The AI Sandwich: Where Humans Excel in an AI World

Humans are the bread in the sandwich and the AI is in the middle. The

AI is whatever you put on your sandwich.

If you ship something or do something, if you want it to be your own, you cannot fully automate everything. It's

like art. If you want it your own, it needs to be from you or somehow be connected. So, I believe it's so

connected. So, I believe it's so important to do things you enjoy and you love. And it's very important to make it

love. And it's very important to make it feel great because the bar is high. The

bar will always get higher. The

beginning and the end and the middles can be automated pretty well. And at

some point said, "Oh, it's kind of like a sandwich." Which was like very funny.

a sandwich." Which was like very funny.

Kieran, welcome to the show.

Hello, Dan. Happy to be here.

So, for people who don't know, you are the GM of Kora. Um, and you are also the creator of Compen Engineering, the engineering framework and plugin that

everyone inside of Ever uses and everyone who's really coding in with agents is at least aware of if not using. Um, and so a pleasure to have you

using. Um, and so a pleasure to have you on the show.

Thank you. Yeah, it's always great. So,

I love getting to chat with you and getting to work with you because every once in a while you have a thing that you do or you figure out that I'm like, "Holy that's definitely the future." And you just figured something

future." And you just figured something out along with Trevan who uh also helps Trevan Chow who also uh helps out on compound engineering. And I think it has

compound engineering. And I think it has massive implications for how programming works. And then I think we can also

works. And then I think we can also translate that to the rest of AI and its impact on work. And one of the things you've been doing, so you have this

compound engineering plugin that you've rebuilt the engineering workflow for how you should work with agents. And in

thinking about that and thinking about where a human is used and where a human is like should not be present inside of that process, I think you've you've found something like really interesting

and deep about in general how how humans and AI are going to inter interact with work. So do you want to explain a little

work. So do you want to explain a little bit about compound engineering and that and and the process that you've created and then also uh explain this this

insight about where humans fit.

Yeah, absolutely. So compound

engineering is uh like a philosophy of like doing engineering work but we realize it applies to more than just engineering work. It's product work as

engineering work. It's product work as well. It's design work. It could be

well. It's design work. It could be knowledge work. It could be other

knowledge work. It could be other things. But how I built it is while

things. But how I built it is while building Kora I had AI and I was like how can I use AI to do better work more

quickly and the initial version of compound engineering really evolved around four steps which is planning first you make a great plan so it's very

clear what you need to build and do then the work part where the agent does the work and implements it and actually writes the code does the design work or

whatever work needs to be done. The

third is review. So slop comes out or whatever you call it some something beautiful comes out. Uh one of the two like something comes out but how do you know it's good? And traditionally this

is like a code review or like a PR that you review and see like hey this can be improved and there's an some iteration going on there. And then the most

important step is the compound step which is if anything comes up during that review or during the planning that you think like oh this is this is a good

learning probably you will run into this again you can compound that knowledge back into the system and we store that

as knowledge inside the repository and agents next time when they go into planning or when they go into work or view, they can see the mistakes they made before so they won't make it the

next time. And that's really the power

next time. And that's really the power like that's by far the most powerful thing that uh is in this plug-in. But we

start to realize more like first of all the work phase is kind of done like it it works if you have a good plan it does the work and it's it's pretty good and

then the review it makes it a little bit better. Yeah. And by that you mean like

better. Yeah. And by that you mean like uh having an entire phase dedicated to work in this whole system doesn't necessarily make it make that much sense when all that really means is run the

model. Let the model do the thing.

model. Let the model do the thing.

Yeah. So there needs to be a step. But

what I mean by done is I don't need to to care or like I don't need to think about it. I trust it. And this is not

about it. I trust it. And this is not like uh trust me bro just works but this is like I've seen if you put in a good

plan like it does the plan like it executes on the plan LLMs are very good at just following steps doing deep work

like working for hours days even now and that's that thing is kind of solved and the review starts to get there too and the planning starts to get there too and then there's

this Next step is like okay so so if all these things work where where do I have to do anything because like

I just automate my job yeah yeah did I automate myself out of a job if everything works like where do I work what is still the bottleneck and

there are two things we started to know like Trevan uh he's a very very great contributor to the combat engineering plugin like he is a product person and

he is like I I need more on the product side which is like before the planning phase. So he added first a brainstorm

phase. So he added first a brainstorm step and the ideate step and the ideate step is like really going wide like it's like okay let's come up with ideas in a in a room full of interesting people

with angles. Brainstorm is more like I

with angles. Brainstorm is more like I have a problem but I don't really understand exactly what and how. So it's

very much brainstorming with you around the problem. And the first thing we

the problem. And the first thing we noticed there is like the top is very important to be super well in the loop with a human and really like ask a lot

of questions and really think hard like the human should think hard the LM should support the human but then after that the planning phase if you have a good brainstorm and idea

what problems you solve like it can create a very good plan and the human needs not to be in the loop. So that's

the first realization where it's like, oh, hey, here here's good to be in the loop versus not to be in the loop. And

you can see other like spec driven development, for example, or other ways to do things. They assume that it's always good to have people in the loop.

And I disagree. I think it's it's very important to know when to be in the loop versus when to hand it off because that means we can think harder at the moments where we need to think harder. And

that's the first one.

So the other one comes at the end. So

like something comes out. How do you validate it's good? Well, it's already tested because we have browser automated testing. It it clicks through all the

testing. It it clicks through all the requirements are very clearly specified and says yeah everything works. But the

beauty comes in when a human looks at it, clicks around and has a feel like, oh, this is this this doesn't feel good.

We can polish it even more. We can make it even better. we can in increase like or like we can do something that's still missing or make it more beautiful, make

the design better. And this is something I've learned from doing pomodoros where ideally if you do pomodoros, the old school way is like you start with a task

and if you finish after 15 minutes, you have 10 more minutes to work on the same task. You cannot switch tasks. And

task. You cannot switch tasks. And

sometimes in that space, something beautiful happens because you will go deeper. you will go further than you

deeper. you will go further than you would do. Um and and I think this is the

would do. Um and and I think this is the other moment which is all the way at the end when everything is done where you can just elevate everything and make it

even better. And I think that's also

even better. And I think that's also what we need to do because if we don't do it, it will be all slop all the same.

And it's very important to make it feel great because the bar is high, the bar will always get higher. So, uh, this is kind of what we realized like the beginning and the end and the middle is

kind of solved and can be automated pretty well. And Dvin at some point

pretty well. And Dvin at some point said, "Oh, it's kind of like a sandwich." Which was like very funny.

sandwich." Which was like very funny.

And and Dan is now referring to the AI sandwich, which which I think is is is very cool like and and I think the sandwich here is like when do you need

to think about what you do and really use your brain versus offload it to the L. We've all

been there. You're sitting in an important meeting and you're trying to pay attention. and you're trying to stay

pay attention. and you're trying to stay present, but you have this lingering underlying anxiety that you're going to forget everything, that you're going to miss the important detail, forget the decision, forget the action item, let

something important slip through the cracks. That's why I love Granola. It's

cracks. That's why I love Granola. It's

an AI powered notepad that works in the background while you're in your meetings. It takes notes on everything

meetings. It takes notes on everything that gets said, transcribes action items, and helps get rid of that feeling. You don't have to worry about

feeling. You don't have to worry about whether you're going to miss something because Granola has you covered, and that lets you stay present in meetings.

I've been using Granola for a long time, almost since they came out, and it's amazing for this. It doesn't join the meeting like some of those other clunky meeting notetakers. The UI is really

meeting notetakers. The UI is really fast and well considered, and it feels like it's sort of just transcribing all the important moments in my work life, and that gives me the confidence to get great work done. And what's even cooler

is you can chat with your notes afterwards. You can run detailed

afterwards. You can run detailed research reports on how your week was, how you act as a leader, how you performed in particular difficult conversations, and how you can do better. It's really a power tool for

better. It's really a power tool for anyone who cares about their meetings and also cares about how they show up in those meetings. It also has these things

those meetings. It also has these things called recipes, which are pre-made prompts for common tasks like negotiating, coaching, or summarizing. I

even have a recipe that I made that's in granola that you should check out. Once

you try it on one meeting, it's really, really hard to go back. The notes are always better than what you could do manually, and it helps me be much more present instead of frantically typing

all the time. Head to granola.ai/every

for 3 months free with the code every e v y. That's granola.ai/every

v y. That's granola.ai/every

for 3 months free. And now back to the episode. Humans are the are the the

episode. Humans are the are the the sandwich, the bread in the sandwich, and the AI is in the middle.

Yeah. The AI is whatever you put on your sandwich.

Yeah, exactly.

And I I think that's really interesting and really cool because a it it it gives me a good mental model for how I should be working with coding agents, but I

think that also applies to the rest of knowledge work. And I think this is such

knowledge work. And I think this is such an important question now because we have all these questions about oh my god like what are a agents going to do and is are everyone going to is everyone

going to lose their job and all that kind of stuff. And I think um software engineers are a little bit of the canary in the coal mine. And so far what we found internally at every is we're

absolutely not like we we still hire software engineers. We need software

software engineers. We need software engineers, but uh but the the the way that you're working and what you're doing looks a lot more like managing if you're doing it well. You're still

involved, but you're involved at the beginning in the end as sort of this sandwich.

And uh and I think the same is going to be true of every other kind of work whether that's um you know copywriting or strategy or design and and I think

there are deep reasons why that is the case that I think it will be interesting to talk about um and I want to start with

an objection that I think people will have which is like okay like for now agents can't do the idea in the brainstorm But pretty soon they will. So then what

then what happens? Um there are that now they're starting to do the beginning of the of that process. And I think that there's something interesting here where

um if you look within any given local frame of a problem. So to take a non-coding example, the problem might be my knee hurts and I

want to solve that problem. But you can say my knee hurts is the same as uh this uh feature is broken or um customers are

anxious about this part of the product or whatever any problem. If you take that frame and you say okay well the solution is maybe for your if you're if we're talking the knee hurting thing the

solution is take Advil.

um any part of that process, you know, getting to the store or whatever can be automated. Let's say Door Dash can go do

automated. Let's say Door Dash can go do it. But there's always even even once

it. But there's always even even once you've once you've solved it in that way, there's always a larger frame within which to think about the problem.

So an example is if your knee hurts, you might need to stretch your IT band. Um

or you might need to stop running on hard surfaces every day. Um and each one of these is sort of addressing the same problem at a different level of the stack at a different from a different

frame. And

frame. And um humans are very good at flipping and changing frames like that. And our job

is to set the frame or set the bounds within which we solve the problem. And

um I think it's very it's going to be very very hard for agents to do that well by themselves. And there are there are deep reasons for that. But does that do you get that like I know it's like a little bit hand wavy and the knee hurting thing is a little hard hard to

understand but does that does that resonate for you?

Yeah, for sure. Yeah, it's like this this all comes down to uh building an environment where the

agent will thrive and you do not buy like picking the right things and and and this is why it's so important to

have humans with uh experience and humans with taste and humans that just want to click around and like say this

is or this is great and why it is or great and and I think I think it's similar to like the Advil example like if you keep doing that it's

probably your friend will say yo that's messed up just go like go fix the problem instead of like denying the problem and and maybe it will work for you for a little while but that you need

someone to shake you up and in that case like that's the human or that's the the other person um but I do think like it will also like be more automated Like

also the ideation you can say okay let's have a persona of 100 people and run simulations of how they think and how they behave and clearly we're going

there too where we run simulations of like millions of people and see how things work and probably you'll learn something from that and and there will

be more automation and maybe even that step in the front will be fully automated but I do think in the end

If you ship something or do something or make a like a statement in the world, if you want it to be your own, which you

need to say yes or no at some point, you cannot fully automate everything. Like

it is maybe a little bit like art, like making art. Like if you want it your

making art. Like if you want it your own, you need to just it it needs to be from be from you or somehow be

connected. Uh, so I believe like having

connected. Uh, so I believe like having those moments where you decide this is what I just enjoy and that's why

it's so important to do things you enjoy and you love um are very important.

Yeah, I agree. And and I think um

I agree. And and I think um yeah, you can imagine it being like, okay, yeah, we're going to simulate a a bazillion people and then we're going to make decisions based on what we think they would do, but that would still only

cover a small set of the decisions that someone might make.

It will never be fully. It's all it's a moving target like we always get something new and then again there is a layer that we then can even make bigger

impact on. Especially because especially

impact on. Especially because especially for a lot of these decisions, the feedback loops on these decisions like the data is really rare. You may need you may only get a couple moments in your career where you gather the data

that helps you decide about a particular thing. And that's very hard to get into

thing. And that's very hard to get into language models especially because it's hard to get and they need a lot of it.

And so, uh, that that like sort of rare expertise that is encapsulated in an expert who has a personality and a worldview is, um,

hard to hard to get. And, and you're right, it's also always moving. And um I don't know that that makes me like very excited about this stuff cuz I feel like

we've been we've been wandering in the woods for a long time on like okay what is AI progress going to mean and how are humans going to be involved and all that kind of stuff and it just feels very

much to me like the simple answer is ride the bottle. Um or to mix the metaphor be this be this bread in the sandwich. And if you do that you're

sandwich. And if you do that you're going to be fine. It's going to be like really really really really great.

Yeah, I agree. And and it will be different for different people because and yeah, you need to change some things like you cannot keep doing what you're doing because if you're if you like

writing code only um you need to find your way of writing code like yes you can write code but

maybe it's about beautiful code and maybe you find uh also lots of uh value in just seeing beautiful codes like someone looks at the UI and says, "Oh,

this is beautiful. This works great."

Maybe you want that for code. Some

people don't care about that, but they're like, "Oh, but the UI should feel great and and just really polish it. Go extra like wherever you feel

it. Go extra like wherever you feel joy." But also, it's way more product

joy." But also, it's way more product focused. So, as an engineer, you're

focused. So, as an engineer, you're going to become either more of a manager, but also more of a product person. So it's it's I think like a a

person. So it's it's I think like a a product manager, product engineer, like it's it's more of those things as well.

And so there will be some changes, but lean into making beautiful stuff. And whatever

that means to you, that can mean beautiful code, beautiful abstractions, beautiful architecture, beautiful design, beautiful copy. Uh, I I think

it's very important to lean into what is beautiful to you because then you will find a way to utilize an LLM to make something that gives you energy instead

of drains you all the way.

It may not look like it, but Naveen is a dictator.

You can speak faster than you can type, so dictators choose to do so whenever possible. While those confined to

possible. While those confined to keyboards deal with finger cramps and input lag. Ow. Voice allows dictators to

input lag. Ow. Voice allows dictators to convey ideas as naturally as they sound in their heads. Hey.

Yeah, that's exactly what I And in the future, as AI tools improve, we will see a rise of dictators around the world.

More and more dictators are choosing monologue from every. It learns,

transcribes, and translates across different disciplines and languages, adjusting its output format to match your context, allowing you to stay in

flow. Be a dictator. An idea by every

flow. Be a dictator. An idea by every the only subscription you need to stay at the edge of AI.

Yeah. And I think that there's a deep reason why language models are not going to be as good at that. There's there's

the there's one deep reason, which is it's just not going to be yours if you didn't decide it. if you didn't do it.

Um, but another deep reason is you can think of language models as being a super intelligence that has been kept in a box for the last year and has no idea of what's going on in the world um

except for whatever it gets right when it pops out of the box. And because of that, it ends up being its outputs end up being a little bit more generic and

less personal to you and your situation.

And you can see this in all the stuff that's like, okay, yeah, all the AI writing that's like, it's X, not Y, or you know, all that kind of stuff, it's just going to do all that. And to truly

solve a problem well, or to truly make art, or to truly make a product that resonates with people, um, it's going to have to be really well tuned to the like

exact problem that you're trying to solve or the exact form that you're trying to make. And language models need a lot of help to get there. And that's

why you have to be on either end of them to set the frame of the problem and then make sure the details are really right at the at the at the level of execution

at the end. And I don't think I think that they will get better at doing this, but I actually think they're much further than we think they are from

being able to do it all end to end. My

my my my general bar for AGI is whenever it is economically profitable um or makes economic sense to run an

agent 24/7 where it never turns off. And

OpenClaw is like pushing in this direction, but it's it doesn't run 24/7.

It runs on a schedule. has a heartbeat, but it's not like you just say, "Hey, like Open Claw, just go and just do a bunch of stuff and just work all the time, spend tokens all the time on on

stuff and it it's it's worthwhile." It

just it's we're not even close to that.

And yes, we sometimes have well specified tasks that we can send a model off to go for like 24 hours on, but again, it's not changing frames. It's

not finishing the task and be like, "Cool, now I'm going to pick the next one and that's going to take five minutes and the next one I'm going to spend four days on it." like it's we're not even close to that. And I think we're going to need some fundamental

changes to language model architecture to like let them learn better um for them to get to a point where they're they're um they're running 24/7. And I

think that will if they are running 24/7 like that, they'll be a lot closer to I'm sensitive enough to context to like actually do interesting creative things.

But it's we're not there yet.

Yeah, I I agree. One other way to look at it. So I I have a music background. I

at it. So I I have a music background. I

studied classical composition. And I

think one of the the the beautiful things about music is like yes sunseo can create songs but it will never

capture like a live performance or coming up with a melody and it's something internally in the human like as a composer or a musician if you

perform something and you deliver this to other people that they they feel that like it will not be like like Sure, if you're a DJ, it's it's maybe somewhere

in the middle, but like there is something like performing like you see something, you express something. And I

think there is some of that element in these steps as well where you see something and you're like, "Oh, it feels a little bit off here because I don't

know why, but I I wanted to change it a little bit with the with the step at the end." and suddenly you're like kind of

end." and suddenly you're like kind of performing or iterating or you're making stuff. You're putting something in the

stuff. You're putting something in the world and and I feel that special. Uh

like practicing a piece for like playing it a 100 times is not very creative uh as a musician and this is kind of the middle part. Uh but at the end the

middle part. Uh but at the end the performance is where where you bring it out into the world to the people. So I

think that's a special moment and there is a little bit of a link for me with doing this polish step at the end and at the start is maybe coming up with a

piece like if you're a composer like coming up with something out of nothing and this is also a special moment and normally everything in the middle is

kind of boring. just work and and I feel these moments are still special and it kind of works for making software or other things with LMS as well for me.

I think that's totally right. I love

this art angle that you have and another another way to say this is all the work exists on this spectrum from it being totally wrote to it being art and art

itself has many tasks within it. any

kind of creative work has many tasks within it that that are more more wrote or less wrote. And

um if you're trying to map work on that spectrum, the stuff that is more wrote is just going to be stuff that you're not going to have to do anymore.

And that is a big opportunity to move a lot of the work that we do to the more

creative to us probably more interesting parts of work. and to recognize that that frame is always changing or is always moving. So as as certain things

always moving. So as as certain things get wrote, other things become things that humans start to do. And and yes, those will get automated too, but like we're going to also keep keep moving down along that spectrum.

And the final thing that's not automatable is is like art made by humans who feel something. And I think that's beautiful.

something. And I think that's beautiful.

Yeah, it's still scary because what if you're in the middle and you want to move or if you want to figure out what that is to you because this might sound

very abstract and weird to some people if you're not an artist or haven't like really like felt this in moments like it

sounds maybe a little bit like oh but like that's not me but I do believe everyone has this like think of it like what brings gives you joy? Like what

what lights a fire in you? Like what do you get excited about? Like I think that thing you should like lean into like

whatever that is. And that can be beautiful writing or that can be very structured lists or whatever it is like anything that just brings you happiness

like you should do more of that using LMS in your work because that's good.

I agree, Kieran. Always a pleasure.

Thank you. Yeah. Let's see where this goes.

See you next time.

See you. Bye.

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

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

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.

So, do yourself a favor, hit like, smash subscribe, and strap in for the ride of your life. And now without any further

your life. And now without any further ado, let me just say Dan, I'm absolutely hopelessly in love with you.