The Era of Compound Engineering — Kieran Klaassen, Every/Cora

I want to start with saying I haven't I want to start with saying I haven't written a single line of code this year. written a single line of code this year. written a single line of code this year. Um, maybe I haven't even looked at most Um, maybe I haven't even looked at most Um, maybe I haven't even looked at most of it yet. I do ship. Uh, I have a of it yet. I do ship. Uh, I have a of it yet. I do ship. Uh, I have a product I built that thousands of people product I built that thousands of people product I built that thousands of people use and trust with their email inbox, use and trust with their email inbox, use and trust with their email inbox, which is amazing. which is amazing. which is amazing. I'm actually proud of the code I ship I'm actually proud of the code I ship I'm actually proud of the code I ship and I'm proud of the product I ship. and I'm proud of the product I ship. and I'm proud of the product I ship. I've been doing this for two years and I've been doing this for two years and I've been doing this for two years and trying to extract my thinking and my trying to extract my thinking and my trying to extract my thinking and my taste into a system that compounds. And taste into a system that compounds. And taste into a system that compounds. And I'm going to share you how I do that. I'm going to share you how I do that. I'm going to share you how I do that. Lots of stuff you hear is like, "Oh, you Lots of stuff you hear is like, "Oh, you Lots of stuff you hear is like, "Oh, you should use this the factory dark factory should use this the factory dark factory should use this the factory dark factory do that blah blah blah all the new hip do that blah blah blah all the new hip do that blah blah blah all the new hip cool things." Uh, what I'm trying to do cool things." Uh, what I'm trying to do cool things." Uh, what I'm trying to do is not that today. I'm going to just is not that today. I'm going to just is not that today. I'm going to just show you how I work and hopefully share show you how I work and hopefully share show you how I work and hopefully share something that you can bring to your something that you can bring to your something that you can bring to your workflow that will outlift trends and workflow that will outlift trends and workflow that will outlift trends and really set yourself up for success for really set yourself up for success for really set yourself up for success for newer models, bigger models. Uh there newer models, bigger models. Uh there newer models, bigger models. Uh there are two halves in this talk. One is why are two halves in this talk. One is why are two halves in this talk. One is why it's so important to compound how I got it's so important to compound how I got it's so important to compound how I got here. So this is for people that maybe here. So this is for people that maybe here. So this is for people that maybe are not at the end of the the are not at the end of the the are not at the end of the the trajectory. It's interesting to see how trajectory. It's interesting to see how trajectory. It's interesting to see how to get there. And then stuff you can run to get there. And then stuff you can run to get there. And then stuff you can run yourself, you can use uh day-to-day to yourself, you can use uh day-to-day to yourself, you can use uh day-to-day to ship, to build, uh to research, to do ship, to build, uh to research, to do ship, to build, uh to research, to do knowledge work even.

knowledge work even. knowledge work even. Hello, I'm Kiran. I work at every is an Hello, I'm Kiran. I work at every is an Hello, I'm Kiran. I work at every is an AI lab for the future of work. And we AI lab for the future of work. And we AI lab for the future of work. And we ask ourselves the question, ask ourselves the question, ask ourselves the question, what's next? And we write about it, we what's next? And we write about it, we what's next? And we write about it, we teach about it, we build. And we have a teach about it, we build. And we have a teach about it, we build. And we have a studio se uh studio um where we have studio se uh studio um where we have studio se uh studio um where we have mostly single engineering teams that mostly single engineering teams that mostly single engineering teams that take a problem they really care about take a problem they really care about take a problem they really care about and use AI to build a product out and and use AI to build a product out and and use AI to build a product out and really leverage that and compounded really leverage that and compounded really leverage that and compounded knowledge is a big way we do that lots knowledge is a big way we do that lots knowledge is a big way we do that lots of loops shipping faster and faster and of loops shipping faster and faster and of loops shipping faster and faster and core as mine is where I invented core as mine is where I invented core as mine is where I invented compound engineering and it's a complete compound engineering and it's a complete compound engineering and it's a complete AI email inbox it's agent native. So AI email inbox it's agent native. So AI email inbox it's agent native. So that means whatever you can do the agent that means whatever you can do the agent that means whatever you can do the agent can do. H it runs on your desktop phone can do. H it runs on your desktop phone can do. H it runs on your desktop phone CLI insight codeex like uh MCPS and I'm CLI insight codeex like uh MCPS and I'm CLI insight codeex like uh MCPS and I'm rebuilding it as version two. Uh so soon rebuilding it as version two. Uh so soon rebuilding it as version two. Uh so soon beta access if you want access just DM beta access if you want access just DM beta access if you want access just DM me talk to me.

me talk to me. me talk to me. The cool part is it's one engineer and I The cool part is it's one engineer and I The cool part is it's one engineer and I have support. I have design support. I have support. I have design support. I have support. I have design support. I have some like database have some like database have some like database hardcore engineering problem support hardcore engineering problem support hardcore engineering problem support like you need some support. Um but I like you need some support. Um but I like you need some support. Um but I built a full email client alone and I've built a full email client alone and I've built a full email client alone and I've only started building this in January only started building this in January only started building this in January this new rebuild. I use reals on the this new rebuild. I use reals on the this new rebuild. I use reals on the back end. I love Ruby React on the front back end. I love Ruby React on the front back end. I love Ruby React on the front end and I own products fully. So I talk end and I own products fully. So I talk end and I own products fully. So I talk to people when something goes down I'm to people when something goes down I'm to people when something goes down I'm the one responsible and it's set up like the one responsible and it's set up like the one responsible and it's set up like this on purpose. I'm an ex VPB of this on purpose. I'm an ex VPB of this on purpose. I'm an ex VPB of engineer and founder and I know how to engineer and founder and I know how to engineer and founder and I know how to hire grow teams all that stuff. But I hire grow teams all that stuff. But I hire grow teams all that stuff. But I wanted to do the opposite with sonnet wanted to do the opposite with sonnet wanted to do the opposite with sonnet 3.5. 3.5. 3.5. I just felt there was something new that I just felt there was something new that I just felt there was something new that was unlocked and I wanted to see how far was unlocked and I wanted to see how far was unlocked and I wanted to see how far can AI go before I actually need to grow can AI go before I actually need to grow can AI go before I actually need to grow the team. And I'm still alone with some the team. And I'm still alone with some the team. And I'm still alone with some support which is cool. So I built Kora support which is cool. So I built Kora support which is cool. So I built Kora and this is what I learned.

and this is what I learned. and this is what I learned. Two years ago I started and the Two years ago I started and the Two years ago I started and the bottleneck by then was code. So it kept bottleneck by then was code. So it kept bottleneck by then was code. So it kept moving and my job changed over the years moving and my job changed over the years moving and my job changed over the years but first there was bad code but first there was bad code but first there was bad code hallucination just stuff that didn't hallucination just stuff that didn't hallucination just stuff that didn't work. I added agents I added skills just work. I added agents I added skills just work. I added agents I added skills just reviewing it. So okay code got good. The reviewing it. So okay code got good. The reviewing it. So okay code got good. The plan was the bottleneck because I could plan was the bottleneck because I could plan was the bottleneck because I could do things but larger things. So whenever do things but larger things. So whenever do things but larger things. So whenever I have a good plan set out, it would do I have a good plan set out, it would do I have a good plan set out, it would do bigger things than just code changes. bigger things than just code changes. bigger things than just code changes. Okay, plans got good. Um the next Okay, plans got good. Um the next Okay, plans got good. Um the next bottleneck was deciding what to build. bottleneck was deciding what to build. bottleneck was deciding what to build. Talking with users, really understanding Talking with users, really understanding Talking with users, really understanding problems you're solving. This is why problems you're solving. This is why problems you're solving. This is why it's so good that you use your own it's so good that you use your own it's so good that you use your own product. You love what you're building product. You love what you're building product. You love what you're building for. for. for. And And And that got really good as well. The scope that got really good as well. The scope that got really good as well. The scope got bigger. AI could help writing uh got bigger. AI could help writing uh got bigger. AI could help writing uh plans. And I kept repeating myself and plans. And I kept repeating myself and plans. And I kept repeating myself and that was annoying. So I figured out that was annoying. So I figured out that was annoying. So I figured out there needs to be some kind of memory there needs to be some kind of memory there needs to be some kind of memory system. So every time um I repeat system. So every time um I repeat system. So every time um I repeat myself, I can say, "Hey, can you make myself, I can say, "Hey, can you make myself, I can say, "Hey, can you make sure to store this knowledge in some sure to store this knowledge in some sure to store this knowledge in some way?" I started with storing this in way?" I started with storing this in way?" I started with storing this in cloth MD, but at some point that became cloth MD, but at some point that became cloth MD, but at some point that became too large. Um, so I built a system that too large. Um, so I built a system that too large. Um, so I built a system that remembers and that's really where remembers and that's really where remembers and that's really where compound engineering came from and you compound engineering came from and you compound engineering came from and you see me go away from typing more towards see me go away from typing more towards see me go away from typing more towards judgment and taste and I think

judgment and taste and I think judgment and taste and I think implementation is mostly solved even implementation is mostly solved even implementation is mostly solved even though you see many people that do though you see many people that do though you see many people that do orchestration dark factories who orchestration dark factories who orchestration dark factories who it kind of works which is cool but the it kind of works which is cool but the it kind of works which is cool but the thing that doesn't work is our judgment thing that doesn't work is our judgment thing that doesn't work is our judgment and our taste. and our taste. and our taste. And And And for me it's really where do I turn my for me it's really where do I turn my for me it's really where do I turn my brain on versus when do I leverage the brain on versus when do I leverage the brain on versus when do I leverage the model and it's where you make judgments model and it's where you make judgments model and it's where you make judgments and it's where you add taste. So where and it's where you add taste. So where and it's where you add taste. So where you think where you iterate where you you think where you iterate where you you think where you iterate where you jam where you brainstorm I extract that jam where you brainstorm I extract that jam where you brainstorm I extract that into a system and if it's extracted into into a system and if it's extracted into into a system and if it's extracted into the system you can move on to bigger the system you can move on to bigger the system you can move on to bigger problems because the next time the AI problems because the next time the AI problems because the next time the AI will come up with a brainstorm it will will come up with a brainstorm it will will come up with a brainstorm it will already include that thinking so you can already include that thinking so you can already include that thinking so you can go on for the next one go on for the next one go on for the next one and I see that one engineer with a and I see that one engineer with a and I see that one engineer with a compounding system just beats teams like compounding system just beats teams like compounding system just beats teams like full teams that use AI full teams that use AI full teams that use AI that don't.

that don't. that don't. This is my loop. It's This is my loop. It's This is my loop. It's it there's more to it than this, but it there's more to it than this, but it there's more to it than this, but this is the overview. Brainstorming, this is the overview. Brainstorming, this is the overview. Brainstorming, planning, working, reviewing, polishing, planning, working, reviewing, polishing, planning, working, reviewing, polishing, compounding, and repeating. And the real compounding, and repeating. And the real compounding, and repeating. And the real trick here is on both ends. It's kind of trick here is on both ends. It's kind of trick here is on both ends. It's kind of the human AI sandwich where the human is the human AI sandwich where the human is the human AI sandwich where the human is the bread and the AI is the middle part. the bread and the AI is the middle part. the bread and the AI is the middle part. And the brain is on on the ends. So the And the brain is on on the ends. So the And the brain is on on the ends. So the start brainstorming where you have to start brainstorming where you have to start brainstorming where you have to decide what to work on what the problem decide what to work on what the problem decide what to work on what the problem is and really understand what you're is and really understand what you're is and really understand what you're trying to do and at the end where your trying to do and at the end where your trying to do and at the end where your taste comes in where you decide this taste comes in where you decide this taste comes in where you decide this looks very good makes me very happy or looks very good makes me very happy or looks very good makes me very happy or we need to raise the bar we need to do we need to raise the bar we need to do we need to raise the bar we need to do better we need to make it more snappy we better we need to make it more snappy we better we need to make it more snappy we need to go optimistic or whatever that need to go optimistic or whatever that need to go optimistic or whatever that is like like delight is like like delight is like like delight and throughout here especially in the and throughout here especially in the and throughout here especially in the brain on parts it's important to extract brain on parts it's important to extract brain on parts it's important to extract the learnings to compound. So that's the learnings to compound. So that's the learnings to compound. So that's basically the loop. basically the loop. basically the loop. You cannot run the middle if it's not You cannot run the middle if it's not You cannot run the middle if it's not set up correctly. And it's very set up correctly. And it's very set up correctly. And it's very important to be able to let go and let important to be able to let go and let important to be able to let go and let the machine rip overnight for many hours the machine rip overnight for many hours the machine rip overnight for many hours in parallel.

in parallel. in parallel. And the only way to be able to do that And the only way to be able to do that And the only way to be able to do that is making sure you spend time on uh on is making sure you spend time on uh on is making sure you spend time on uh on that system. So my rules 50% should go that system. So my rules 50% should go that system. So my rules 50% should go into creating into creating into creating uh the feature just making sure like did uh the feature just making sure like did uh the feature just making sure like did it build the feature? Did it deliver the it build the feature? Did it deliver the it build the feature? Did it deliver the value you set out to do? But 50% of the value you set out to do? But 50% of the value you set out to do? But 50% of the time should go to um teaching the system time should go to um teaching the system time should go to um teaching the system for anything that it did wrong. Can we for anything that it did wrong. Can we for anything that it did wrong. Can we learn something? Can you teach the learn something? Can you teach the learn something? Can you teach the system something? And this is something system something? And this is something system something? And this is something that is kind of hard, but it's very that is kind of hard, but it's very that is kind of hard, but it's very important because it will make the next important because it will make the next important because it will make the next time better. time better. time better. One bonus is because of this extraction One bonus is because of this extraction One bonus is because of this extraction um I store all of this knowledge inside um I store all of this knowledge inside um I store all of this knowledge inside my repository as solution documents and my repository as solution documents and my repository as solution documents and people say oh but tokens and in my people say oh but tokens and in my people say oh but tokens and in my research it's actually more token research it's actually more token research it's actually more token efficient because if you have the right efficient because if you have the right efficient because if you have the right answers and the right solutions already answers and the right solutions already answers and the right solutions already within the token you don't need to do within the token you don't need to do within the token you don't need to do review you don't need to correct you review you don't need to correct you review you don't need to correct you don't need to do deep research across don't need to do deep research across don't need to do deep research across the internet because the token's already the internet because the token's already the internet because the token's already there so it's actually more token there so it's actually more token there so it's actually more token efficient in the long term, which is efficient in the long term, which is efficient in the long term, which is cool. Less research, finding things cool. Less research, finding things cool. Less research, finding things faster.

faster. faster. The real reason why this works is my The real reason why this works is my The real reason why this works is my brain is fixed and AI isn't or less brain is fixed and AI isn't or less brain is fixed and AI isn't or less fixed. And my philosophy is keep fixed. And my philosophy is keep fixed. And my philosophy is keep extracting until the complete middle extracting until the complete middle extracting until the complete middle runs itself and is so freaking good that runs itself and is so freaking good that runs itself and is so freaking good that it will surprise you. it will surprise you. it will surprise you. Um let me show you how this works. Uh so Um let me show you how this works. Uh so Um let me show you how this works. Uh so I have a plugin called the compound I have a plugin called the compound I have a plugin called the compound engineering plugin that you can install engineering plugin that you can install engineering plugin that you can install in whatever tool you use codeexcloud in whatever tool you use codeexcloud in whatever tool you use codeexcloud code cursor plus 10 others and I just code cursor plus 10 others and I just code cursor plus 10 others and I just built this while building Kora shared it built this while building Kora shared it built this while building Kora shared it at some point and now hundreds of at some point and now hundreds of at some point and now hundreds of thousands of people use it daily. So thousands of people use it daily. So thousands of people use it daily. So thank you all for using it if you did. thank you all for using it if you did. thank you all for using it if you did. I'm honored. Um, I never decided this I'm honored. Um, I never decided this I'm honored. Um, I never decided this should be something like hype. It's just should be something like hype. It's just should be something like hype. It's just me using my plug-in shipping code. Uh, me using my plug-in shipping code. Uh, me using my plug-in shipping code. Uh, you can install it wherever. Uh, you can you can install it wherever. Uh, you can you can install it wherever. Uh, you can also create your own version of this, also create your own version of this, also create your own version of this, which could be just storing information which could be just storing information which could be just storing information in files. Uh, however you do it. But let in files. Uh, however you do it. But let in files. Uh, however you do it. But let me show you the plug-in. So, compound me show you the plug-in. So, compound me show you the plug-in. So, compound engineering became compound product as engineering became compound product as engineering became compound product as well. Uh I have a lovely uh well. Uh I have a lovely uh well. Uh I have a lovely uh co-contributor Trevan Chowo who has a co-contributor Trevan Chowo who has a co-contributor Trevan Chowo who has a very good product sense and product very good product sense and product very good product sense and product background. So he brought a lot of background. So he brought a lot of background. So he brought a lot of product thinking and I think compound product thinking and I think compound product thinking and I think compound engineering is really for engineers, engineering is really for engineers, engineering is really for engineers, PMs, designers, even people that do PMs, designers, even people that do PMs, designers, even people that do knowledge work within every love to use knowledge work within every love to use knowledge work within every love to use compound engineering. It's such a uh

compound engineering. It's such a uh compound engineering. It's such a uh like universal uh concept of compounding like universal uh concept of compounding like universal uh concept of compounding knowledge. It doesn't have to be used knowledge. It doesn't have to be used knowledge. It doesn't have to be used for engineers but that's where it came for engineers but that's where it came for engineers but that's where it came from me. So the first demo is from me. So the first demo is from me. So the first demo is um um um it's it's here to activate your brain. it's it's here to activate your brain. it's it's here to activate your brain. So this is called CE ID8 and you can run So this is called CE ID8 and you can run So this is called CE ID8 and you can run it. And here I run it in it's maybe a it. And here I run it in it's maybe a it. And here I run it in it's maybe a little bit small but I say hey I have little bit small but I say hey I have little bit small but I say hey I have Kora version version one. I want to Kora version version one. I want to Kora version version one. I want to upgrade people to version two. Um come upgrade people to version two. Um come upgrade people to version two. Um come up with oh no actually this is look at up with oh no actually this is look at up with oh no actually this is look at all my open open tickets. Tell me what all my open open tickets. Tell me what all my open open tickets. Tell me what to do next. It's a great command. It to do next. It's a great command. It to do next. It's a great command. It will just go through all your issues and will just go through all your issues and will just go through all your issues and you can link linear open like open you can link linear open like open you can link linear open like open source issues on GitHub, Slack, source issues on GitHub, Slack, source issues on GitHub, Slack, intercom. What it will do is it will intercom. What it will do is it will intercom. What it will do is it will generate uh structure from all this mess generate uh structure from all this mess generate uh structure from all this mess and we'll make arguments about what is and we'll make arguments about what is and we'll make arguments about what is good to work on versus not good to work good to work on versus not good to work good to work on versus not good to work on. And the cool part is it will reason on. And the cool part is it will reason on. And the cool part is it will reason about this and the output here is a about this and the output here is a about this and the output here is a clean HTML page that you can share with clean HTML page that you can share with clean HTML page that you can share with the team that you can be inspired by. So the team that you can be inspired by. So the team that you can be inspired by. So this is generation of ids and the cool this is generation of ids and the cool this is generation of ids and the cool part is you can point it to your OKRs part is you can point it to your OKRs part is you can point it to your OKRs you can um get ideiation aligned to your you can um get ideiation aligned to your you can um get ideiation aligned to your strategy and that's kind of how it strategy and that's kind of how it strategy and that's kind of how it compounds. So if you have past compounds. So if you have past compounds. So if you have past experiments or past learnings in your experiments or past learnings in your experiments or past learnings in your repository or a strategy document which repository or a strategy document which repository or a strategy document which you can create with CE strategy, it will you can create with CE strategy, it will you can create with CE strategy, it will score these ids against this knowledge score these ids against this knowledge score these ids against this knowledge already which is really cool. And I've already which is really cool. And I've already which is really cool. And I've seen people dump this uh document inside

seen people dump this uh document inside seen people dump this uh document inside cloth design and say create a PowerPoint cloth design and say create a PowerPoint cloth design and say create a PowerPoint and you get a beautifully designed and you get a beautifully designed and you get a beautifully designed PowerPoint with like XY matrix of where PowerPoint with like XY matrix of where PowerPoint with like XY matrix of where the sweet spot is for what to do for the sweet spot is for what to do for the sweet spot is for what to do for your OKRs which is very low effort for your OKRs which is very low effort for your OKRs which is very low effort for you and very impressive to bring to your you and very impressive to bring to your you and very impressive to bring to your team. team. team. Uh next one is a very simple one. It's Uh next one is a very simple one. It's Uh next one is a very simple one. It's called C do review but is very useful. called C do review but is very useful. called C do review but is very useful. Um, if someone hands you a PRD or some Um, if someone hands you a PRD or some Um, if someone hands you a PRD or some kind of document, run dock review on it kind of document, run dock review on it kind of document, run dock review on it and it comes back with very sharp and it comes back with very sharp and it comes back with very sharp questions. I always like the questions. questions. I always like the questions. questions. I always like the questions. I'm like, "Oh, that's a good question. I I'm like, "Oh, that's a good question. I I'm like, "Oh, that's a good question. I did not think about it." So, either you did not think about it." So, either you did not think about it." So, either you relay this to your colleague or you ask relay this to your colleague or you ask relay this to your colleague or you ask them to answer. You can then compound them to answer. You can then compound them to answer. You can then compound that knowledge after answering with C that knowledge after answering with C that knowledge after answering with C compound so that the next time um this compound so that the next time um this compound so that the next time um this answer is already baked in and it answer is already baked in and it answer is already baked in and it wouldn't ask you it would already know wouldn't ask you it would already know wouldn't ask you it would already know the answer because it's already embedded the answer because it's already embedded the answer because it's already embedded in the system. You can share this with in the system. You can share this with in the system. You can share this with people. You can say oh you can actually people. You can say oh you can actually people. You can say oh you can actually run this yourself as well. This runs run this yourself as well. This runs run this yourself as well. This runs anywhere. So you can do it in co-work as anywhere. So you can do it in co-work as anywhere. So you can do it in co-work as well. It doesn't need to be in cloth well. It doesn't need to be in cloth well. It doesn't need to be in cloth code. Um it's a very simple thing that code. Um it's a very simple thing that code. Um it's a very simple thing that we spend a lot of effort in to make very we spend a lot of effort in to make very we spend a lot of effort in to make very good and it's part of our flow.

good and it's part of our flow. good and it's part of our flow. This my most used one u it's when the ID This my most used one u it's when the ID This my most used one u it's when the ID is too big to describe. So this was the is too big to describe. So this was the is too big to describe. So this was the example of Kora version one to version example of Kora version one to version example of Kora version one to version two. I say c brainstorm. This is a brain two. I say c brainstorm. This is a brain two. I say c brainstorm. This is a brain on command. Uh I know I need to get into on command. Uh I know I need to get into on command. Uh I know I need to get into into the zone. I block off time. I'm not into the zone. I block off time. I'm not into the zone. I block off time. I'm not going to multitask or anything like going to multitask or anything like going to multitask or anything like that. Um, and I run this. So, it pulls that. Um, and I run this. So, it pulls that. Um, and I run this. So, it pulls in compound knowledge. It looks at the in compound knowledge. It looks at the in compound knowledge. It looks at the difference between Kora one and two and, difference between Kora one and two and, difference between Kora one and two and, uh, looks at the personas I've set up. uh, looks at the personas I've set up. uh, looks at the personas I've set up. So, it will see, hey, like certain So, it will see, hey, like certain So, it will see, hey, like certain people need certain things. And it will people need certain things. And it will people need certain things. And it will ask me questions. And it doesn't ask me ask me questions. And it doesn't ask me ask me questions. And it doesn't ask me a lot of questions. It's dialed in to a lot of questions. It's dialed in to a lot of questions. It's dialed in to ask you just the right amount of ask you just the right amount of ask you just the right amount of questions it needs to do the work. It's questions it needs to do the work. It's questions it needs to do the work. It's very easy to get 30 questions and feel, very easy to get 30 questions and feel, very easy to get 30 questions and feel, "Wow, I did so much." But in the end, "Wow, I did so much." But in the end, "Wow, I did so much." But in the end, the goal is not to answer questions. In the goal is not to answer questions. In the goal is not to answer questions. In the end, it's to get the absolute best the end, it's to get the absolute best the end, it's to get the absolute best work out of it. And I think other work out of it. And I think other work out of it. And I think other libraries might over question. H I think libraries might over question. H I think libraries might over question. H I think there's a balance uh to be found there.

there's a balance uh to be found there. there's a balance uh to be found there. So out comes a plan, a brainstorm So out comes a plan, a brainstorm So out comes a plan, a brainstorm document stored and compounded. And then document stored and compounded. And then document stored and compounded. And then my favorite, which is SL LFG, which is my favorite, which is SL LFG, which is my favorite, which is SL LFG, which is basically the loop, the the automation basically the loop, the the automation basically the loop, the the automation loop. And if you like vibe coding/ LFG loop. And if you like vibe coding/ LFG loop. And if you like vibe coding/ LFG something is great as well. It will run something is great as well. It will run something is great as well. It will run for hours. It will do planning work for hours. It will do planning work for hours. It will do planning work review testing. Opens a PR. It will dog review testing. Opens a PR. It will dog review testing. Opens a PR. It will dog food. It will try fix fix things. It food. It will try fix fix things. It food. It will try fix fix things. It will then do a before and after video will then do a before and after video will then do a before and after video screenshot in the pull request. Makes it screenshot in the pull request. Makes it screenshot in the pull request. Makes it super easy for you to then see what super easy for you to then see what super easy for you to then see what happens last if it comes back. So this is last if it comes back. So this is overnight. You can do parallel. There's overnight. You can do parallel. There's overnight. You can do parallel. There's polish. This is the brain on again C polish. This is the brain on again C polish. This is the brain on again C polish. You give it the pull request and polish. You give it the pull request and polish. You give it the pull request and what it will do is it will show you. So what it will do is it will show you. So what it will do is it will show you. So I like to run it in cursor and on the I like to run it in cursor and on the I like to run it in cursor and on the left side I like to run this and it will left side I like to run this and it will left side I like to run this and it will tell me hey this was introduced with tell me hey this was introduced with tell me hey this was introduced with this LFG flow and on the right it will this LFG flow and on the right it will this LFG flow and on the right it will show the product. This is important.

show the product. This is important. show the product. This is important. Sometimes I don't even know what was Sometimes I don't even know what was Sometimes I don't even know what was built because I also have video built because I also have video built because I also have video recordings that I dump into LFG that it recordings that I dump into LFG that it recordings that I dump into LFG that it will then process and analyze and see will then process and analyze and see will then process and analyze and see what went wrong. So sometimes I don't what went wrong. So sometimes I don't what went wrong. So sometimes I don't even know what it was solving for. So even know what it was solving for. So even know what it was solving for. So it's a good primer to know, okay, this it's a good primer to know, okay, this it's a good primer to know, okay, this is what we are here where we are. This is what we are here where we are. This is what we are here where we are. This is what it's solving. This is how I is what it's solving. This is how I is what it's solving. This is how I solved it. And you tell me what do you solved it. And you tell me what do you solved it. And you tell me what do you think? And this is not QA. This is think? And this is not QA. This is think? And this is not QA. This is raising the bar like it should work. If raising the bar like it should work. If raising the bar like it should work. If it doesn't work here, your LFG flow it doesn't work here, your LFG flow it doesn't work here, your LFG flow failed. Um, but you can see here like failed. Um, but you can see here like failed. Um, but you can see here like this works only in this example there is this works only in this example there is this works only in this example there is a mark of a logo mark twice which is not a mark of a logo mark twice which is not a mark of a logo mark twice which is not technically wrong but I don't want two technically wrong but I don't want two technically wrong but I don't want two marks on one page. So in this case I can marks on one page. So in this case I can marks on one page. So in this case I can say hey there are marks two marks here. say hey there are marks two marks here. say hey there are marks two marks here. Can we just make sure we only ever have Can we just make sure we only ever have Can we just make sure we only ever have one and run C compound. So it will one and run C compound. So it will one and run C compound. So it will extract that knowledge, make sure next extract that knowledge, make sure next extract that knowledge, make sure next time when I do design work, it's tagged time when I do design work, it's tagged time when I do design work, it's tagged correctly, it will find that file and uh correctly, it will find that file and uh correctly, it will find that file and uh know not to do that. So that's closing know not to do that. So that's closing know not to do that. So that's closing the loop. You merge it and you learn the loop. You merge it and you learn the loop. You merge it and you learn something.

something. something. So why does compound engineering So why does compound engineering So why does compound engineering resonate with people? I think it's not a resonate with people? I think it's not a resonate with people? I think it's not a very new concept. It's just something very new concept. It's just something very new concept. It's just something how we do software engineering. is just how we do software engineering. is just how we do software engineering. is just now instead of working with teams we use now instead of working with teams we use now instead of working with teams we use with AI we use AI and we leverage that with AI we use AI and we leverage that with AI we use AI and we leverage that and AI is very good at specific things and AI is very good at specific things and AI is very good at specific things especially with large amounts of especially with large amounts of especially with large amounts of knowledge and doing the right thing knowledge and doing the right thing knowledge and doing the right thing especially with latest models so uh if especially with latest models so uh if especially with latest models so uh if you want to do this yourself if you you want to do this yourself if you you want to do this yourself if you don't want to use my plug-in uh make don't want to use my plug-in uh make don't want to use my plug-in uh make sure to extract never repeat if you see sure to extract never repeat if you see sure to extract never repeat if you see yourself repeating yourself make sure to yourself repeating yourself make sure to yourself repeating yourself make sure to extract it somehow make sure it doesn't extract it somehow make sure it doesn't extract it somehow make sure it doesn't happen again make sure that there is a happen again make sure that there is a happen again make sure that there is a middle that can run without you that middle that can run without you that middle that can run without you that does the planning, working, reviewing, does the planning, working, reviewing, does the planning, working, reviewing, and it should be boring. It should just and it should be boring. It should just and it should be boring. It should just work. Uh you should not be needed if work. Uh you should not be needed if work. Uh you should not be needed if you're still needed in the loop. Spend you're still needed in the loop. Spend you're still needed in the loop. Spend time on the middle. Do it manually. Feel time on the middle. Do it manually. Feel time on the middle. Do it manually. Feel where it's off and like iterate until where it's off and like iterate until where it's off and like iterate until you can actually let it go. And if if you can actually let it go. And if if you can actually let it go. And if if you are at a point where you just run you are at a point where you just run you are at a point where you just run something and runs for three hours and something and runs for three hours and something and runs for three hours and it's always good, you know you're there.

it's always good, you know you're there. it's always good, you know you're there. [sighs] It's important to document the [sighs] It's important to document the [sighs] It's important to document the thinking, not the code. This is also thinking, not the code. This is also thinking, not the code. This is also very anti- um developery. It's like yeah very anti- um developery. It's like yeah very anti- um developery. It's like yeah but documentation shouldn't mean the but documentation shouldn't mean the but documentation shouldn't mean the code and like the code is the artifact code and like the code is the artifact code and like the code is the artifact itself but I am of the opinion to itself but I am of the opinion to itself but I am of the opinion to generalize you need reasoning behind why generalize you need reasoning behind why generalize you need reasoning behind why you did something and all these traces you did something and all these traces you did something and all these traces even though they're bad could lead to even though they're bad could lead to even though they're bad could lead to things like hey something happened right things like hey something happened right things like hey something happened right at postmortem what decision was made by at postmortem what decision was made by at postmortem what decision was made by whom or what agent that led to this can whom or what agent that led to this can whom or what agent that led to this can we then turn that into a learning so we we then turn that into a learning so we we then turn that into a learning so we change that behavior for the next time change that behavior for the next time change that behavior for the next time and I've seen it work very well uh and I've seen it work very well uh and I've seen it work very well uh especially with postmortems especially with postmortems especially with postmortems and again every interaction spend 50% of and again every interaction spend 50% of and again every interaction spend 50% of your time to make it better the next your time to make it better the next your time to make it better the next time. So, make sure to build the system time. So, make sure to build the system time. So, make sure to build the system that will remember uh instead of was that will remember uh instead of was that will remember uh instead of was this good, make the system better and this good, make the system better and this good, make the system better and make the system know. And I know it's make the system know. And I know it's make the system know. And I know it's hard like it's just hard to do for hard like it's just hard to do for hard like it's just hard to do for myself and we all know we need to do it, myself and we all know we need to do it, myself and we all know we need to do it, but it's kind of awkward and it's like h but it's kind of awkward and it's like h but it's kind of awkward and it's like h it's it works. It's great. Let's just it's it works. It's great. Let's just it's it works. It's great. Let's just move on. But it's very important and you move on. But it's very important and you move on. But it's very important and you can see the system really go if you do can see the system really go if you do can see the system really go if you do that a lot.

that a lot. that a lot. So the bet is implementation is only So the bet is implementation is only So the bet is implementation is only getting cheaper and judgment is not and getting cheaper and judgment is not and getting cheaper and judgment is not and the future models and systems need to be the future models and systems need to be the future models and systems need to be set up so they have access to this set up so they have access to this set up so they have access to this judgment that we have our taste uh to judgment that we have our taste uh to judgment that we have our taste uh to have more leverage. So that is the have more leverage. So that is the have more leverage. So that is the bottleneck and remember brain at the bottleneck and remember brain at the bottleneck and remember brain at the ends really activate your brain make ends really activate your brain make ends really activate your brain make sure you really understand what you're sure you really understand what you're sure you really understand what you're doing in the start. Don't offload the doing in the start. Don't offload the doing in the start. Don't offload the thinking to the AI. Make sure you truly thinking to the AI. Make sure you truly thinking to the AI. Make sure you truly feel understand what you're doing, the feel understand what you're doing, the feel understand what you're doing, the problem. H let the AI go and at the end problem. H let the AI go and at the end problem. H let the AI go and at the end raise the bar. Make sure you don't fix raise the bar. Make sure you don't fix raise the bar. Make sure you don't fix things. It should be very good at the things. It should be very good at the things. It should be very good at the end, but make sure to raise the bar end, but make sure to raise the bar end, but make sure to raise the bar because we're not shipping shitty code. because we're not shipping shitty code. because we're not shipping shitty code. And your standard should be the next And your standard should be the next And your standard should be the next feature should be easier because you feature should be easier because you feature should be easier because you ship this one. If the next feature is ship this one. If the next feature is ship this one. If the next feature is harder because you added complexity, harder because you added complexity, harder because you added complexity, which is normally how engineering works, which is normally how engineering works, which is normally how engineering works, we're flipping that. The next feature we're flipping that. The next feature we're flipping that. The next feature should be easier to build because you should be easier to build because you should be easier to build because you ship this one.

ship this one. ship this one. I'm Kiran. Uh, check out the plugin. I'm Kiran. Uh, check out the plugin. I'm Kiran. Uh, check out the plugin. It's open source. Please um, contribute. It's open source. Please um, contribute. It's open source. Please um, contribute. PR is welcome. I love PRs from everyone. PR is welcome. I love PRs from everyone. PR is welcome. I love PRs from everyone. Go build your orchestration system. Go Go build your orchestration system. Go Go build your orchestration system. Go build your personal uh, knowledge base build your personal uh, knowledge base build your personal uh, knowledge base that compounds. And thank you. I'll be that compounds. And thank you. I'll be that compounds. And thank you. I'll be hanging around if you have questions and hanging around if you have questions and hanging around if you have questions and enjoy the rest of your day. [applause]