Best of the Pod: Claude Code - How Two Engineers Ship Like a Team of 15

If you’re using AI to just write code, you’re missing out. Two engineers at Every shipped six features, five bug fixes, and three infrastructure updates in one week—and they did it by designing workflows with AI agents, where each task makes the next one easier, faster, and more reliable. In this episode of AI & I, Dan Shipper interviewed the pair—Kieran Klaassen, general manager of Cora, our inbox management tool, and Cora engineer Nityesh Agarwal—about how they’re compounding their engineering with AI. They walk Dan through their workflow in Anthropic’s agentic coding tool, Claude Code, and the mental models they’ve developed for making AI agents truly useful. Kieran, our resident AI-agent aficionado, also ranked all the AI coding assistants he’s used. If you found this episode interesting, please like, subscribe, comment, and share! Want even more? Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only for paying subscribers, but you can get it here for free. To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Head to ai.studio/build to create your first app. Pitch is the AI presentation platform that helps professionals collaborate on, create, and deliver winning slide decks — all while staying on brand: https://pitch.com/use-cases/ai-presentation-maker/?utm_medium=paid-influencer&utm_campaign=every Timestamps: Episode start: 00:00:00 Introduction: 00:01:16 Why Kieran believes agents are turning a corner: 00:03:18 Why Claude Code stands out from other agents: 00:06:36 What makes agentic coding different from using tools like Cursor: 00:11:58 The Cora team’s workflow to turn tasks into momentum: 00:15:20 How to build a prompt that turns ideas into plans: 00:23:07 The new mental models for this age of software engineering: 00:34:00 Why traditional tests and evals still matter: 00:39:13 Kieran ranks all the AI coding agents he’s used: 00:42:00 Links to resources mentioned in the episode: Try Cora, our AI email assistant: https://cora.computer/ Kieran Klaassen: @kieranklaassen Nityesh Agarwal: @nityeshaga The book that helps Nityesh form mental models to work with AI agents: High Output Management

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

• 0:00Dan Shipper?

  You're figuring out how to do compounding engineering. There's two people on the team, but it really feels like there's 15.

• 0:06Speaker 01

  Coding with AI is more than just a coding part. Utilizing it for research, for workflows, it should be used for everything.

• 0:15Speaker 02

  We haven't touched Quince or Cursor in the last three weeks. Both of those have agentic coding capabilities, but Pod just takes it one step further by simplifying it by a factor of 10.

• 0:27Speaker 01

  We've been really leaning into, let's AI do the work for us and we're just managing the AI.

• 0:33Dan Shipper?

  What you did first is spent time building a prompt that effectively builds other prompts. That's really cool.

• 0:53Dan Shipper?

  Kieran, Natasha, welcome to the show.

• 0:55Speaker 01

  Thank you.

• 0:56Speaker 02

  So much for having us, Tom.

• 0:58Dan Shipper?

  I'm psyched to have you. So for people who don't know, both of you work on Cora, which is Evri's AI email assistant. Kieran, you're the GM. Natasha, you're an engineer. And beyond the fact that Cora is a really cool product, and I'm really excited to bring that to everybody who listens to the show or watches the show. I wanted to do an episode with the two of you because I think that you're figuring out a new way to do engineering. Because really, Cora has, you know, there's two people on the team, but it really feels like there's like 15 because you've got, you've got agents who are pulling down PRs and working on branches. And then you're like pushing them up and other agents reviewing. And it's just like this kind of crazy thing that

• 1:42Dan Shipper?

  it's a new way to build software. And, and Kieran, you said something the other, the other day that like really stuck with me, which is like,

• 1:51Dan Shipper?

  You're figuring out how to do compounding engineering. So with each piece of work you do, you're making it easier to do the next piece of work. And I just think that it's really important to bring what you guys are learning to everybody that watches the show, because it's like we have new tools and so we need new principles and new workflows for using those tools. And so I'm really excited to talk to you about that.

• 2:17Speaker 01

  Yeah, thanks. It's really fun to build Cora, but like being part of every and like being in an environment where you get access to tools, like access to thinking, access to exciting new ways to to work really helps us rethink how we build. So like it's it's really an experiment. We're building a product Cora, but at the same time, we're figuring out how we should build. And and that's super interesting. And we're like right in the middle where people say, what do you think of this new model? Like, like, how do we use this research tool? And we're just trying things out. And Natasha and I, we've been like really feeling a shift in the last weeks, I would

• 2:59Speaker 01

  say, where we're like, like, things are changing and we're not the only ones. Like, we hear other people say that as well, but not a lot of people. And what we've learned is a lot and we want to share a little bit of what we learned. And also what we know is like, we're just barely starting. We're scratching the surface of this and it's a big shift that's happening right now by new models, by how people think, by MCP, by like, just, it's a lot. And yeah, like, it's great to talk about that from different perspectives. Yeah.

• 3:37Dan Shipper?

  Yeah, I agree. And I think it is so special to be at every because we do like every day, there's someone new in the Discord who's like, I built an AI agent. Do you want to like use it before we launch it? And so, you know, we get access to. OpenAI models before they come out and sometimes anthropic models. And so we have this like early edge and then and then you guys are so good at figuring out how to actually incorporate them into like a production process. So you said, Kieran, that something changed. So I guess I want to get a sense of what you think changed and what like draw the broad strokes of what the workflow is that's starting to emerge for you guys.

• 4:16Speaker 01

  Yeah, for me, like, obviously, it's it's like everything coming together. But I think the biggest thing is a realization in myself that coding with AI is more than just a coding part. And it's really about like utilizing it for research, for workflows, for for everything. Like, it should be used for everything. And we're now at a point where the agents are good enough that they can actually do everything. So we need to rethink again, like, hey, Curse or Windserve, like, the old school way of coding was great, like more of the vibe coding, like, that was one step.

• 4:57Speaker 01

  And then now it's the realization, oh, actually, we can just give a task and it will do it. But still, the work needs to be done by like, what do we do? How do we do it? And just a realization that we should lean into that more and really go deep. And and it's like Claude Code, like, it's just good coding agents or agents available that actually start to work with new models like Claude four, like really good at following directions and instructions. And it's all of that coming together and that that I realized like, oh, we're here, like, the future is here, this thing we've been talking about that was going to be the

• 5:36Speaker 01

  agentic evolution, suddenly it works and it's working in real world, non experimental playing thing. It's just like we're building an app and it's working, building the app.

• 5:49Dan Shipper?

  So what I'm hearing is like, it's not just about developing with AI. It's all the things that go into developing that you're using AI for. And that the, the thing that you're using the most for this is Claude code. Is that right? And if it's right, like, tell, tell me about, like, for people who don't know Claude code or haven't used it, give us a little introduction to Claude code. And then tell us about like exactly how you're using it.

• 6:13Speaker 01

  Yeah, Claude code is basically the coding agent version from Anthropic that uses Claude under the hood. And it runs in your, in your terminal as a CLI tool, which is kind of.

• 6:28Dan Shipper?

  Do you want to share your screen and like, show us?

• 6:30Speaker 01

  Yeah, yeah. So Claude code is a tool that you use in your terminal. And I know for non-technical people, this is like, oh, this is scary. But I've converted friends who were not technical to use Claude code. And they were like, oh, this is great. But it's really simple. You just hit, you start your terminal, you say Claude, and an interface will pop up.

• 6:54Dan Shipper?

  And basically for people who are, who are listening instead of watching, he's in his terminal. It's, you know, the, the classic black screen that you're, you know, it feels like you're using DOS or something and he just typed Claude. And then we just got a thing that says, welcome to Claude code. And there's a little text box for him to type in any command.

• 7:12Speaker 01

  Yeah. And why is this different or what makes this different? This has access to the directory or the computer. So it can look through files on my computer already. It can run things on my computer. It can take screenshots of websites, it can search the web. Like it has tools, but way more tools than available in a normal Claude version.

• 7:39Speaker 01

  That's important because engineering work, like building stuff, you do need more tools than just like the basics. You need GitHub to see what you need to build or what the status is or what the CI pipeline does, like do the test fail. Like having all of these things available in one coding agent actually makes it possible for me to have a workflow or like a thing I do actually be done by an agent. And that's, that's the important thing. Like really, the compound word comes in by doing more than just coding. Because lots of, like if you talk to an engineer, like most of the work is maybe coding,

• 8:23Speaker 01

  but maybe it's actually 20%, maybe 80% of the work is like figuring out what to do next or understanding what people, like what their feedback is and how to interpret it. And what you can do here is you can, for example, like a fun way is like to use it and say, let's say, what did we ship in the last week? So like it, it knows stuff. So I'm asking it what we shipped and it will most likely look at the Git log because that's how we track what we did ship. And yeah, so it looks through the Git log. It looks at what we merged to main.

• 9:06Speaker 01

  And yeah, that's a fun way to use it. And for example, we can use this for product marketing. And it says, oh, these are debug fixes, a brief skip functionality, chat panel state, email summary, XML tags, major features, brief help monitoring, time zone, auto detection. These are all things we released. And now I can say-

• 9:29Dan Shipper?

  And it's written in a nice write-up that-

• 9:32Speaker 01

  Yeah, it's not technical.

• 9:34Dan Shipper?

  And it's actually a lot for, for two people. There's, there's what, like six major features and like five important bug fixes and three infrastructure updates? Like that's a lot.

• 9:46Speaker 01

  Yes, it's a lot. And, and like this week, we've been really leaning into like, let's AI do the work for us and we're just managing the AI. One other thing, for example, is if, if you have someone come to you like, oh, what is the status on this? Or like, what are you going to ship next week? Let's see what it will do. Can you see what is in the pipeline and what will come out soon?

• 10:12Dan Shipper?

  So this is awesome. Nitesh, while this is going, if you want to jump in at any point, feel free to. At some point, I'll lob it to you, but also like just I'll, you know, feel free to jump in. Yeah.

• 10:22Speaker 02

  Sure. Yeah.

• 10:28Speaker 01

  So we'll see. Like, I don't know if it has project access, but like you get the gist. Like if you have the information connected to the agent, it's very easy to use it. And it's very important to use a tool you're familiar with. And at this point, I think Claude Code works the best for me. It is the most flexible because it doesn't only solve coding issues. And that's important. Lots of these coding agents are made to code. But I want to do more than coding. I want it to be like a support in engineering in general. And I think the Claude team really thought about that. They made it not too specific. And they

• 11:12Speaker 01

  kept it general while actually being really good at solving things and looking at what it did, thinking about the mistakes it made and self correcting. So that is stuff coming together. That's very hard. That makes it possible to use now. Yeah.

• 11:29Dan Shipper?

  What's the difference between coding in Cursor and Agentic Coding?

• 11:35Speaker 02

  Claude Code is such a simple departure from the Cursor and WinSurf that we're used to. Like, both of those have Agentic Coding capabilities. But Claude just takes it one step further by simplifying it by, I think, like a factor of 10. So what Karen was telling earlier about how Claude Code may feel intimidating because it is a terminal, but in reality, it is like so much simpler than the WinSurf and Cursor because there is nothing except a text button, text box here. Like, there's no like command key, no shortcuts, no accept,

• 12:15Speaker 02

  delete, reject, remove. Like, there's nothing. It's just a text box and it works because the model, the underlying Claude model, is so much more capable now. So it's able to work for longer and do tool calls. So it

• 12:33Speaker 02

  It's like a simpler UI, which makes it at the same time more powerful. Even though, even though like the underlying model behind like Cursor and Plotcode is the same.

• 12:45Speaker 01

  Yeah, and an example of this is this morning I was pulling some metrics and I was like, why didn't we get any, any responses to this form? And then.

• 12:56Dan Shipper?

  And for, for, for context, like basically we have a form that we ask people how disappointed they would be if they could no longer use Quora. So we can tell how, how well we're doing. And you noticed, we have a, we have a weekly meeting where we go through all the metrics and we know that you noticed that no one had filled out that form. So you're going into Claude Code and you're asking, hey, like, why is no one filling out this form?

• 13:18Speaker 01

  Yeah, I was like, there has to be something like this form was not sent. And I asked like, hey, 14 days ago, something went wrong. Uh, can you see what went? And what it did, it made a checklist, uh, to do's like fetching recent log changes to the, the controller, searching the code base. So it looked through what changed around that date and it found, uh, we removed a piece of code that adds people there, which is here. Like it says, hey, actually you just need to add this. And I said, okay, do it for me, create a pull request. And it did that. And I said, oh yeah, by the way, I'm also going to create a script that will then add everyone that we missed to it.

• 14:03Speaker 01

  Migrated and that was it's like, and the fun part was like, I didn't, it didn't cost me any energy. Like it was as easy as me writing it down in GitHub to look at later. I don't need to, I just ask it and it does it immediately, which is really nice. It's like the inbox zero, does it take less than five minutes? Do it kind of thing.

• 14:27Dan Shipper?

  Yeah, I think the thing that people may not fully realize is that that's a thing that task could take anywhere from like thirty minutes to a couple of hours without AI. And it's not just that, it would require you to like focus on it and like put aside time to like sit down and do it. And now you just sort of like send off requests like that, and then you can send off another one and another one. You have a bunch of these like sort of working in parallel. So give me like a snapshot of what that looks like concretely, like what your actual workflow is. What are you actually doing? How many tabs do you have open? Like, are you actually doing any hand coding yourself? Do you have like five in parallel? Are you just using Claude code? Like, give us, give me a sense of that.

• 15:11Speaker 01

  Yeah, I'll show you my screen as well. Maybe, Nitesh, you can, you can tell what we did before, like when we got early access to Claude. Like, we were excited what we did. I'll share my screen.

• 15:23Speaker 02

  Yeah, yeah, so this is like, like one day before the Claude livestream was scheduled. We were like, okay, tomorrow, coding is gonna change. We'll have a much more capable model, which will be able to work for everything that we want. We're basically gonna get like a coding genie for us. So the best, most productive thing for us to do today, instead of doing our regular scheduled programming, we should just jam for a two-hour call where we make a massive list of issues that we want the future, like tomorrow's superior model to solve. And we did that. We created like twenty issues in terms of, you know, like what we want to fix, what were the things that we were planning to work on,

• 16:08Speaker 02

  and prepared the system for the new Claude model.

• 16:15Speaker 01

  Yeah, and it was funny because Nitesh had like, he prompted ChatGPT to say, hey, tomorrow we have, we reached AGI. Can you, can you, yeah, can you help us come up with everything we need to do and like prepare the AGI to solve everything we did? And then we fed that into the prompt improver of Anthropic, and then we use that as a prompt.

• 16:43Speaker 01

  We create it.

• 16:45Dan Shipper?

  Before you move on, before you move on, so for people, for people who are listening, so basically you have this sort of Trello board type thing inside of GitHub, Combon board. And for each thing that you've identified as what you want to do, it looks like you have a document that lays out in detail. Okay. If it's a feature or it's like a bug fix or whatever, lays out in detail what it is and how to actually do it. Can you open up one of them? Okay. So like a feature is you want to generate, you want to have AI generate synthetic data. And it has, this document has everything from a problem statement to like a solution vision to all the requirements.

• 17:22Dan Shipper?

  And all the technical requirements and like a bunch of, a bunch of stuff, but it's, and even it has, it seems like it has implementation steps with day counts and stuff like that. So.

• 17:32Speaker 01

  Which is funny.

• 17:33Dan Shipper?

  So this is.

• 17:33Speaker 01

  One day is like one second.

• 17:35Dan Shipper?

  Okay.

• 17:36Speaker 01

  Yeah, yeah, yeah. So this, we use Claude code and we have this custom prompt that we generated to create these.

• 17:44Speaker 01

  Because like it's a lot of work to create these. And even with chat GPT, like there is a lot of steps. You need to look at all the code. You need to.

• 17:52Dan Shipper?

  You have to think about it a lot.

• 17:53Speaker 01

  You have to think about it. Yeah, there's a lot of thinking. So it's really hard to do well. So what we did, we created an command in Claude code. A command is kind of a custom prompt that you use a lot. And ours is like, hey, there's a feature.

• 18:09Dan Shipper?

  Sorry, this is a command in Claude code or a command in cursor? Cause you have cursor open.

• 18:12Speaker 01

  Yeah, I have cursor open because that's how I edit files, but it's Claude code. So you can see we're in Claude. And, and I can use this command by hitting CCY, which is Claude code. And then I say, something like a problem I have, like a bug, a problem, anything. So it's very low friction. So I have this CCI command. And it's actually, I were just jamming. We're like, oh, what if we do this? Oh, that sounds cool. And then a voice to text. And it starts, um, so, so let's, let's see how this works. And then while it's running, we can go over the thing. So. I want infinite scroll in Cora where if I am at the end of a brief,

• 18:58Speaker 01

  it should load the next brief and it should go until every brief that's unread is read. So like-

• 19:07Dan Shipper?

  So yeah, I just want people to understand like Kiran almost never types anything

• 19:13Dan Shipper?

  and does all voice attacks. So he was just doing voice attacks into his terminal, into Claude code with, I believe, an internal, as of yet unreleased, internal every incubation called Monologue, which he is the number four biggest user of, but still under wraps, but you know, a little preview in here coming soon. And basically, what it seems like it's doing is it's taking that, is it turning that into that document that we were looking at earlier? Or is it actually going and executing it?

• 19:48Speaker 01

  Yeah, so what it does is it will insert whatever I said here in the feature description, and then it will follow all these steps. And these steps are research, research best practices. So one is grounding itself in the codebase, so researching what exists. Then it's researching best practices, so it's searching the web, finding open source patterns. So it's like grounding it in like best practices in general. Then it will present a plan. And when I say, yep, sounds good, like I like that review human in the loop for the plan, because sometimes it does it wrong, but most of the time it's right.

• 20:27Speaker 01

  Then I say, yep, sounds good. And then it creates the GitHub issue and it will put it in the right lane and all that.

• 20:34Dan Shipper?

  Oh, interesting. So it's like that whole Kanban we were looking at in GitHub earlier. You've created a way for you speak your feature into Claude code and then it does all the research to create that long document and then just adds it into GitHub issues. That's really cool.

• 20:53Speaker 01

  Yeah, it's an important step because it's like this is different from Cursor coding, because in Cursor normally you skip this step because the tool is not really made for it, like the tool's made to code. Yes, you can create markdown files and all of that, but let's lean into- Like an issue tracker, it exists and it works well and people use it and it already hooks into existing like patterns like it like we can give this to a developer and they can implement it.

• 21:27Dan Shipper?

  Yeah, and one of the things that just to point out is like you're running this and I think one of the special things that when we saw Opus for for the first time, we were like, holy shit, is that it just runs forever with without any intervention and then gives you a pretty good result, which we've had sort of agentic type things for a little while, but it's just a way different level of autonomy and quality than than we've ever had before. And it's like just checking things off of this to do list in a way that I think other agent loops are just going to be a lot less thorough.

• 22:03Speaker 01

  Yes, absolutely.

• 22:05Speaker 02

  Me and Kieran have like a fun thing going on where we're trying to see who can have Cloucode running for the maximum amount of time. Kieran is stopping the list right now.

• 22:15Speaker 01

  Twenty five minutes.

• 22:16Speaker 02

  He ran it for twenty five minutes. I'm only at eight minutes right now.

• 22:20Dan Shipper?

  Oh, man.

• 22:23Dan Shipper?

  How how did you get it to go so long, Kieran?

• 22:26Speaker 01

  A very, very long plan includes, yeah, it's just very, very complicated long plan and also include a lot of tests and just make sure that it runs all the tests and fixes all the tests and

• 22:40Dan Shipper?

  Interesting.

• 22:40Speaker 01

  It goes pretty long. Yeah.

• 22:42Dan Shipper?

  Take me through, wait, I want to understand, how did you make that prompt that that creates the prompt? Like the prompt that creates the research document. So like, how did you know which elements to put in? Did you just use, did you just do the same thing where you you use like a Claude prompt improver or the Anthropic prompt improver to make that or? Yeah, why? How did you think about putting that together?

• 23:04Speaker 01

  Yeah, this is part of like the compounding effect. It's like having an idea that has like a lot of a lot of outcomes. So this was what Nitesh sent me. He said, we just got AGI, it got delivered and we can write software. That this was your initial prompt, which is kind of fun, like like it's very dramatic. And then ChatGPT said, I'm ready. Okay, so now do this. And I was like, okay, yeah, that's fine.

• 23:39Speaker 01

  That's fine, but like, uh, do you know, uh, the Anthropic Console Prompt Improver? You're like, what is that? Uh, well, anyone that doesn't know, this is the, uh, they changed it.

• 23:53Speaker 01

  Is this console? Yeah, it is the, oh yeah, it is. Okay. They changed it a little bit, but this is great because basically you paste in a prompt or something like that and you can say, yeah, we will have thinking and you click generate and it will improve the prompt automatically. And you think like, eh, how good can it be? It's pretty good because it's also very low friction. So like, it's very easy to just take a minute to see if something comes out, if it works. If it doesn't work, delete it. Doesn't matter. We were just jamming and we were like, well, we're going to come up with 30 research tasks. So like, we better have a prompt. So I just copied this prompt.

• 24:31Dan Shipper?

  And that became the document? Yeah. Okay.

• 24:33Speaker 01

  Into here and change the arguments and then you can trigger those in Claude by doing slash and we have these two custom prompts here.

• 24:43Dan Shipper?

  Hmm. And then I think that actually gives me a much better idea of like what you mean by compounding engineering because what it says to me is what you did first is spent time building a prompt that effectively builds other prompts because those research documents are effectively prompts for Claude code. And so now that you have a prompt that builds prompts, um, every time you want to make a new feature, you have to specify less. Like you just say the little feature and then it'll go do the research to like build it out into a big document versus before, every single time you have to do a feature, you have to say, at first I want you to research it and then I want you to like think through all these like different corner cases or the ways that, you know, I like things built or whatever.

• 25:29Dan Shipper?

  I think that's so. That's so cool. And what's also really interesting to point out is it's working while we've been talking, and that's just a different way to code. Like, we were, you know, we were on the phone together like last week or the week before, and we were testing this out together, and I shipped a feature that went to prod while we were talking, which I'm not in the codebase at all. So it's like, kind of crazy that that actually happened. And it's like, it's a kind of more social way to code, like we're coding right now, building stuff, which was not possible before. Do you want a winning deck that'll actually help you land big deals? Pitch combines design, collaboration, and delivery all in one platform. With Pitch,

• 26:12Dan Shipper?

  there's no version chaos and no off-brand slides. It's everything that you need to create and present professional, beautiful decks. Pitch's new AI actions let you instantly rewrite slide text for any audience. They let you maintain brand tone and automatically generate slide summaries and speaker notes. And they even let you enhance visuals without starting over. Pitch manages your entire presentation workflow from design to delivery. And it does all of this without compromising on design quality. It features cloud-based collaboration, brand libraries, interactive embeds, and smart scaling tools. With Pitch, every slide you create stays on-brand, thanks to custom templates and brand tones. And every presentation you share tracks engagement, so you know whether prospects have opened it. If you have a new audience, AI rewrites your messaging instantly. Do you want to track which slides

• 26:57Dan Shipper?

  resonated? Engagement analytics show you. If your client needs a dedicated space for their deal, create a custom Pitch room. The Pitch platform adapts to how you actually work. When you're ready to present, share via live links or custom rooms. Pitch handles the hosting, the tracking, and the professional polish. Are you ready to design, collaborate, and close deals all on one platform? Start creating for free at pitch.com and get your team set up in minutes. That's pitch.com. Start your free trial today. And now, back to the episode.

• 27:23Speaker 01

  Yeah, absolutely. And, oh, so while we were talking, we did the research and we created this issue, which is cool. And we had, I think, six or seven running at the same time, because we were just like, new idea, let's go. New idea, let's go. And what we also did, we went through user feedback, we read emails, we just, everything we could, we gathered, and we were just like brainstorming. And it's really fun, because If you're in this brainstorming place, you can just kick off agents and see what comes up, what they come up with and take another time to then review. So what we do also is, um, yeah, like to agree with you on like,

• 28:08Speaker 01

  it's really fun to do this together on a call.

• 28:12Speaker 01

  Because that's where magic happens. And there is still a human review step here because we found that we want to look at it, see if it makes sense, if anything is missing. Like this is having taste, experience, intuition.

• 28:29Speaker 01

  Like this, this, uh, the, the bug I solved earlier with the email not going out. Natasha did the same with his Claude code, but it didn't give the right answer. Yeah. So, so there is like, there is still like a human touch of intuition. Like I hinted at, look at the history. And that actually made it think into the right direction. And Natasha didn't add, look at the history. And then it said, no, everything works fine. So there is still like intuition and.

• 29:00Dan Shipper?

  It's, it's still a skill. It's still a skill.

• 29:03Speaker 01

  It is a skill for sure. Yeah, it's not. Yeah, it's absolutely a skill. There's no magic prompts that does everything like. It is about using it the right way and using it to its strengths for sure. Yeah.

• 29:17Dan Shipper?

  Yeah. Natasha, how have you found this all? Because I know, you know, Kieran is like a long time like Rails, like expert person who's just like an incredible programmer. And I think you're a little bit earlier in your programming journey. So what has that been like to come to every, uh, start working on Cora and start working on it in this way?

• 29:38Speaker 02

  Yeah, no, uh, this has been like incredibly eye opening, I would say, because, um, honestly, uh, like my experience with programming is that two years ago when ChatGPT came out, I thought, okay, now it's, uh, perfect for me to teach myself programming and build a SaaS application. And, uh, that I always wanted to. So I taught myself programming using ChatGPT from the very first day. So I have gone through all the transitions. I went from ChatGPT and then when Cursor came out, I shifted the workflow to Cursor. And then the Wind surf got better, we shifted into Wind surf. And, uh, you know, I was always thinking like, okay, I am. At the forefront, I don't know any of my friends who are doing so much with AI and I'm at the forefront.

• 30:19Speaker 02

  Then I joined uh every and start working with Kieran and Kieran is at a whole other level. Like he's in our meetings, he's like nervous writing code, he's nervous typing, he's always speaking into the uh computer. And um uh so I was like, okay, I need to uh log that into the workflow. Um and then uh even when Claude code came out, um Kieran actually pushed me into using it. And uh clearly it it is now the the way uh to program like me and Kieran both. I was like, we haven't even touched uh Windsor or cursor uh in the last like three weeks or so. Uh or even if we do touch it, like it's it's usually uh just because we wanna read something.

• 31:04Speaker 02

  Uh it's it's basically like we're using it because we don't have VS code on our computer. Like it wouldn't matter if it was VS code, like the older VS code or a person, because uh all the AI stuff is happening with Claude code now. And um it's uh really fun to uh, you know, have in be in this position where the entire coding landscape just changes completely every three months. And uh you realize like nobody's at the forefront.

• 31:31Dan Shipper?

  I gotta say, I'm jealous of you learning to code right when ChatGPT came out, because I learned to code from books like twenty years ago.

• 31:38Speaker 01

  BHB four for dummies.

• 31:41Dan Shipper?

  Yeah, like basic for ba- learn basic in twenty four days, like Sam's teach yourself basic or whatever. Yeah.

• 31:46Speaker 01

  Del five five.

• 31:48Dan Shipper?

  Yeah.

• 31:50Dan Shipper?

  Um and and also it's so funny for you to say like, I thought I was, I thought I was sort of at the for- at the forefront of AI coding. And then I joined every and started working with Kieran because it just reminds me of, I don't know if like there's this scene in um Star Wars uh the prequel, episode one, where like they're they're under the water and and they're like being attacked by a sea monster and it looks like they're gonna die. And then another bigger sea monster comes out and just like eats the eats the the one that's killing them. And Qui-Gon is like, there's always a bigger fish.

• 32:19Speaker 03

  There's always a bigger fish.

• 32:24Dan Shipper?

  And yeah, Kieran is the bigger fish.

• 32:28Speaker 01

  But I feel I feel the same like like you say that about me, but I'm like, I'm I have no idea what I'm doing. Like, I need to like, I'm running behind. We need to do like a million more things. So that's just the reality of the landscape. Like, there is always more. But it's really about practice. Like, you should practice using AI. You should push yourself every day. If you don't, like, you'll miss very cool stuff.

• 32:54Dan Shipper?

  Yeah. Well, what are I guess I'm curious, like,

• 32:58Dan Shipper?

  personally, and also for people in the audience, like, what are the problems with this, right? So basically, it sounds like you're moving to a form of coding where you don't touch the code.

• 33:09Dan Shipper?

  You're one level above. And so what are the problems that come up with that? And how are you solving them? Like, what are the new engineering practices that you need to incorporate in order to make sure that things go well?

• 33:20Speaker 02

  For me, like, the most important realization for me has been like this thing that I always keep going back to, especially with Plot Code. I read this in that management book, like High Output Management, which I tell CEO wrote like 50 years ago. And the first chapter, he mentioned something like how in any production process, you should fix any problem at the lowest value stage. And I just can't stop thinking about that statement because

• 33:54Speaker 02

  because AI and Plot Code can now do so many things for us. It has become really important to focus on the earliest part of things. So what I mean by that is when when we see that, you know, when we are using the workflow that Karen just showed to create a GitHub, like a very detailed GitHub issue, then it's very tempting to like start another Plot Code to ask it to just, hey, go now work on this GitHub issue and fix it. But that's actually gonna be a problem because there are chances that, you know, the the plan that Claude was able to give in that issue, it wasn't the direction that you wanted to go.

• 34:36Speaker 02

  And you want to catch that before you ask Claude to go and implement the solution and then you have to fix it over there.

• 34:44Dan Shipper?

  That makes perfect sense. I really, really like that idea. The thing it reminds me of is just, it's like, all this stuff is like, it's like a lever. And like, the further out you get on the lever, like, the more power you have, but also, the more power you have to go in the wrong direction. Like, every little inch makes a big difference at the end. And, and so, trying to catch it earlier, I think, is the thing that makes sure that you're not shooting off into space, or, this lever metaphor is totally breaking, but like, you know what I mean? Like, if you, if you point a rocket at the moon, like, one inch means thousands of miles of

• 35:24Dan Shipper?

  difference. And so, I guess the same thing is true with AI stuff. And I think that's actually a good lesson for me, because I, I tend to want to like rush through the planning stuff. It's like, it's just hard for me to like, look at a document like that, like the thing that's that Claude is writing, and concentrate on it. So, how have you guys found that?

• 35:47Speaker 01

  Yeah, it's, it's kind of boring to read most of the time.

• 35:55Speaker 01

  But you can make it more fun. Like, you can say, just like, minimal, minimal, this is too much, just, but, but then the thing is, then it misses things again. So, it's actually important. So, for code, I like it to focus on user stories, or like, asking questions and answering them. So, let's say, like, hey, what are some questions a good PM would ask about this, like, that we should consider, and give like, two options. Like, that's, it's more fun to read that than, like, week one, we'll do this, week two, we'll do that. Like, that's, it's like, PRDs are boring, and you can make them a little bit more fun, or give more examples, or, like, you can shape

• 36:36Speaker 01

  that research. And that's normally what we do in the, in the human review step. It's like, do we see any red flags? Do we need more stuff to be added? Because it will save so much time.

• 36:49Dan Shipper?

  Yeah. That actually reminds me of something that we're finding in another part of the business. So, Danny, who's been on this show, is the GM of Spiral. And inside of Spiral, we're building a writing agent. So, you can think of it sort of like Claude Code, but specifically for writing tasks. And I think there's something similar about that, where sometimes you want that writing agent to Shift into like an interview mode where it like tries to understand more about what, who you are and what you want, rather than just like spitting out a bunch of stuff that then you have to read through. And it sounds like there's maybe something missing here in Claude code or these sort of coding workflows where it would be really nice, instead of having to read that like

• 37:30Dan Shipper?

  long document, it's finding ways to like ask you questions so that the thing it outputs is more likely to be right without you having to read through the whole thing.

• 37:39Speaker 01

  Yeah, absolutely.

• 37:40Speaker 02

  That's an interesting idea for a custom command click here. We should totally try that.

• 37:43Speaker 01

  Yeah, for sure. Like this is something we should automate and make better, like for sure. And at the same time, it knows a lot because it has access to your code base and your style and like that's, that's very powerful. So like, like you have the code base and it's actually pretty good.

• 38:04Speaker 01

  Doing it like I, I think in addition to like making it very good at the beginning, I think just boring traditional tests and evals are very important as well. Because how do you know what you did is actually working? Well, you can open a console and click through it, but like, why? Just have it tested, write a test for it. Like just, just the bare minimum. Smoke tests are great where you just see does, does it kind of work? Because otherwise it does way too much, but it's a very good way to have it iterate and fix things by itself.

• 38:44Speaker 01

  And we haven't tried it as much yet, but we, we use the Figma MCP where we say, hey, implement this from Figma. And then now there is like, you can have puppeteer, take a screenshot for a mobile version and then say compare the two. Like we haven't really tried it out, but like we want to try more of that out. So there are these checks in place, tests in place that you normally do manually. And the same for prompts, like evals for prompts. So I kind of think of an eval as like writing a test for code. An eval is a test for a prompt.

• 39:24Speaker 01

  And what I've seen last week as well, I had Claude Code run an eval and then say, actually, it fails four out of 10 times. I said, run it 10 times. Does it always pass? No, four times it doesn't. I said, oh, look at the output. Well, like, why didn't it call that tool? It was a cool tool, a tool call test. And it says, oh, yeah, it wasn't specific enough. And I said, OK, just keep going and change the prompt until it's passing consistently all the time. And it did it. Like, I just walked downstairs, got a coffee, walked up, and that was it. So evals are also very powerful because they will tell you if a prompt works.

• 40:07Speaker 01

  And similar to writing code, a test says your code works. So leaning into those more boring, traditional ways is also very powerful.

• 40:18Dan Shipper?

  That makes sense. I have a thought. And because one of the things I think is really special, and I think, Natasha, you're in this boat too, so you tell me if I'm wrong. But one of the things I think is really special about you, Karen, is that you just test everything. So like, you've tested every single agent. Natasha, have you have you used like a lot of the agents as well?

• 40:39Speaker 01

  Oh, that's Karen.

• 40:40Dan Shipper?

  OK, well, I think we could, I think we could still do this. I think it'd be kind of fun. I want to spend five minutes with Karen doing a S tier through F tier ranking of agents. And so what I'm going to do is I'm going to share my screen. And I'm gonna, I'll call out an agent and then you tell me where it ranks. Are you game?

• 41:05Speaker 01

  Yeah, let's do it.

• 41:06Dan Shipper?

  OK, cool. Let's see.

• 41:12Dan Shipper?

  Does, I guess, let's do cursor.

• 41:16Speaker 01

  Yeah, so it's fun because Cursor, like what Cursor? Is it Claude 4? Is it Max?

• 41:23Dan Shipper?

  Cursor on the best possible settings.

• 41:27Speaker 01

  And is it the background agent? Or is it the... Okay, Cursor, traditional best possible setting. Like, that's the confusing part about Cursor and Windsurf. Like, there are like a million versions of it. And like, why don't you just have the best version? And that's what I love about certain agents. They just say, "Look, this is the best agent." So that's why it wouldn't be the best. I would say A.

• 41:54Dan Shipper?

  A? Okay.

• 41:55Speaker 01

  Cursor is very good with Claude 4.

• 41:59Dan Shipper?

  All right, Windsurf?

• 42:03Speaker 01

  C, because they don't have Claude 4. It's ridiculous, because 3 weeks ago, they would be A. And now they're not.

• 42:15Dan Shipper?

  Wow, wow, okay.

• 42:17Speaker 01

  Because I switched from Windsurf to... Or from Cursor to Windsurf, like, a few months back. But I switched back.

• 42:28Dan Shipper?

  Okay, so we've got Windsurf is a C. Cursor is an A.

• 42:35Dan Shipper?

  Let's see, Devin?

• 42:41Speaker 01

  It's a B.

• 42:42Dan Shipper?

  B? Why?

• 42:46Speaker 01

  It's like, it's not as integrated, a little bit hard to set up. And the code quality is... Like, it's not as well-rounded as Cursor or Claude Code. I don't know if they use Claude for the background. But like, it's not as usable as the others.

• 43:08Dan Shipper?

  Charlie?

• 43:11Speaker 01

  Charlie is like for code reviews. So we use Charlie for code reviews mostly. So I haven't really used it as an agent as much. I think Charlie as an agent is B, but it's A as a code reviewer. Like, I really like the code reviews it does. So that's interesting. Like, it's really good at something.

• 43:35Dan Shipper?

  And then what about Friday?

• 43:38Speaker 01

  I put Friday...

• 43:43Speaker 01

  Higher than Cursor, maybe between S and A. And it's funny, because they don't even use Claude 4 yet. They're still, like, they're still working on how how they like really make it work well. It's 3.7, but like, why I like it there? It's definitely different than Claude Code, but Friday has a very opinionated way of working. And, and I love their opinions and it really works well. And it just does it like you give, give an issue, they make a plan, you approve and it does it. It creates a pull request and I've, I've seen it do this stuff that I couldn't do with Claude Code.

• 44:28Speaker 01

  Like, for example, implement this Figma design. It just one shot at a Figma design for the assistant. And, and I've seen moments where more, multiple moments like that, where it did things where like, wow, okay, this, I taste the future, which is really unique and it's a small team as well. So really cool.

• 44:48Dan Shipper?

  Codex?

• 44:50Speaker 01

  Um, this is B for me.

• 44:56Dan Shipper?

  All right, Codex is a B. Copilot?

• 45:02Speaker 01

  Uh, I haven't used Copilot.

• 45:06Dan Shipper?

  You never used GitHub Copilot?

• 45:08Speaker 01

  No.

• 45:10Speaker 01

  I mean, I used it three years ago, but I like, no, I, I, okay. Let's be fair, I tried it maybe a half a year ago and after one second I stopped using it.

• 45:22Dan Shipper?

  So where do you, where do you rank it?

• 45:26Speaker 01

  D, like it was not agentic, but, but I mean, I should try the new version for sure.

• 45:32Dan Shipper?

  We have not tried, yeah, we haven't tried the, the agentic Copilot. So that's, that's not totally fair, but, um, okay. Uh, are we missing anything? I feel like we are.

• 45:42Speaker 01

  Claude, Claude Code.

• 45:43Dan Shipper?

  Obviously Claude Code, but I assume S tier, baby.

• 45:49Speaker 01

  We have, uh, Factory as well.

• 45:52Dan Shipper?

  Oh yeah, what's, how, where do you rank Factory?

• 45:54Speaker 01

  Uh, it's interesting. Factory with certain things is like better than any others, but it's not my style. It's like Factory is for more enterprise-y people that are very nerdy and want like absolute bangers of code.

• 46:10Speaker 01

  And it's actually good, like multi-repos, stuff like that. It's a little bit hard to use because it's on the web, but also local. So I rated B, maybe a little bit below Codex and Devin. Yeah, but it's like, there is a use for it for sure.

• 46:26Dan Shipper?

  There's something going, there's something good there, but it's maybe not, not for us.

• 46:29Speaker 01

  It's not my thing. Yeah.

• 46:31Dan Shipper?

  Yeah.

• 46:32Speaker 01

  AMP also.

• 46:34Dan Shipper?

  M. What's that?

• 46:35Speaker 01

  AMP. A M P.

• 46:37Dan Shipper?

  AMP. Oh, AMP. Yeah, yeah. How's that?

• 46:40Speaker 01

  Uh, I would put it, uh,

• 46:46Speaker 01

  S tier under Claude Code.

• 46:48Dan Shipper?

  Whoa, another S tier.

• 46:53Speaker 01

  Yes.

• 46:54Dan Shipper?

  All right.

• 46:54Speaker 01

  Why? It's, it's very good at just getting work done. The economics are pretty good, good tools already. Like, like people, people use that tool that build it. They're dog fooding, like you can feel from Claude Code and AMP are developers that love agents and they're just building the best thing and they're trying new things out.

• 47:19Speaker 01

  So yeah, that's it. Let's see.

• 47:23Speaker 02

  This is exactly why Kiran is the big fish.

• 47:30Dan Shipper?

  I mean, you are, yeah. You're stringing them together, like you're using Claude Code and Friday and, and other stuff all at the same time, which is, yeah, the thing that is really cool.

• 47:39Speaker 01

  Yeah, like, like there, yeah, like how I think about, like, I'm, I'm thinking about it more. It's like you're interviewing for a role and you find a developer to like solve a certain problem. I think it's similar with coding agents, like Friday is good at like doing UI now. So if I need UI work, I will go to Friday. If I need to do research, I go to Claude Code.

• 48:02Speaker 01

  And, and yeah, there is a, if, if I want a code review, I use Charlie. Like it's, it's fun and agents work together. You don't need to have one agent. We have Claude Code.

• 48:11Dan Shipper?

  And that's because Charlie like works in GitHub. So you can just like CC Charlie and, and Charlie will do the, the code review on the PR.

• 48:19Speaker 01

  Yeah, so we use GitHub and pull requests and normal developer flows. So humans can hook in. So we can hire someone that's very good at specific thing and review code. And then Claude Code will just do the work. But it's very powerful because it is just an ecosystem that we refined over like 20 years or whatever, like, and it works. So let's lean into that. And that's probably why Copilot will probably be fine, since it's in there already. Yeah.

• 48:52Dan Shipper?

  Wait, you actually did that recently. Like, we had some infrastructure things where, you know, we've handled tons and tons and tons of emails at Cora, so we had some infrastructure issues to work out. And you seemed, I think you brought in someone who's like a real expert and then worked with them in a specific agentic way that you got what you needed from them, but it was less work for them.

• 49:12Speaker 01

  Yeah, yeah. So like, like, there was no issue yet, but we wanted more visibility in, in delivery of like the most important things. And like, I'm not very good at it, or like, I know stuff, but like, let's bring in someone. And what we did, we just had a conversation, like a two-hour call, and I recorded everything. And at the end, I just fed that into Claude and say, okay, can you make two issues, resource issues from this? And like 10 minutes later, I said, okay, here are the issues, can you review them? And he was like, holy, what, what? What?

• 49:49Speaker 01

  Like, this guy, like, he's not an AI skeptic, but he's like, he's, he's very good at what he does. And normally what he does, AI is not good at yet. Because like, there are things AI is not as good at yet. Um, but he was very impressed with it and he had like very good, uh, like comments on it to iterate over it. And like what we basically did, we just iterated more quickly through ideas because we had something to talk about. And then I said the next day when we, he was like, did the human review, like, let's go. I just use Claude Code to implement it. And we sat down and did the code review. So it's like, It's just accelerated what would have taken two weeks, maybe is now in like a few hours, which is really cool.

• 50:34Dan Shipper?

  I love it. Well, there you have it. You've got your tier list of agents. Claude Code takes the cake. We've got AMP coming up, uh, coming up in second and GitHub Copilot, unfortunately, bringing up the rear, but with room for improvement. Once we try out their agentic capabilities. Anything else you guys wanna wanna say or talk about before we, uh, before we end today?

• 50:58Speaker 01

  Everyone should use Claude Code or try it out, even if you're not technical. Subscribe for their max or pro plan. It's only a hundred dollars per month. You have unlimited access. If you're skeptical about being technical, that it's very easy. And I've seen people, a friend of mine, he, he used Cursor and I said, just use Claude Code. It's better. Like, how, how much better can it be? And he said, yes, it's better. And he rebuilt everything he did with Cursor, Vibe coded, uh, into Claude Code. And he's like, yeah, this is great. Uh, he felt that next step and you should, everyone should try it and really push, push their tools. Yeah.

• 51:40Dan Shipper?

  Natasha, any other words of wisdom?

• 51:42Speaker 02

  Just be sure to, uh, check the AI's work at the lowest failing stage. Uh, you want to catch those problems, uh, early.

• 51:51Dan Shipper?

  Yeah, that's, that's a great one. Uh, and also use Cora, um, cora computer. Check it out. It's pretty awesome. We're shipping you things all the time. Uh, thank you both for coming on. This is a true pleasure. I cannot wait to see what else you cook up over the next couple of months and we'll talk soon.

• 52:07Speaker 01

  Thank you. Thank you so much.

• 52:16Speaker 04

  Oh my gosh, folks, you absolutely positively have to smash that like button and subscribe to AI and I. Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard, but instead of gold, it's filled with pure, unadulterated knowledge bombs about ChatGPT. Every episode is a roller coaster of emotions, insights and laughter that will leave you on the edge of your seat craving for more. It's not just a show, it's a journey into the future with Dan Shipper as the captain of the spaceship. So do yourself a favor, hit like, smash subscribe and strap in for the ride of your life. And now, without any further ado, let me just say, Dan, I'm absolutely, hopelessly in love with you.