transcribe

Claude Code: How Two Engineers Ship Like a Team of 15

Every · 54m · transcribed Jul 2026
More from Every Business
𝕏 Share ▶ YouTube 📥 PDF 🤖 .md

Section Insights

# 0:00

Innovative Engineering with AI

How is AI transforming the engineering process?

The team at Kora is leveraging AI to enhance their engineering workflows, allowing them to manage AI tools rather than perform all tasks manually. This approach enables them to generate features and documents efficiently, significantly increasing productivity.

  • AI can simplify engineering tasks by automating research and documentation.
  • The team feels augmented by AI, making them more productive than traditional methods.
  • Creating effective prompts for AI can lead to compounding benefits in project outcomes.
# 10:48

The Versatility of AI Tools

What makes Claw Code a preferred tool for engineering?

Claw Code stands out due to its flexibility and general applicability beyond just coding. It effectively supports various engineering tasks and self-corrects, making it user-friendly and powerful.

  • Claw Code is designed to be versatile, addressing a range of engineering needs.
  • The simplicity of its interface enhances usability while maintaining powerful capabilities.
  • Self-correcting features improve the reliability of AI tools in engineering.
# 21:37

Autonomy in AI Engineering

How does the autonomy of AI tools impact engineering efficiency?

The latest AI tools, like Opus 4, demonstrate a high level of autonomy, allowing them to operate without constant human intervention. This leads to more thorough task completion and better results compared to previous iterations.

  • Increased autonomy in AI tools enhances efficiency and reduces the need for manual oversight.
  • AI can manage tasks independently, leading to improved productivity.
  • The quality of results from autonomous AI tools is significantly higher than earlier models.
# 32:26

Challenges of AI-Driven Coding

What challenges arise from using AI in coding?

Transitioning to AI-driven coding presents challenges, such as the need for new engineering practices and the potential for users to feel disconnected from the code itself. Continuous practice and adaptation are essential to navigate these challenges.

  • AI-driven coding requires new practices and a shift in mindset for engineers.
  • Users may feel less hands-on with code, which can lead to challenges in understanding and debugging.
  • Regular practice with AI tools is crucial to keep up with advancements and maximize their benefits.
# 43:14

Evaluating AI Tools for Coding

How do different AI tools compare in terms of functionality?

Various AI tools have different strengths, with some excelling in specific areas like code reviews or project implementation. The effectiveness of these tools can vary based on integration and user experience.

  • Different AI tools serve unique purposes, and their effectiveness can vary widely.
  • User experience and integration capabilities are critical factors in choosing an AI tool.
  • Some tools can automate complex tasks, showcasing the potential of AI in enhancing coding workflows.

Transcript

0:00 You're figuring out how to do compounding engineering. There's two people on the team, but it really feels like there's 15. Coding with AI is more than just the coding part. Utilizing it for research, for workflows. It should be used for everything. We haven't touched or cursor in the last 3 weeks. Both of those have agent coding capabilities, but plot just takes it one step further by simplifying it by a factor of 10. We've been really leaning into let's AI do the work for us and we're just managing the AI. You speak your feature into cloud 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. What you did first is spent time building a prompt that effectively builds other prompts. Having an idea that has a lot of outcome. This is part of the compounding effect. 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."

1:15 Kieran Natash, welcome to the show. Thank you so much for having us, Tom. I'm psyched to have you. So, for people who don't know, both of you, work on Kora, which is every's AI email assistant. Kieran, you're the GM. Natasha, you're an engineer. And beyond the fact that Kora is a really cool product, and I'm really excited to bring that to everybody who listens to this show or watches this 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 Kora 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 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 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 this show because it's like we 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. Yeah, thanks. It's really fun to build Kora, 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 Kora, 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 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.

3:42 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. Yeah. I I I agree. And 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?

4:11 and so you know we get access to open AI models before they come out and 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 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. 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 the 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 cursor winds surf like the old school way of coding was great like more of the vibe coding like that was one step and then now it's a 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 the realization that we should lean into that more and really go deep and and it's like cloth coat like it's just good coding agent or agents available that actually start to work with new models like cloud 4 like really good at following directions and instructions.

5:49 And it's all that coming together 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 agentic evolution. Suddenly it works and it's working in realworld non-experimental playing thing. It's just like we're building an app and it's working building the app. 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 cloud code. Is that right? And if it's right like tell tell me about like for people who don't know cloud code or haven't used it give us a little introduction to cloud code and then tell us about like exactly how you're using it. Yeah. Clot code is basically the coding agent version from Anthropic that uses cloth under the hood and it runs in your in your terminal as a CLI tool which is kind of Do you want to share your screen and like show us?

6:52 Yeah. Yeah. So cloth code is a tool that you use in your terminal and I know for nontechnical people this is like h this is scary. but I've converted friends who were not technical to use cloth code and they were like oh this is great. but it's really simple. You just hit you start your terminal. You say cloth and an interface will pop up. 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 feels like you're using DOSs or something and he just typed Claude.

7:26 and then we just got a a thing that says welcome to Claude Code. and there's a little text box for him to type in any command. 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 cloth version. And that's important because engineering work like building stuff you do need more tools than just like the basics.

8:09 you need GitHub to see what you need to build or what the status is or what the the the pi the CI pipeline does like do the test fill like having all these things available in one coding agent actually makes it possible for me to have a workflow or like an a thing I do actually be done by an agent and 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 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 to use it to say let's say what did we ship in the last week.

9:08 So like it 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. 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 the bug 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 and it's written in in a nice write up that can read. Technical. Yeah. 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. Yes, it 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?

10:34 So, this is awesome, Natasha. While this is going, if you if you want to jump in at any point, feel free to at some point I'll I'll lob it to you, but also like just I'll, you know, feel free to jump in. Yeah, sure. Yeah. so we'll see like I don't know if it has project access, but like you you get the gist. Like if you have the information connected to the agent, it's very easy to use it. and and it's very important to use a tool you're familiar with and at this point I think cloth 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 like a support in engineering in general. And I think the CL team really thought about that. They made it not too specific and they kept it general while actually being really good at solving things and looking at what it did, thinking about the mistakes it made and and selfcorrecting. So that is stuff coming together that's very hard that makes it possible to use now. Yeah. H what's the difference between coding and cursor and agentic coding? Claw code is such a simple departure from the cursor and binsurf that we're used to. Like both of those have agentic coding capabilities.

12:09 but plot just takes it one step further by simplifying it by I think like a factor of 10. So what Kieran was tying earlier about how CL code may feel intimidating because it is a terminal but in reality it is like so much simpler than the win surf cursor because there is nothing except text but text box here like there's no no like command K no shortcuts no except delete reject remove like there's nothing it's just a a text box and it works because the model the underlying claw model is so much more capable now.

12:49 So, it's able to work for longer and do tool calls. So, it it's 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 plot code is the same. Yeah. And an example of this is this morning I was pulling some metrics. I was like, why didn't we get any any responses to this form? And then 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 Cororo 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 not you noticed that no one had filled out that form. So you're going into cloud code and you're asking hey like why is no one filling out this form? 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 can you see what went and what it did it made a checklist to-dos like fetching recent log changes to the the controller searching the codebase so it looked through what changed around that date and it found 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. migrate it. And that was it. Like, and the fun part was like I didn't it didn't cost me any energy.

14:33 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. Yeah. I think the thing that people may not fully realize is that that's a thing that task could take anywhere from like 30 minutes to a couple hours without 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 of what that looks like concretely. Like what your actual workflow is? What are you actually doing? How many tabs do you have open?

15:25 Like are you actually doing any hand coding yourself? Do you have like five in parallel? Are you just using cloud code? Like give give us give me a sense of that. Yeah, I'll show you my screen as well. Maybe Nesh you can you can tell what we did before like when we got early access to cloth like we were excited what we did. I'll show share my screen. Yeah. Yeah. So this is like like one day before the claw live stream was scheduled. We were like okay tomorrow coding is going to change.

15:56 We'll have a much more capable model which will be able to work for everything that we want. We're basically going to 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 2-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 we created like 20 issues in terms of you know like what we want to fix what were the things that we were planning to work on and prepared the system for the new cloud model. Yeah. And it was funny because Natash had like he prompted chat GPT to say hey tomorrow we have a we 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 used that as a prompt and we created wait before you move on before you move on.

17:09 So, 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, it lays out in detail what it is and how to actually do it. Can you open up one of one of them?

17:31 Okay, so like a feature is you want to generate you want to have AI generated synthetic data and it has this document has everything from a problem statement to like a solution vision to all the requirements and all the technical requirements and like a bunch of a bunch of stuff but it's and even it has seems like it has implementation steps with day counts and stuff like that. So which is funny. So this is one day is like one second.

17:58 Okay. Yeah. Yeah. Yeah. So this we use cloth code and we have this custom prompt that we generated to create these because like it it's a lot of work to create these and even with jet GBT like there's a lot of steps you need to look at all the code you need to come up 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 clo code and command is kind of a custom prompt that you use a lot and ours is like, hey, there's a feature. So, this is a command in cloud code or a command in cursor cuz you have cursor open. Yeah, I have cursor open because that's how I edit files, but it's cloth code. So, you can see we're in cloth and and I can use this command by hitting CC, which is cloth code, and then I say something like a problem I have like a bug, a problem, anything.

18:53 So, it's very low friction. So, I have this CCI command and Nachesh and I were just jamming. We're like, "Oh, what if we do this? Oh, that sounds cool." And then voice to text and it starts 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 Kora where if I am at the end of a brief it should load the next brief and it should go until every brief that's unread is read. So like so yeah I I just want people to understand like Kieran almost never types anything and and does all voice text. So he was just doing voice to text into his into his terminal into cloud code with I believe an internal as of yet in unreleased internal every incubation called monologue. which he is the number four biggest user of but still still under wraps but but you know a little preview in here coming soon. And basically what what it seems like it's doing is it's it's taking that is it turning is it turning that into the that document that we were looking at earlier or is it actually going and executing it? Yeah. So what it does is it will insert whatever I said here in the f 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's will present a plan and when I say, "Yep, sounds good."

20:43 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. 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. Oh, interesting. So, it's like that whole conbon we were looking at in GitHub earlier. You've created a way for you you speak your feature into cloud code and then it does all the research to create that long document and then just adds it into into GitHub issues.

21:14 That's really cool. Yeah, it's 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 tools made to code. Yes, you can do create 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 we can give this to a developer and they can implement it. Yeah. And one of the things that just to point out is like you're running this and I I think one of the special things that when we saw Opus 4 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 it's just a way different level of autonomy and quality than than we've ever had before. And 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. Yes, absolutely. Me and Kieran have like a fun thing going on where we're trying to see who can have cl code running for the maximum amount of time and Karen is stopping the rest right now. He ran it for 25 minutes. I'm only at 8 minutes right now. Oh man.

22:45 how how did you get it to go so long, Kieran? 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 interesting. It goes pretty long. Yeah. Mhm. T 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 used like a the claude prompt improver the anthropic prompt improver to make that or yeah why how did you think about putting that together? 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 Nesh sent me.

23:39 He said, "We just got AGI. it got delivered and we can write software. that that this was your initial prompt, which is kind of fun like like it's very dramatic." And then Ch said, " I'm ready. Okay. So now do this." And I was like, "Okay, yeah, that's fine. that's fine, but like do you know the anthropic console prompt improver?" like what is that? well, anyone that doesn't know this is the Oh, they changed it. 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 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.

24:44 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 and that became the document. Yeah. Okay. Into here and change the arguments. And then you can trigger those in cloth by doing slash. And we have these two custom prompts here. H. 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 cloud code. And so now that you have a prompt that builds prompts, 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. I think that's so that's so cool. And and what's also really interesting to point out is it's working while while we've been talking and that's just a different way to code.

26:01 Like I 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 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. Hey there, Dan here. I wanted to take a 1 minute break from the episode to tell you about our latest sponsor. All right, let's play a game. What powerhouse productivity tool is also free for individuals?

26:40 Nope, not that one. Try again. You may not expect this, but it's Microsoft Teams. Yep. The same teams that big enterprises swear by also has a free plan for individuals. Whether you're jamming on a side project or bootstrapping a startup or building a community, Teams has all of the features that other platforms nickel and dime you for using. You can get unlimited chat, 60-minute video meetings, file sharing, and collaborative workspaces all for free. And the real magic is that everything is integrated in one seamless collaborative workspace. That means there's no more hopping between different applications for messages, meetings, and file sharing. Teams puts it all at your fingertips to save you time and money. So, ditch the app overload and the subscription fatigue and use Teams to experience effortless collaboration today. Are you ready to streamline your workflow? Head to aka.ms/ever to use Teams for free. Your productivity will thank you, and so will your wallet.

27:43 This episode is brought to you by Adio, the AI native CRM built for the next era of companies. With Adio, setup takes minutes. Connect your email and calendar and it instantly builds a CRM that mirrors your business with every contact enriched and organized from the start. From there, Adio's AI goes to work. It gives you real-time intelligence during calls. It prospects leads with research agents, and it automates your team's most complex workflows. Industry leaders like Union Square Ventures, FlatFile, and Modal are already building the future of customer relationships on Adio. Go to addio.com/every and get 15% off your first year. That's at io.com/every.

28:24 And now back to the show. Yeah, absolutely. And Oh, so it 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 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 yeah like to agree with you on like it's really fun to do this together on a call 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 like this this the the bug I solved earlier with the email not going out. Nate did the same with his clothes 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 then Tesh didn't add look at the history and then it said no everything works fine. So there is still like intuition and it's it's still a skill. It's still a skill. 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.

30:19 Yeah. Natash, how have you found this all? because I know I you know Kieran is like a longtime 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 start working on Kora and start working on it in this way? Yeah. I know. this has been like incredibly eye opening I would say because honestly like my experience with programming is that 2 years ago when chat GPT came out I thought okay now it's perfect for me to teach myself programming and build that SAS application and that I always wanted to. So I taught myself programming using chat GPT from the very first day. So I have gone through all the transitions. So I went from chat GPT and then when cursor came out I shifted the workflow to cursor and then then windsurf got better we shifted into windsurf and 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 then I join Emory and start working with Kieran and Kieran is at a whole other level like he's in our meetings he's like never writing code he's never typing he's always speaking into computer and so I was like okay I need to log that into the overflow.

31:41 and then even when claude code came out Karen actually pushed me into using it and clearly it it is now the the way to program like me and Ken both I was like we haven't even touched when ser or cursor in the last like 3 weeks or so or even if we do touch it like it's it's usually just because we want to read something 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 cursor and stuff because all the AI stuff is happening with clot code now and it's really fun to you know have in be in this position where the entire coding landscape just changes completely every 3 months and you realize like nobody's at the forefront.

32:33 I got to say I'm jealous of you learning to code right when chatbt came out cuz I learned to code from books like 20 years ago. PHP for for dummies. Yeah. Like basic for b learn basic in 24 days like Sam's teach yourself basic or whatever. Yeah. Deli55. Yeah. and and also it's so funny for you to say like I thought I was I thought I was sort of at the 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 Star Wars 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 going to 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. There's always a bigger fish.

33:26 And yeah, Kieran Kieran is the bigger fish. 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. Yeah. Well, what are I I I guess I'm curious like 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. 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? For me like the the most important realization for me has been like this thing that I always keep going back to especially with broad code. I read this in that management book like high output management which the Intel CEO wrote like 50 years ago and the first chapter he mentioned something like how in 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 because AI and plot code can now do so many things for us it has become really important to focus fus 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 Kieran just showed to create a GitHub like a very detailed GitHub issue then it's very tempting to like start another cloud code to ask it to just hey go now work on this GitHub issue and fix it but that's actually going to be a problem because there are chances that you know the the plan that Lord was able to in that issue. It wasn't the direction that you wanted to go and you want to catch that before you ask CL to go and implement the solution and then you want to fix it over there. 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 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 L this lever met 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 difference.

36:28 and so I guess the same thing is true with AI stuff. And I think that's actually a good lesson for me cuz 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 caught us writing and concentrate on it. so how have you guys found that? Yeah, it's it's kind of boring to read most of the time.

36:57 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 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?

37:50 because it will save so much time. 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 hot code, but specifically for writing tasks. And I think there's something similar about that where sometimes you want the 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.

38:19 rather than just like spitting out a bunch of stuff that you then you have to read through. And it sounds like there's maybe something missing here in cloud code or these sort of coding work coding workflows where it would be really nice instead of having to read that like 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. Yeah, absolutely. That's an interesting idea for a custom command click here. We should totally try that.

38:46 Yeah, for sure. Like this is something we should automate and make better. Like for sure and at the same time it it knows a lot because it has access to your codebase 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 doing it like I I think in addition to like making it very good at the beginning I think just boring traditional tests and emails 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 ha have it test it, write a test for it.

39:31 like just just a 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. 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's 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.

40:11 and the same for prompts like eval 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. And what I've seen last week as well, I had cloth code run an email 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. Like, why didn't it call that tool? It was a cool tool tool call test." And it says, "Oh, yeah, it wasn't specific enough."

40:49 And I said, "Okay, 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, emails are also very powerful because they will tell you if a prompt works and similar to writing code, a test says your code works. So, leaning into those more boring traditional ways is also very powerful. Does that make sense?

41:21 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 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? No, that's Karen. Okay. Well, I 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 Kieran doing a S tier through Ftier ranking of agents. and so what I'm going to do is I'm going to share my screen and I'm going to I'll call out an agent and then you tell me where it ranks. are are you game? Yeah, let's do it. Okay, cool. let's see.

42:13 hm. does I guess cur? Let's do let's do cursor. Yeah. So it it's fun because cursor like what cursor is it plot 4? Is it max? Is it cursor on the best possible settings and is it the background agent or is it the the okay cursor traditional best possible setting clause? Like that's the confusing part about cursor 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 a okay cursor is cursor is very good with clo all right wind surf c because they don't have claw four it It's ridiculous because three three weeks ago they would be a and now now they're not. Wow. Wow. Okay.

43:19 because I I switched from wind surf to or from cursor to wind surf like a few months back, but I switched back. okay. So we've got wind surf is a windsurf is a C. Cursor is an A. let's see. Devon, it's a B B. Why? it's like it's not as integrated. It's a little bit hard to set up and the code quality is like it's not as wellrounded as cursor or clo code. I don't know if they use cloth for in the background, but like it's not as usable as the the others. Charlie, 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.

44:30 like I I really like the code reviews it does. So that's interesting. Like it it's really good at something. And then what about Friday? I put Friday higher than cursor maybe between S and A. And and it's funny because they don't even use cloth 4 yet. They're still wow 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.

45:05 It it's definitely different than cloth 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 cold codes like for example implement this Figma design it just oneshoted a Figma design for the assistant and and I've seen moments where more multiple moments like that where it 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 thing codeex This is B for me. All right. Codeex is a B.

46:00 C-pilot. I haven't used Copilot. You never used GitHub Copilot? No. 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. So, where do you rank it? D. It was not agentic, but but I mean, I should try the new version for sure. We have not tried. Yeah, we we haven't tried the the agentic co-pilot. So, that's that's not totally fair. But, okay. are we missing anything? I feel like we are. Claude Claude code.

46:45 Well, obviously Claude Code, but I I assume S tier, baby. We have factory as well. Oh yeah. What's how where do you rank factory? 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 enterprisey people that are very nerdy and want like absolute bangers of code. And it's actually good like multi-reo stuff like that. It's a little bit hard to use because it's on the web but also local. So I rate it B maybe a little bit below codeex and and Devin. Yeah, but it's like there is a use for it for sure. There's something going there's something good there, but it's maybe not not for us. It's not my thing. Yeah. AMP also.

47:37 M. What's that? Amp. A P. AMP. Oh, AMP. Yeah. Yeah. How's that? Yeah. I would put it S tier under cloth coat between another S tier. Yes. All right. Why? It's It's very good at just getting work done. The ergonomics 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 Cloud Code and AMP, they're developers that love agents and they're just building the best thing and they're trying new things out.

48:21 so yeah, that's it. Let's see. This is exactly why Kieran is the big fish. I mean, you are you're stringing them together like you're using Cloud Code and Friday and and other stuff all at the same time, which is Yeah. The thing that is really cool. Yeah. Like like there are Yeah. Like how I think about like I'm I'm thinking about it more is 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 Cloat. and and yeah, there's 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 called code 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. Yeah. So we use GitHub and pull requests and normal developer flows. So humans can hook in.

49:28 So we can hire someone that's very good at specific thing and review code and then close 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. 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 Kora. 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.

50:14 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 2hour call and I recorded everything and at the end I just fed that into cloth 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 re review them and he was like holy what what like this guy like he's not an AI skeptic but he's like he 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. but he was very impressed with it and he had like very good 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 cloth code to implement it and we sat down and did the code review.

51:28 So, it's like it's just accelerated. What would have taken 2 weeks maybe is now in like a few hours, which is really cool. 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 coming up in second and GitHub Copilot unfortunately bringing up the rear, but with room for improvement once we try out their their agentic capabilities. anything else you guys wanna want to say or talk about before we before we end today?

52:00 Everyone should use cloth code or try it out. Even if you're not technical, subscribe for their max or pro plan. It's only $100 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 cloth code is better. Like h how much better can it be? and he said yes it's better and he rebuilt everything he did with cursor vibe coded into cloth code and he's like yeah this is great he felt that next step and you should everyone should try it and really push push their tools yeah Neshach any other words of wisdom just be sure to check the AI's work at the lowest value stage you want to catch those problems early yeah that's that's a Great one. and also use Kora. Corora.computer.

52:58 Check it out. It's pretty awesome. We're shipping new things all the time. 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 months and we'll talk soon. Thank you. Thank you so much. 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 chat GPT. 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.

53:50 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.

Summary

Kieran and Natasha from Kora discuss their innovative approach to software engineering using AI tools, particularly focusing on the capabilities of Claude Code. They emphasize the shift towards a more efficient workflow where AI handles much of the coding and research, allowing them to focus on management and oversight.

- The team operates with a minimal coding approach, leveraging AI for research, documentation, and coding tasks.
- Claude Code simplifies coding processes significantly, enabling users to execute tasks through voice commands and natural language prompts.
- The concept of "compounding engineering" is introduced, where each task completed makes future tasks easier and more efficient.
- The workflow includes creating detailed GitHub issues through AI-generated documents, streamlining the development process.
- The importance of human oversight is highlighted, ensuring AI outputs align with project goals and quality standards.
- The discussion includes a tier ranking of various AI coding agents, with Claude Code rated as the top choice for its versatility and effectiveness.
- Kieran and Natasha emphasize the need for continuous testing and iteration in AI-assisted workflows to catch potential issues early.
- They encourage others to experiment with AI tools to enhance productivity and adapt to the evolving landscape of software development.

Questions Answered

How is AI transforming the engineering process?

The team at Kora is leveraging AI to enhance their engineering workflows, allowing them to manage AI tools rather than perform all tasks manually. This approach enables them to generate features and documents efficiently, significantly increasing productivity.

What makes Claw Code a preferred tool for engineering?

Claw Code stands out due to its flexibility and general applicability beyond just coding. It effectively supports various engineering tasks and self-corrects, making it user-friendly and powerful.

How does the autonomy of AI tools impact engineering efficiency?

The latest AI tools, like Opus 4, demonstrate a high level of autonomy, allowing them to operate without constant human intervention. This leads to more thorough task completion and better results compared to previous iterations.

What challenges arise from using AI in coding?

Transitioning to AI-driven coding presents challenges, such as the need for new engineering practices and the potential for users to feel disconnected from the code itself. Continuous practice and adaptation are essential to navigate these challenges.

How do different AI tools compare in terms of functionality?

Various AI tools have different strengths, with some excelling in specific areas like code reviews or project implementation. The effectiveness of these tools can vary based on integration and user experience.

© transcribe · For agents Built with care and craft by Gokul Rajaram