Devon is async. Once you kick off a Devon session, Devon'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.
Devon'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 chat PRD MCP server." So, this will produce a pull request for us. Often you're running a few of these at once. It's 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 multi-thread a lot with tools like this instead — two, three, four, five, ten 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 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, Devon. We're going to hear about how Scott uses Deep Wiki and Devon to kick off well-scoped tasks to get things done, uses Devon 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, Shishta 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 Flash-Lite 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 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.
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.
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?
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 has got to be one of the coolest things that we could probably spend our time on. I wanted to show a couple 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 pull requests out of it. I think there's some real nuance in 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, you know, an IDE for example or like a terminal UI. Like Devon is, I think, first and foremost almost like an engineer on your team.
Yep, totally. So what are some of the things that you reach for with Devon and the capabilities that you think really make a difference for you as a software engineer?
The way that we like to describe it is Devon as a junior engineer. And so Devon is not going to go and — you know, we're working on getting Devon as a senior engineer, obviously. You know, we'll get Devon the promotion and everything, but Devon is not going to go 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. Devon can help you with the decision obviously by kind of like referencing the right things or giving a few things or input. But I think where Devon 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 is exactly what we need to go do and here's the task and here's all the details of what we need, Devon is really great at going and executing that for you and makes that much faster. And so naturally 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 don't really — or search 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 for 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, 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 Devon as the first pass. 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 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 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 adding 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 what you said about, you know, Devon's a junior engineer. I say Devon'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 working with AI and even, you know, 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 your product and let's, you know, show us how you would work through that end to end.
Yeah. Let's do it. So, as you might know, I'm a huge fan actually of ChatPRD, and the natural thing that came to mind for me was we need to integrate into ChatPRD's MCP server. And so, I was looking into how to do that with Devon. And so the first thing that I always kind of go to as an initial thing is what we call the Deep Wiki, 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 here's, you know, this is the Devon web app repo appropriately. There's nothing too sensitive here, but it's basically, you know, it explains Devon. It's pulling a lot of this information from the README or understanding the system architecture and I can search this and pull up different things. And so, you know, if I want to 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 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 Devon web app repo. I understand a bit. And so that helps a lot, which is, you know, Devon builds this representation of the codebase over time and we can see what's going on here. It has all of this.
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 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 nitty-gritty.
Yep. Combination of English and code. It's an interesting one where it's like, you know, I think 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 — you as the engineer want to be looking at both 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, we have 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 Devon. And so the whole idea is now that we're in this context, you know, we know what the questions were, 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 task in mind then we can get that going. So I'll say please go research the ChatPRD MCP server and add that to the list here. And so what this will do — I basically construct a Devon 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 Devon that I can just go ahead and use the Meteor. And you can see here it'll tell you, you know, you want to follow the pattern of existing servers like Atlassian and HubSpot. Here's the exact TypeScript structure 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, Devon — would have just sent that prompt, which is add, you know, add ChatPRD'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 one going to be the job to be done of the tool itself. So, does that 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.
Yeah, for sure. And I think it's, you know, it's a great call because, you know, as we said, Devon is async, right? And so from this point onward, the nice thing about this is, you know, once you kick off a Devon session, Devon's going to start working and looking through the code and reading online about ChatPRD, for example, right? And it's going to do all this, 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 your intern a project and your intern is going and working on it. And so, you know, they could 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 Devon for every step of the way here. And so one way that we kind of describe it is, you know, 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, 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 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 ChatPRD to this and, you know, just go take a look at how that MCP server is implemented 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 two minutes of going back and forth with Devon, your intern. And then as soon as you hit go on the Devon 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 something you expect an intern to come back to immediately. You also from a product perspective don't expect Devon 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, ten 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?
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 had an issue backlog or hey, there's these three or four things I was hoping to look at today, right? And you kick off each one with Devon 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 of the before and after, right? You can see it's going and researching ChatPRD.
Well, I will say just — clearly my SEO on my MCP is not good, but Devon did make my MCP homepage, so it's in the top nav.
For me, so it should know.
Yeah. 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.
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 Devon 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. 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 seven weeks.
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 Devon to go.
Sure. Sure. Sure. You're getting a true live demo here.
