it's a big time, you know, we all have to do it. And then somehow these new packages just come out so quickly. But obviously, the devil over 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.

• 28:24Speaker 00

  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 three, I'd say, is Documentation they want as well. And so we have our, you know, Devin docs, for example, like our, our, our own kind of like docs page, like the external docs page. And I mean, Devin has written the entire thing.

• 28:47Speaker 00

  I mean, deep working itself, obviously, is, is, is kind of an extension of that, but, but you know, even writing your own docs pages or putting the series together. A lot of what Devin does is going and processing code base and understanding this reference is that. And, you know, here, here's what this does and so on. And so it's, 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. Okay. Number four that I would say is incident response, actually. 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 the page and Devin gets started,

• 29:32Speaker 00

  goes and, you know, kind of runs a session. And obviously, you probably want a human there too, you know, especially for, for these big incidents that to make sure what's going on. But the nice thing is, you know, it's like 4:00 AM and, and you're kind of like half asleep. And then you, 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, or yesterday that happened. You know, here's exactly where, you know, the, the trace of the error goes. It's, we use that a lot. It's, it's a huge lifesaver for us. And then number five, let's see, I, I, I, I would say adding testing is a big one for us. You know, it's a very common thing where this is especially for, for kind of like

• 30:13Speaker 00

  individual engineers as they're going and working on things, you know, you have your whole PR, you, you built things out, you built a new feature and, and always 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 a test and then it'll run the test locally itself and make sure those tests pass. And so it can iterate with you to make sure the link pass, make sure the CI passes and so on, and, and just kind of like add those for you.

• 30:41Claire Vo?

  All right. Well, we're, we're very close. My, my five are very close. So I love those. So to recap and I'll augment yours with mine. So number one, front end fixes. My particular version of front end 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 want to like toil in front end 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 our documentation, internal documentation into our repo, so that Devin has access to the to the doc.

• 31:25Claire Vo?

  But I think he'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. 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 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? If this is crazy? You know, Sunday night, Monday night, Saturday morning, where

• 32:06Claire Vo?

  you like really don't want to 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 going to close with just 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 use case that I hadn't heard before. So do you mind spending a few minutes just telling us about that?

• 32:36Speaker 00

  Yeah, for sure. So I'm a big fan of voice. I actually think there are a lot of interesting input. You know, we've played around with, you know, we have voice in Windsurf now, actually, as of Wave 11, too, partially because of that. But in short, the way I'm describing it's 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 it 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 can get an even faster answer. It's fully synchronous and do it in the conversation.

• 33:19Speaker 00

  And then obviously you have all of the detail of it can go and research and do these other things, too. What I'll often do is, you know, if I'm in a meeting and 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, you know, there are 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 plus software engineers, you know? And how many are there in the world, right? You know, you obviously like, you know, the big bang shot there, tens of thousands of software engineers, big tech companies, you know, those are the first couple, maybe the Accenture and Versace, you know, that category. Those are the first ones that comes to mind. But like, what are all these different companies that have it?

• 34:01Speaker 00

  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,

• 34:07Speaker 00

  be totally unresponsive for like two minutes. So it said, 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 when I say, hey, like, can you, can you please like, tell us like, how many, how many companies out there have 10,000 plus 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,

• 34:37Speaker 00

  a natural stepping stone where I just find that voice lowers the friction even further in a way that actually really matters. Like, 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, five 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 one or two seconds where you can just get on instantly and just say what you want to say. And that actually matters, I think, 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, that you want to ask.

• 35:15Claire Vo?

  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 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 chat, chat GPT into it. Okay, we will do.

• 35:55Speaker 00

  Must be nice. Must be nice.

• 35:57Claire Vo?

  Man, it's the dream, man. Um, 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 going to be the form factor to rule AI engineering?

• 36:14Speaker 00

  I, 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, the next generation of human computer interface. And, and like the, the way that I like to say it is, you know, Tony Stark doesn't have a laptop. Like, like you, 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 products, 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, let's, let's ask the user for this and that. And so, you know, and, and you're just making the changes in real time in your products and your agent obviously is going and implementing this for you.

• 36:58Speaker 00

  And so I think it's a, it's, it's certainly very agentic, but, but I think it's almost like we, we might, whether we call it an IDE or an agent or whatever, it, it really is basically just like a a different human computer interface where you are just looking directly at your product rather than having to go through all your code or go through your, you know.

• 37:16Speaker 00

  And so, so I think that's the, 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, so I'm, for example, in meetings all the time.

• 37:32Speaker 00

  Unfortunately, you know, not that, but, but, but, but, but yeah. You know, and because of that, I actually think the Slack agent workflow is a super, supernatural one, you know, or, or like linear, for example, and tagging, you know, dev and prime linear. I think for an engineering IC who is, who's, you know, gets to code for, for, you know, eight or 10 hours a day, again, must be nice. But the, the, the IDE is kind of the natural place where a lot of this starts, right? Which is, you know, 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.

• 38:07Claire Vo?

  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, a little credits back, like you did that wrong. I get credits back. So I know you see a lot of 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?

• 38:51Speaker 00

  I can give some advice. I can't say that I have 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, 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. 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 and look through all the history of what he was doing, right? And so like we had an example of that just now where, you know, Devin got stuck of like, I see the chat, there are any pages, it's probably have an MCT 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

• 39:36Speaker 00

  and it found some other things, right? And that was what the issue was, right? And so, 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 when you send that. And so I think a lot of it actually with agents is just, it's kind of like pair, 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, that, that's, that's the biggest thing that, that will really move the needle.

• 40:12Claire Vo?

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

• 40:24Speaker 00

  Yeah, yeah, so we're cognition and Devon on Twitter. We officially got the Twitter of slash cognition, which is great. And then obviously, it's devin.ai if you'd like to use the product.

• 40:37Claire Vo?

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

• 40:41Speaker 00

  Cool. Thank you so much for having me.

• 40:43Claire Vo?

  Thanks so much for watching. If you enjoyed the 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.