Spec-driven development: The AI engineering workflow at Notion | Ryan Nystrom

One line that I've been putting in my proms lately is I literally don't know what I'm doing here. You gotta explain it like I'm a five year old. I didn't start with writing code, I didn't start with anything. I just started with an empty markdown document. I actually just opened up whisper and just started yapping about how this feature should work. I gave the app session to codex and it was like right to spec. I then opened up codex again, pointed it at this spec file and I said build it and basically one shot at this. I've been in software engineering for 20 plus years. We were writing these documents and we were sitting in meetings with other engineers debating the merits of one implementation versus another and now no more waiting for the meeting, no more waiting for review. I'm not a CI expert but I kind of know what I want and so other folks were kind of like can you just bring some of your like puppy dog energy to like CI and just see what we can do? Your AI, your agent is never going to complain when you ask it to do this five minutes before the meeting starts. It is more relaxing and it's more fun and I feel like I'm getting more done. It's weird to have this like win-win-win. They do the triangle and they're like pick two and you're like no I'm going to pick all three. Give me the whole triangle. Welcome back to How I AI. I'm Claire Vell, product leader and AI obsessive here on a mission to help you build better with these new tools. Today we have Ryan Nystrom from Notion and he's going to show us as an engineering manager how you can never prep for a stand-up again. We're also going to see how you can get a background agent to write code for a fix your friend texted you and how spectrum and development really works in a code based at scale. Let's get to it. This episode is brought to you by Work OS. AI has already changed how we work. Tools are helping teams write better code, analyze customer data and even handle support tickets automatically. But there's a catch. These tools only work well when they have deep access to company systems. Your copilot needs to see your entire code base. Your chatbot needs to search across internal docs and for enterprise buyers that raises serious security concerns. That's why these apps face intense IT scrutiny from day one. To pass they need secure authentication, access controls, audit logs, the whole suite of enterprise features. Building all that from scratch, it's a massive lift. That's where Work OS comes in. Work OS gives you drop-in APIs for enterprise features so your app can become enterprise ready and scale up market faster. Think of it like Stripe for enterprise features. Open AI, perplexity and cursor are already using Work OS to move faster and meet enterprise demands. Join them in hundreds of other industry leaders at WorkOS.com. Start building today. Ryan, welcome to How AI. I am really excited because you're going to show us, I think, start, medium, advanced mode on some AI coding stuff. Before I jump in, how has AI just changed how you live your life at work? It has completely upended the way I work. I've been doing this. I did a lot of mobile iOS work in my past. I worked the same way every day for 12 plus years. And then the last year, I have changed IDEs, terminals, tools, whatever, 10 plus times. So it's really weird and scary to be changing this stuff so much. But I feel that I've been doing this for a while and I'm feeling so much joy and freshness and newness in this. I wake up every day super excited to tinker and build things. And I'm also working faster and harder than I feel like I ever have, but in a good way. I know people are freaked out about everything's changing the pace is up, but it's really energizing for me. Well, you are not alone. I think every how AI guests has come on and said, I'm having more fun. I'm working faster and everything is different. And what I love about what you're going to show us is it's not just the set of tools, which I think has changed or how we write code has changed. How you like a run a team has changed. So and I think for the better, you know, so I would love to see how you're using notion AI to actually run teams differently. Yeah. So for context, I manage a team of like six, seven people. I'm like an engineering manager or technical engineering tech lead manager. Where do we call it? I manage people and I write code is like my role, which I love. And I've run a bunch of different projects here at notion. The one I'm going to show today, we've we've nicknamed afterburner. Like kind of a quick backstory is I've been kind of vocal about our like dev X CI for a while. I've just I worked at places where it's really slow. I've worked at places where it's really fast. And I came here and I was like, we're kind of like in between, but I feel like we're like slower than we need to be. And eventually this like caught up to me and somebody was like, could you just come fix it and like come work on it? And I'm not like an infrared expert. I'm not a CI expert. But I kind of know what I want. And I think also most importantly, the the group that I manage and the the org that I work in, we're a little notorious for being like really fast and like very, very AI-pilled. And so other folks were kind of like, can you just bring some of your like puppy dog energy to like CI and just like see what we can do? And that's what we've that's what we've done. So we had this really aggressive goal to cut our CI into like a quarter of what it is. We're on the path to doing that. But so what I want to show you is a little bit about how we run projects in notion and how I'm using AI to kind of streamline those projects. So what we're looking at here is like our like project hub called afterbunner. And so in here I've got all this documentation. I've got databases. We'll look at some meetings. I have like a automation that looks for any sort of like little wins if we knock off seconds from different jobs or whatever and we keep it we keep track of them in here. But what I want to show you is basically how we run our meetings. Our small group we run a stand up every single day and doing stand-ups where everyone just like is kind of like dead eyed and going around being like, I did this, I shipped this change or you know, no updates for me. Thanks is like painful. And in my opinion like a huge waste of time, I want to like get to the the me. So we have this kind of like automated meeting template that shows up every single day that we run our meetings, which is basically every day. And it starts blank. And then what I have set up behind the scenes is a custom agent. So we chip this notion AI custom agent stuff a little bit ago. And this runs right after the meeting template gets generated. And it looks through all of our like Slack conversation in the last 24 hours. Any tasks in notion that we close any pull requests that we've like merged just like all sorts of contexts. Oh, and it looks at like yesterday's meeting transcript as well. And then it compiles it basically like a pre read. And this is a this is one from a week or so ago. And it yeah, it shows it pulls metrics. It can show us like what are latest CI time is. It shows some of the things we've decided shows like progress on different like projects or like different things that we're trying to like make faster bugs, feedback, open questions, tat, like anything that's like of concern. And like I can basically work up until like the minute of our meeting without having done a bunch of like prep. And then we all get on a video call and we look at the screen and we're like, okay, here's what we need to talk about. And we'll like hit each bullet. We have like meeting notes that we run down here within notion. And like all the context is basically captured all of the like agenda is like set up for me. So we spend the entire time talking about like problems, decisions, wins, findings, like what are we going to work on next? And it's less the like, oh, I did this thing. Yeah, what I want to call out for folks that are maybe listening and not watching is this is a very detailed meeting like kind of like pre read slash status update, which if you're a you know, TLM or an EM running good meetings, unfortunately, as part of part of the job. And there's a really big difference between a good stand up and a bad stand up. And I think the the ones you described these like wrote like I wrote this PR today, I'm going to start on this. And then basically like a notes document that's a very high level because some human is putting it together. It stinks. And you start to like do the other thing that I found and maybe I'm curious if this is impacted how you work or just made it easier, which is like you start to have those meetings less because the updates aren't for rich. People don't feel like it's a good use of their time. And I think you lose something by reducing the frequency. But if you can have high bandwidth, high quality meetings with high frequency without the overhead, I think you can get better, more detailed work done collaboratively, especially if you're running a remote team or not everybody's in the same room. Sam, curious, do you feel like just being able to get to this level of detail in your stand-up has improved how you can actually build this product and do this work basically? I've been in way too many meetings where I can tell everybody's eyes are glazed over nobody's paying attention and I have run enough projects at this point where to me, that's pretty dangerous because everybody in that room has ideas, they have insight, but because we've made it so non-productive and not engaging, the point of the meeting is like exchange ideas and information and if we're not doing that, literally what's the point? The whole like this could have been an email, that's what the meme is from. I've found that this is basically a good conversation starter and a key thing to me that tells me that this is working is when I'm running these meetings and kind of going through bullet by bullet and then I see somebody fixed our mock server environment in our just tests and we're seeing a test improvement by up to 13%. I'd miss that. That's super cool. Let's talk about it and then from that maybe there's additional headroom that we can make on this and so all of a sudden let's drill into it. I also think it sort of democratizes that sharing so that you've got some people that I could talk for an entire 30 meeting without shutting up and then other engineers are like keeping to themselves but brilliant and super talented and I think it's great. This kind of raises everything up to the top and makes it very visible. I was thinking last night, truly this is a little bit of a cyber but I was thinking last night how people don't know this. It's very very confusing as Claire Vauda podcast host. I am such an introvert. I'm a crazy introvert. I will avoid humans with every fiber of my being and I find like AI as a proxy for me to get over my own anxiety communicating with the world. It's not so insane but I really feel it. Whenever I like message my open clock and I'm like, hey, Polly, can you email so and so blah, blah, blah on my behalf. My anxiety is gone but when I sit in front of my Gmail and start typing an email my introvert start showing and I'm like, I can't get to. So I think this is a real point which is like you get to pull information out of everybody. Yeah. And there's like spikes and values of who is going to come and show off their work, how detailed they're going to be. It does not mean the work is not good. It does not mean they are not talented. They just have different skills in different environments. And so I love this call out of like, we're going to pull equal amounts of information out of everybody because the playing field is equal. I also want to go back to something you said, which makes me think about burnout, which you said I can like work up until this meeting starts. And I know so many people who feel like they're in meeting after meeting after meeting one because when they're not in meetings they're preparing for meetings. So you're getting rid of that. And then two, I think managers being able to, for example, code up until the stand up is such a burnout like protection mechanism, which is you would much rather your managers hands on the code, hands on doing work, filling a creative impulse than prepping for meetings. Sure, they're great at running the meetings, but let's do that in like this just in time mechanism where they're supported through these automations. And so I just imagine I used to feel so stressed as a leader and as a manager being like, if I'm not in a meeting, I'm prepping for a meeting and then I'm in a meeting. And if I can carve back more of my time to just do real things, that feels so much, so much so much better. So I'm guessing you're having more fun just through the balance of the kind of work you're trying to do. I'm, yeah, I'm having so much more fun working this way. I have done the like run a big engineering group where yes, you're spending half of your time just compiling information, synthesizing it, writing reports, like doing all the stuff. And I, I hated it. Like it's so draining. And now I feel like I'm in a sweet spot where I can support and work with a team of like very talented individuals, but also not have to, yeah, be like doing like paperwork the entire time. Like, yeah, I don't want to do like the TDM. I get a lot of joy out of working with people. It's like why I like managing and like talking with them, having fun. I love like, solving hard problems together. And then I like building stuff. And yeah, I think though we're maybe at an inflection point where like, maybe this is controversial or not, but like if you're like a line manager, like, right, right? Like code, you know, get in there and like, stay, stay close. Maybe don't do the P zero hero projects, but like, help your team fix bugs, like make optimizations like whatever, you know, I, it's just, it's so easy now. I mean, I'm going to pull that thread all the way up, which is like, directors of engineering, VPs of engineering, like CTOs, CPOs, it, right, write some code now is the time. And I say this all the time on this podcast, this is the era of the hard skill. Is this not how do we get better at my, my soft skills and things they call this is literally like, how do you write code? How do you write automations? How do you learn these new tools? How do you understand what models do, do what for your own skills? That anything is super important. Okay, we could go on forever on this topic. I do want to show folks how you built this. Yes. Because we haven't seen, actually haven't seen, we've had a couple of notion folks on the podcast. And I think we've seen a notion AI in action. And I just want to see kind of your thought process on how you build something like this out. So I'm going to flip over to you. This is our custom agent. Don't ask me why we got this like potato theme for like the entire project. I think it was kind of something about like, see I was just this like, cobbled together, like, mess. And so we're going to like make the potato like a rocket ship. I don't know. I don't even know if that makes any sense. But like, now we're having fun with it. And we have reactions and like agents and it has spun off into its own thing, which is fun. But this is our hot potato agent. So you can see I have this setup to run at 9am every single day. It's also set up for chat. It's set up if the agents mentioned, but we never really use any of that. And probably the important part is the actual instructions. So in this instruction page, giving context on like what the purpose of this agent is, I am telling it to run. Yeah, look back at 24 hours. So basically telling it your job is to run every single day. And I only want you to look back for the last like 24 hours of activity. I'm explicitly telling it to use sub agents, which is kind of a sleeper feature in notion AI like this exists, but we don't really push it to use it very often yet because it's one, it's very expensive and to it can be kind of finicky sometimes. But I helped build it some, I know how this works. And then I ask you to kind of like fan out and do like a map reduce where I'm saying, go use the honeycomb mcp to figure out what the latest metric is. Look in our project channel and like find updates feedback questions. I tell it where the task databases and how to look for tasks within this project and then how to find yesterday's meeting. And then I give it a template in the instructions or I'm like, this is your format. I care about CISPE decisions, progress changes bugs, questions, risks, a little bit of guidance on writing. And then when it's done, I have it post the Slack and I like emphasize this like, I want it to be brief and fun. And sometimes it's really corny and then sometimes it's like really good and it would be very quirky and just post this like link in our Slack channel and it's like, hey, here's your pre-read some little quiddle about like whatever, you know, hey, hey, you guys are not making enough progress. And then that's it. And then it's we have our meeting note. It's updated. What I like the most about this one, you can show you some of our like internal settings. So this is like, I give it access to all these things and I'm like, you can only view all of this stuff because I don't want it going and like modifying our task database or project database. Like everybody at Notion uses those. But this meetings database in particular, I'm like, you know, you can edit content because this is one you're going to like write and update the page. It can read from our Slack channels, respond to our project one. And then this was new to me. Actually when I set the Sajin up is our MCP. So we've had MCP and you know, this other thing called workers, which is like kind of like writing code. I haven't used them very much within custom agents. But in this one in particular, I'm like, I know exactly where this metric is. It's in Honeycomb. And so I like just configured the MCP in Notion. And by the way, I like, I like used the agent to like set itself. up because I was like, here's the query. I literally give it a screenshot of the Hing Home Query. I was like, I don't know how this works. Can you just update your instructions? - I love that you screenshot it. You didn't even copy and paste it. You're like, please OCR, this screen shot. - Exactly, too lazy. I'm like, here it is, just take it, figure it out. And it kinda, it got it mostly, like most of the way there. I had to fiddle with it a little bit, but yeah. - What I appreciate about this, and again, for anybody trying to just brainstorm workflows where AI can actually have a huge impact on your productivity at work or life, I just go right down what you would do if you had time. If you had time every morning at nine, you would sit down and you with your eyeballs would go through a slash, you would go through Hing Home, you would ask people what's going on, you would look at GitHub, and then you would compile it, and then you would try to be very fun and slack. It's just a description of what you would do. And it doesn't have to be that complicated, and you can iterate so quickly on it. What I appreciate about this, versus old era of more deterministic workflow style builders is the updates are so easy to make. Just change the natural language, redo the order, change the trigger, give it more access to data, and then it's ready, ready to go. - Yeah, and you know what I think, the other thing, I've gotten hung up on when trying to think about these automations, and I've seen others do, is that you get this, you start gigabraining it, and you're like, well, how am I gonna say if like five hours of work a day? And what you just said, made me realize too, that the tedium that this removes for me is not like world changing, but it's like 20 minutes a day. And that's like 20 minutes I can spend doing other stuff, and it's not even just about saving that 20 minutes, but it's like protecting my brain from having to contact shifts about all this stuff and ingested, and instead, yeah, it's just, I know that the information will be there when I'm ready to read it, and I'm ready to shift gears to this project, rather than, yeah. I hate doing the like, read the subday, copy all this information, like put it into like an update board, like it's soul sucking. - I mean, you and I have been doing this for a while. That's like, that was, I feel like 70% of my job. At some point, 70% of my job was just like, what's going on? - Mm-hmm. - How do I massage it? - You're going to a format appropriate for the audience at hand, and it's always the same information. - Yeah. - It's just like, what's the executive version of it, and what's the team version of it, and what's the full team version of it? And like, my shoulders drop out of my ears when I realize we don't have, like we just don't have to do it anymore. And the other thing that I think people maybe under appreciate about AI, and this like just in time delivery, is your AI, your agent is never going to complain when you ask it to do this, five minutes before the meeting starts. - I know, so it's so great. - It's so great. It's just like, when you have it, drop it, get it done and out of your brain. I think is, again, I go back to like, burnout and enjoying your work and reducing toil, and it just feels like a more relaxed way to work. - Yeah. - Yeah, we're happy. - It's so funny, 'cause it is more relaxing, and it's more fun, and I feel like I'm getting more done. - Yeah. - It's weird to have like, this like win-win-win. - Yeah. You know, they do the triangle, and they're like, pick two, and you're like, no, I'm gonna pick all three. - Yeah, and I'm like, give me the whole triangle. - Give me the whole triangle. That, stamp it for the YouTube thumbnail. All right. This episode is brought to you by Orcus, the company behind Open Source Conductor, which powers complex workflows and process orchestration for modern enterprise apps in a genetic workflows. Legacy business process automation tools are breaking down. Siloed low-code platforms, outdated process management systems, and disconnected API management tools, and weren't built for today's AI-powered world. Orcus changes that. With Orcus Conductor, you get a modern orchestration layer that scales with high reliability, emberings humans, AI, and systems together in real time. It's not just about tasks. It's about orchestrating everything. APIs, microservices, data pipelines, human loop actions, and even autonomous agents. So build, test, and debug, complex workflows with ease, all while maintaining enterprise-grade security, compliance, and observability. Orcus, orchestrate the future of work. Learn more and start building at orcus.io. Let's talk about, so we're talking about how meetings happen. Love this. You do write code, though. I do write code. Sometimes with your fingers and sometimes with, you're in my favorite harness of the moment. So let's go to how you get code in. Yeah. I want to show the little bit of a new workflow that we have going on in notion. I honestly don't think this is necessarily a big feature that we're going to ship, or we might ship some version of this feature. So this is all basically internal only at this point. But prior to this, the way one, I love Codex, been a Codex stand for like, I don't know, six, seven months now. And we started building this like Codex integration into notion. Prior to this, it was like, you know, I mean, obviously you're using the CLI to like write your prompt and then they created the Codex app, which is, which is nice, but I'm still like writing my prompt in this thing. So I started actually writing prompts in notion pages where I can be a little bit more like freeform and structured and you know, I'm in like the CLI. I don't have to worry about like hitting enter and then like, oh shit, like I sent my prompts. I can actually like write a document in notion. But then of course I'm like, they're like highlighting all of the text, copying it, going into my terminal hitting paste and like letting it go. It's like fine. There's like MCPs and other stuff that I could be using, but I'm a very simple person. It was like too much stuff. So we built this thing that we're kind of like calling it, I think we're calling it both software factory, but I like its internal project name is Boxy, 'cause it's like all these little VMs that we install codex and Cloud Code on. It's our little boxes. Where now we can actually invoke them from like tasks within notion. And so literally happened this morning, a friend of mine who's a notion fan text to me, he's like, hey, I like the tab block that you built, which is this thing. He's like, but I really wish I could like, I can like copy, I'll show you now. If I click on the dot dot dot thing next to a block, there's like copy link to block. He's like, man, I really wish I could just like, copy link to a tab and then like send it to somebody. And I was like, oh yeah, that sounds really easy. So I opened up this task and I just took some notes and I dropped in this screenshot showing them where it could live. You know, this is like on the tab block, if I right click on it, we get this little flyover menu. And I just described the task. I was like, yeah, let's put a copy link button here. I also noticed that hovering over the delete button didn't change to red. So he's like, yeah, we should fix that. And I was like, I know when edge cases like, you're gonna have to like, if you land on a URL where we're like linking to this block and this tab, like it's gotta like switch to the tab on like fresh refreshes. So I like kind of outlined all the cases, but you can see here, this is one, two, three paragraphs, four sentences and a screenshot. It was like, not a lot. And then this new thing that we built, I can actually mention codecs from within our comments. And this triggers are like boxy. This is all our like internal dev tooling stuff. And then it got to work. And I was looking at the timestamps earlier and I think 1040, 1051 started the implementation and then another 10 minutes later, it replies with a pull request link and a preview URL 'cause we do the preview environment stuff. And it had built the entire thing. And if I switch actually over to, here's the pull request, it built the entire thing. And it was like, here's how I tested it. And this is actually the coolest part to me is like, it actually uploaded screenshots of it doing its own UI verification. And there was like a CI failure in it. So I was like, hey, I replied down here. Like, oh yeah, this part of this code change, I was like, I don't know what is going on here. This doesn't make sense. And there's some type check things. And it was like, cool, here's why we did this change and I fixed your types. And then there was a merge conflict. - Let's also talk about just all-worldly world. The emotions around code review. Like, I love that you're like, I don't get this. Not, I'm gonna try to get it. Or I've done my best to investigate and I'm pretty sure this is wrong. Like, literally, just, I don't get it. I don't get it. I mean, I didn't like sending that to somebody. What if the win team ate? They're like, no, look it up. It makes sense. So that's one of my code review mechanisms as well. is I'm just like, I don't think this is right. - I, yeah. - Yeah, one line that I've been putting in my prompts lately is I'm like, I literally don't know what I'm doing here. You need to explain this to me. Especially doing all this CI stuff, I'm like, I'm in over my head. You gotta explain it like I'm a five year old, and sometimes it's literally caveman style, like here are the things, and I'm like, I need this. - Well, what I appreciate about this, and we'll talk about it a little bit later, I think, is we're not getting any of these Claude code warm fuzzies from Codex. I love it, but when it talks, I feel real dumb when you're talking to me, Codex. (laughing) - It's like, okay, okay, Donda, here's what's going on. - So I think that sort of, like, I don't understand what I'm doing, please explain to me, is I love it, but I think it is a Codex-specific experience. (laughing) Claude code shows up and is like, hey, buddy, guess what, I made for you. (laughing) Okay, so stepping back before we go too deep on the personalities of all these coding models, you have built just, at mention, and I think people miss this, but it's important for, particularly, our engineering team and engineering leader listeners to pay attention to, which is, everybody that know that smart, it has some background agent hooked up to a virtual machine that they kick off so that you're not spinning up your local environment and doing all this stuff on your machine. - Yeah. - And it just, I think, the, we'll talk about this, but the velocity plus your DEVX plus your CI, I think, is a huge piece of AI adoption in engineering. So if you are not, if you don't have a VM strategy and background agent strategy in your large engineering org, time to get one, time to do it. - Totally agree. - And we'll just ask Codex to build it. Be like, yeah. How do I, I don't know what I'm talking about, but I think, I think this is a clear, so this is a good idea. Please build, make no mistake. Okay, last, last one, we have a last use case, you were gonna, you were gonna walk us through. - Yeah, so we recently rebuilt our entire agent harness. The quick TLDR is, just like everybody else, we reach like this point of tool and instruction fatigue, where you have this bloated system props, we're like, okay, we need to dump this down and we borrowed the kind of like skills and progressive disclosure concept from coding agents and brought that to notion AI. And when we were doing this big rewrite, we were asking ourselves like, you know, it only been like six months since we shipped the last rewrite. And this time we were like, what would we do differently? Like seeing the state of the art with coding agents and someone had this really great idea to like, let's not start with code. Like let's just start with specs. And what we've ended up building is we have this like, in our checked into our code base, you see this, we have this, we're looking at, this is a notion repo, but we have this agent specs subfolder. And within this subfolder, we have all of these mark down documents. This is one that I worked on. We have this thing in our AI called ask mode, where we basically ban all of the like mutating tools. So it can only just like read and answer questions. And so when I was building this, I didn't start with writing code, I didn't start with anything. I just started with an empty mark down document. And I mean, I actually just opened up like whisper and just started yapping about how this feature should work. And at the end of it, I gave that, I gave the app session to codex and was like, here's our other like spec library, learn the format, take my information, write a spec. And then it spikes the first version. I did a couple revisions on it. And I ended up with this mark down document. Now, the mark down document is like, it's nice, but what we did with it next in my opinion is, I kind of think that this is like the future of software engineering, where I then opened up codex again, pointed it at this spec file, and I said, build it. And it basically one-shotted this because the entire spec file is so comprehensive with code pointers, with down at the bottom, we have verification. And it was like, here is how you're gonna verify all of this stuff works. And we've even built our own CLI tools so that you can run Notion AI from the CLI. And it could, once it's done seeing that all the tests pass, it could actually just spin up Notion AI itself, send it queries, send it questions, enable ask mode, disable ask mode, and then see the transcripts and like see what actually happens. And I think the first shot of this took a couple hours, but I came back to whenever, a couple thousand lines, did some code review, played with it myself, and I was like, it's right, it's like done. And since then, we've made, I can, the other beauty of this is like, this is in version control. So I can go to the past changes of the spec file and I can see how the spec has evolved. And I could go look through all of the code changes, which also have their own history, but this is now the sort of like source of truth for how this part of Notion AI works. And it's just in plain English that can then be verified and implemented by agents. - Well, I think the other thing that people don't appreciate is taking this outside of the engineering flow is this plain English can be ingested by other parts of the business that need this information. So let's say you need to then release this feature, via some sort of marketing. It's actually like a pretty good asset that explains how it works. That can be translated into another thing, in a way that like code itself, is still a little intractable. And so this idea of spec driven development, but what I like about what you said, I don't want people to miss is the way you make these updates is you update the spec and go go look, make the update change this thing. - Exactly. - And so like the spec is the source of truth, the spec as the change log, I think is a really interesting model. And for people that aren't watching, it's very detailed, it's very technical. So it's not like there is not code in the spec. - Exactly. - There's just not all the code in the spec. And I think that's a really kind of good hybrid model for experienced engineers to start to bridge into what would it look like to have an agent do more of your coding work while you still do architecture work, while you still do design work, while you still make sure that the thing is gonna scale. - Yeah, exactly. I view our job as like engineers evolving into like systems thinkers and architects, and not even just necessarily writing like the spec and thinking about the behaviors, but most importantly is like the verification loop. Like is it a, like how should it verify correctness of this feature or this change? And honestly, it's like if it can't or if like the verification's a little hazy, it's like that's the first thing you actually should be going and doing. It's like do you have a tool to let the agent run itself? That's like one of the first things we did with this project was like we should actually build a CLI so that I can tell codecs like send this prompt and like see what happens. And now that we have that, then we can take these specs and actually just like go deeper and deeper and deeper. And so it's like we're still doing engineering, but I'm not doing the like plumbing work of like wiring up this Asp mode feature. - Well, and what I think is really funny is, I've been in software engineering for 20 plus years. Like we were writing these documents anyways, we were writing technical design documents, back documents anyway, and we were sitting in meetings with other engineers debating the merits of one implementation versus another. And then we still had to go write the code. - Yep. - It's like really, it hasn't added work to go into this model. It's maybe like shifted the emphasis of where the human attention goes, but these were documents that at least I was in every organ I've ever been in writing before. And the other thing that I think has changed so much is those docs then waited for review. And they waited for a meeting. And now no more waiting for the meeting, no more waiting for review. Ship it, have a verification loop, debated on the merits of it being live and working versus the theoretical merits of it sitting in a document waiting for everybody's calendar to open up for a live argument. - Yep, yeah, couldn't agree more. - Let's do it. This is what I, I just, you and I could talk all day about this just to recap for everybody 'cause I know I gotta get you out of here. Three use cases, one, never print for a meeting again, hook it up not only to your Slack, but to your meeting notes, your GitHub, your telemetry, and build the best stand-up meeting. So no one has to stand there glassy-eyed, being boring, giving updates. Second use case, background agents, @mentioned from wherever you work, notion being a great place to do that, kicking off virtual machines, getting PRs done, just saying yes when your friend texts you, can you ship this feature? And then the last one, putting all your specs in your repo, using them as a source of truth for a more autonomous coding agent like Codex, let it cook for a couple hours, review the code, and then when you update the specs, don't update the code. Did I get it right? I nailed it. Okay, let's do a couple lightning round questions, and I'll get you out of here. You and I love Codex. Why? I'll tell you why I love codex, but you go first. >> Okay. Well, so I first fell in love. My God, did I just say that? >> You did. >> First fell in love with codex. Because when I was evaluating both Cloud Code and codex, I found anytime Cloud Code filled up its context window, it would just lose the plot really quickly. Codex, I don't know exactly what it's doing. If it's the model, if it's the compaction, if it's both, it can grind for hours. With the way that I work, both the systems and things that I work on, and I like to be able to fire off a bunch of them at the same time, and then go to a meeting or go do something else, or spend my time round robbing, and managing all of these agents. I don't necessarily want to. I'm not the person that is sitting with the browser open, and some agent next to it, and iterate look at the browser, iterate look at the browser. I'm like, the closer it can get to one-shotting solutions, the better, because that frees me up to do other stuff. I found that codex was pretty good about that. I also just feel it's pretty simple. There's not a lot of bells and whistles. It's not too fancy necessarily. I'm happy with the addition of MCP and skills, and some other stuff coming out. I also really love GPD 5.4. I think it's a great model. All of those things together, it really matches my working style and type of work a lot. Yeah, I'll tell you why. I love codex, and I sent this to somebody. I said, "Work trees everywhere." "Ports 3000 through 2009, spoken for." We're just going across the board. I do think it's fit-it-long running tasks. I like its concept of projects, because I run a lot of different projects. I think it's just a very helpful mental model. Then it's great at code review, honestly. Oh, yeah, it's just a really good code reviewer. It's a really good security reviewer, tireless, uncomplaning with the most tedious of things. I find it's one of my daily drivers. I really like it. It's good. Second question, because you and I also agree on this. Give people the reason. This isn't even a question. This is a demand for you to share my point of view, which is why bang on developer experience and CI speed right now. A couple of things. To me, CI was super important prior to agents. Because in my opinion, it's not even an opinion. It's like fact. The faster you see I completes, the faster you get signal. The faster the more comfortable your engineers will feel with making changes and doing things because they know I can make a change and get it pushed into dev or into production really quick, because I know my CI is fast. If it's slower, then you're building up these monster changes and you're going to be even slower about judiciously reviewing every little tiny thing when I'm like a learn through doing sort of person. And if I can close the iteration loop even tighter, then I'm going to be putting out a change. People are going to be using it. I will take that feedback. I will make another change. I don't have to worry about taking another day before the deploy train is ready to go. I just want to crank really, really fast. And that was all pre-agent. And now that we're in the agent land, it's that, but on steroids. Because agents don't get tired. They can work on a VM. They can work while I'm sleeping. And if I've got a CI loop that takes an hour to run, your agent's just going to sit there and spend for an hour waiting for results to do something. If it takes three minutes to run, like, holy crap, how much more stuff are you as a human? And then especially as you're like, little swarm of agents going to be able to get done. Like, so, so much more. And so I super important. I agree. And we just had Steve from Stripe on. And they're doing like 1300 agent PRs a week. You cannot do-- Yeah. You cannot do that if first, yeah, I slow. It's just-- You might as well be throwing all those PRs in the trash. And so I do think there is just a true mathematical limit on your capacity to ship code to production. That is a reflection of how fast your CI pipeline is. And so if you are, again, engineering leaders, if you are not spending time on making that fast and you are tolerating something slow there, you're not going to get the benefits of AI that you could. And honestly, like, good for AI, good for humans. No engineer wants to sit waiting for their stuff to hit production. It's miserable on the engineer side, lots of downsides. So allocate time to your pipeline, please. Yep. Yep. Ryan and Claire say so. All right. Last question. When AI is not listening, it's writing bad specs. It's not being funny and slack. What is your prompting strategy? Do you yell? Yeah. Yeah, I can-- I can tell. I can be a little bit of a diva sometimes if it really goes off the rails. Though the other prompting strategy that has saved my ass working on the CI stuff lately is because even the best models, I feel like can sometimes be a little sick of fantic. I'll be like, I will just be like, you're wrong. Like, you need to defend your argument. Because I want it to defend it in the way that I want. But I'm like, I just need to see the evidence that if I push counter to what it has done, that it can back up with good pointed reasons rather than just be like, are you sure this change looks OK? It's like, oh boy, it's totally fine. I mean, no, no. I need the cited hard argument against it. Because in a lot of times, with the CI stuff, I'm like, I don't know what I'm doing. I know generally what I'm doing. But the specifics are a lot more nuanced. And I need to get this right. And that's been super helpful. And then when it goes off the rails, I'm like, I could be such a divot. Escape all caps. No. That's what I do. Interrupt and no. Steer the conversation. Little arrow button has never gotten so much work. Ryan, this was so much fun. Where can we find you? And how can we be helpful? You could find me on X. I'm out there shilling for notion right now a lot. But that's basically where I spend my time. Yeah. My DMs are open. So if you have notion problems, I like to try and fix them. I'll send it to boxy and we'll get it done. Perfect. Love it. Well, thanks for joining the podcast. Thanks for having me, Claire. Thanks so much for watching. If you enjoyed this show, please like and subscribe here on YouTube or even better, leave us a comment with your thoughts. You can also find this podcast on Apple podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiipod.com. See you next time.