Claude Cowork is here.
And if you understand how to use it, you're going to be able to outperform 99 of people on this planet.
It is an easy way for you to use Claude Code.
You might have heard of Claude Code.
It's gone viral.
But the problem is it feels technical.
You have to go into the terminal.
And it's not fun for a lot of beginners.
So Claude has come up with Cowork.
And it's a brand new product that harnesses the power of Claude code in a UI that is simple, that anyone could use, that your dad can use, your mom could use.
Hey, even you can use.
So in this episode, I brought on Boris, the maker of this product.
I'm so excited that he shows you the best practices for how to use Cowork.
Claude Cowork, and at the end, how he sets up his Claude Code to get the most out of it.
You're gonna love this episode.
We are lucky.
We've got Boris.
He's the creator of Cloud Code and I would say the co-creator of Cloud Cowork today.
Today.
What I want to get accomplished is.
Everyone's talking about Cowork and I want to best understand what are the use cases?
How can we get started?
What are some non-obvious ways I can use it?
Boris, thank you so much for coming on the show.
I have one question for you.
By the end of this episode, what are people going to get out of it?
Ooh, I think people are going to start to get some more ideas for how to use cowork.
And hopefully, they're going to tweet about it.
And maybe they'll even reach out to me so I could learn how they want to use CodeWork.
It's funny.
I feel like Cloud Code.
From the beginning it was sort of built to be.
It wasn't actually built to be a product at all.
But when we first started thinking about it as a product, we thought that the thing people would use it for is coding.
But we learned very quickly that people didn't just use it for coding.
They used it for all sorts of stuff.
So I kind of feel the journey of Quadcode has been very surprising.
And I have been learning so much just watching how people use the product and how they abuse it and kind of like what they actually want to use it for.
And even if it's not designed for that.
So I kind of feel the same way about coworking.
You know, I have some ideas about what people are going to use it for.
I kind of view these as hypotheses.
And so, you know, happy to talk about it.
Happy to.
Maybe I'll do a quick demo to show you kind of some of the some of the things that we use it for.
But I think that it's going to be pretty surprising.
And I hope that I will be surprised when we see how people actually use it in the wild.
Yeah, I think that's always the case with platforms, especially if you think about it.
When the makers of the App Store created the App Store, the initial apps was a beer drinking app and a bunch of random apps like that.
Did they know that Uber was going to come out of that?
DoorDash was going to come out of that?
TikTok was going to come out of that?
Probably not.
So I think that what's really cool about the phase that we are in right now with Cloud Code and also Cloud Cowork is We're all figuring it out at the same time.
And none of us, including the creator, have all the answers.
But I agree with you.
Like what's it's a good time to be sharing some, you know, sharing what's working, what's not working.
And, you know, if you're open to it, let's let's screen share and get our hands dirty.
Yeah.
Yeah.
Let's do it.
So what are we looking at right now, Boris?
Yeah, so this is the Cloud desktop app.
So you just download it.
CodeWork is only available for Mac OS.
Windows coming soon.
There's a few different tabs in the desktop app.
So there's the chat.
That's the default.
There's CodeWork.
That's the new one.
And then there's code.
And that's just Cloud code.
Um, cowork under the hood, it's actually just quad code.
And so, you know, the agent that makes quad code awesome, we call it the quad agent.
It's also available as the quad agent SDK.
So you can use it programmatically.
You can, you know, all sorts of companies built all sorts of cool things on top of it.
We actually use that same exact SDK directly in CodeWork.
So it's pretty cool.
It's just one way across everything.
We have the best agent, have the best agentic model.
Might as well use it.
And so what I'll do is just to show how to use this thing.
When I think about agentic AI.
This word agentic has sort of lost all meaning because it's just used so much.
So I feel like probably a lot of listeners have heard the word agent, but they don't actually know what it means, or they think it's some cool AI or something.
But it actually has a very specific meaning in the AI world which I think has kind of been lost, because a lot of the products that people have released and called agentic in the past are not actually agentic.
And so like when you think about the AI products that everyone's used, you know, like obviously quad code, chat based apps where, you know, you just chat with the app kind of back and forth, send some messages.
The biggest difference with agents is it can take action.
And you know, it's not just text and it's not just like web searching, but it can actually use tools on your computer.
It can it can interact with the world.
And so for Anthropic from the very beginning, since before our models were good like before, like you know, like Cloud 3 or whatever this is a thing that we wanted to get really good at because we felt that it's very important.
And so from the start we wanted our models to be really great at coding, and then really great at tool use, and then really great at computer use.
So it's kind of cool, like you know the last year, seeing how people have been hacking quad code.
It's pretty obvious this is kind of the place that we should go.
And so for people that have used quad code, you know, none of this will be, you know, like too surprising.
These are actually things that you can do.
So really what we're trying to do is make this something that everyone can use in a way that's safe.
And so what I'm going to do is, you know, here on my desktop, I have this like receipts folder.
I have a few receipts in it.
So I'm just going to give a co-work access to my desktop and you have to pick like which specific folders I can see.
By default, they can't see anything.
So you have to kind of opt in to see, to let it access specific folders.
And so I'm going to say you know, I can say I have a receipts folder.
Can you rename the files?
Match the dates on the receipts.
So i think one interesting thing is, when you're using co-work, it's really like it's operating with your files like that's.
That's a big sort of mindset shift that people should have.
It's almost like your operating system.
Is that right?
Yeah, exactly.
It has your files, so the ones that you give it access to.
But actually, the even cooler thing is it can use all sorts of tools.
And so files actually is like, that's useful, but it's not that cool.
What's actually much more interesting is it can generate files for you.
So it can make presentations and things like this.
It can interact with any tool over MCP.
And it has built-in support for Chrome-based browsers.
So it can actually control your browser to do stuff.
And so I'll kind of show that a little bit.
So this is kind of the first step.
When you're first getting started with co-work, the thing I recommend is do exactly what I just did.
Just mount the folder, give co-work access to it, and just play around with it.
It's super useful for cleaning up files, organizing, things like that.
And so here it found these four receipts that I have.
It's asking me if one of the receipts, I guess, is missing a date.
So should I just rename the others?
So I'll just say, you know, for one, it's I'll say it's like up to you.
And then for two, I'll say don't rename it.
And we actually call this like reverse solicitation in the AI world.
So what this means is, when the model is unsure about something, it's going to ask you for clarification.
And we've sort of taught the model to be pretty good at this.
So instead of assuming if it's unsure about something, it's just going to ask you.
And so, yeah, in this case, so it renamed the receipts.
So I'm just going to open this up to double check.
Yeah, cool.
And so the receipts are named a little bit better organized.
And so maybe what I can try next is, let's put this in a spreadsheet.
So it takes control of your computer, basically, in that sense, right?
If you allow it to take control.
Yeah, yeah, that's right.
And so we put like so much work into kind of safety and making sure that, as this happens, you don't like accidentally shoot yourself in the foot and like delete files or whatever.
So there's just like a huge amount of work that went into this.
And it kind of starts at the model side where you know, for Anthropic, from the very beginning we were the AI safety lab and that's the reason that we exist.
There's a lot of work into alignment and mechanistic interpretability and all these ideas to make sure that the model does what you want in a way that's safe at the model layer.
This literally means studying the neurons the same way that you would study neurons in a human.
And so you can identify structures and you can kind of study in a very scientific way as a black box also to make sure that it's safe.
So this is called alignment.
And then we do a whole bunch of other stuff.
So there's actually a whole virtual machine running under the hood.
And this is just to make sure that any actions taken are safe and don't affect your broader system.
And then as of last week, there's also deletion protection.
So if you accidentally delete something, then you're going to get prompted first.
So the model can kind of make sure that that's actually a thing that you want to do.
Obviously also as we start interacting with the internet.
Something like prompt injection is quite scary.
And so we built in a lot of protections against that.
Obviously, it's not perfect, and it's something we're iterating on.
But there's also part of the reason that we released this pretty early is we want to see how people use it.
And a big part of making models safe isn't just studying them in a lab, but studying them in the wild to see how it's useful.
And so this was pretty cool, right?
So we have this folder.
Um, first it kind of renamed all, all my receipts.
I asked it to make a sheet.
It just made the spreadsheet.
So it's already here.
Um, maybe I don't want a spreadsheet.
Maybe I want like a Google sheet.
So actually.
That's so interesting.
Right.
Cause, like I think uh, where people stumble with tools like coworking, cloud code, is because you can do anything making it a, of course that makes sense.
Making it a Google sheet, but like That's where it's so interesting that you really can treat it like a teammate in that sense, right.
Like, go and do this thing.
The world is your oyster.
Whoa, what is happening right now?
Yeah, so it's like it's opening the browser.
And so here it's going to ask me for permission.
Just for this demo, I'm going to say always allow for the site.
But you can just say, like, allow once or deny.
And so Quad's taking the wheel.
It's making a spreadsheet for me.
This is going to sort of take a while.
And so this is one of the things that we're iterating on is making this kind of computer use a lot faster.
I remember, like man, this is like when I first joined Anthropic and this was maybe like Sonnet 36 days or I forget what we called it, like Sonnet 35 new.
And that was the first model that I think we really started to crack computers.
And I remember I was like sitting with my team.
And there was literally a researcher that ran into the room like in the movies, and was like oh my God, Quad knows how to use computers.
And we just had to like order a pizza.
And it picked a pineapple pizza and then ordered it and asked us for a credit card.
And then we got that delivered to the office.
But it was tedious.
It took like an hour or something for it to click around.
And since then, we've been improving the model's ability to use a computer.
Um, and so you can kind of see that here.
So here the you know quad is typing and it's interacting with the spreadsheet and it can see what's on the screen.
It can interact with it.
Anything that's in your browser, it can, it can just use.
And could it use like email?
You know, let's say we wanted to send this to somebody you know?
Finance team like can you?
Maybe we'll get into it later but, you know, with things like connections and MCPs um, is that possible?
Yeah, yeah, totally.
Okay, so let's make this kind of a nice spreadsheet, because we don't want to send a badly formatted spreadsheet to our coworker.
But let's make it nice, and then we can ask Quad to send it.
And so here it's kind of cool.
It's still early days, and so there's some formatting mistakes.
It didn't paste it exactly correctly, but it noticed it.
So it noticed that it's not actually split correctly, and so now it's trying to format it.
So it kind of noticed this.
And yeah Greg, like to your point, it's funny these like these use cases and the way that people are going to use these tools.
Like I said at the start, it's going to be so surprising.
I'm just so excited to see how people use it.
And sort of the crazy thing about them is they're so general purpose.
It's like it's sort of like a computer itself or like the Internet or something like.
Like you said, like when you first like, had an iPhone, like you would never have predicted that you know there would be an Uber app at some point.
But, you know, that's that's what happened.
And I sort of feel like we're at the beginning of that, but for agents.
Yeah, I think it sounds so obvious in hindsight.
Like, of course, you have a phone with GPS.
Of course, right?
You're going to have things like Uber and DoorDash and stuff like that.
But I feel like, yes, you're right.
I think what I'm trying to figure out in my mind, like I'm watching this and I'm like this is really cool.
But I'm thinking about like okay, how do I audit my entire company?
What are all the tasks that the company is doing?
How are they interacting with files?
And how are they using the internet?
And how are they sending things?
And then what are opportunities I can use to make my team and also my life more productive?
That's what's going through my head right now.
Yeah, yeah, totally.
That's a great way to think about it.
And, by the way, something that's kind of cool is.
You know, as this is running, I'm just going to make a new task and do something else.
So, you know, what are some cool episodes?
Startup.
Cool.
And while this one's running, we can let this one go, too.
And I often have a bunch of tasks running in parallel, too.
But yeah, that's exactly it.
You should just think about, what's all the tedious stuff that you do every day?
And you can just throw all this stuff to co-work.
And I feel like this happened for coding over the last year because, of course, engineers and programmers are the earliest adopters.
So when the tooling first became able to do that kind of work, Engineers adopted it first.
But you know now, now this is coming.
Now this is possible for everyone else to use, too.
So that's like that's super exciting.
And when we talk to engineers about the way they like to use quad code, you know they run a bunch of quads in parallel.
They use it to automate the tedious stuff.
And I don't know man like.
For me this is just the most fun I've ever had as an engineer, because I get to do the stuff that I enjoy.
And I just feel so productive because quad does all the you know, the stuff that I didn't want to do.
Um, okay.
So now we have this, like we have the spreadsheet.
This looks all right.
It's not too bad.
Um, the data looks correct.
Um, you know, one thing that's missing though, is uh, uh.
Well we, we can add, maybe like the totals, but I think, for the sake of the demo, what I'm going to do is um, I'm going to see if it can email it.
So just reading for audio to listeners, can you open Gmail and send the sheet to Amy?
And Yeah, so I'm going to say always continue.
So how is it going to know it's Amy, right?
It's going to pull up the contacts within Gmail?
Yeah, yeah, exactly.
Yeah, that's exactly it.
It's going to interact with it the same way that anyone else would interact with a computer.
And it's the same thing.
It can click stuff.
It can read the screen automatically.
Okay.
So compose window open.
Let me type Amy.
So you have like multiple when you're, when you're like locked in, so to speak.
You're kind of you have multiple of these windows open at, or multiple, multiple virtual machines open at the same time.
Yeah.
Yeah.
I usually have a bunch of these, you know, like five or five or 10 or whatever.
And so we can see the models, you know, trying to interact with this.
And so it filled out Amy, and And you know, by the way, just because this is going on YouTube, you know you're going to have some haters in the comments.
So we're just going to address them right now.
Someone in the comments is going to be like, but that's so slow.
I can do it faster myself or something.
What is your reaction?
Of course you can.
Yeah, I could definitely do this much faster.
And it's actually the same thing for a lot of quad code, right?
Like, especially at the beginning, I could do it much faster.
But I think sort of two things happen.
One is that the model just gets better at doing it quickly.
And this is just something I would expect over time.
But then the second thing is, because you can do multiple things in parallel, it's actually a big time saver.
And so usually my workflow is I'll kick off a few different tasks in parallel.
And I'll just kind of go back and forth between them and kind of tend to my quads, make sure they're in a good place, see if they have any questions or anything like that.
So it's really a different kind of workflow.
Like I feel like now is the age of like kind of multi multi, clotting of, of parallelism, of like not going super deep on stuff but kind of being more of a generalist and more tending tending to your clods.
And so this was this other chat that we kicked off earlier.
And in this case, it sort of did some research.
So that's pretty cool.
So it didn't just go to, you know, like Startup Ideas podcast website, but it searched the internet, checked a bunch of different places, checked like someone's notes about it.
Yeah, 10 rules for quad code.
Yeah, I'll find that interesting too.
Let's see.
So it seems like this is the email is probably all drafted.
The draft has been saved.
Please send.
And i also use this for like slack too.
Like a pretty common use case i've been doing maybe a couple times a week is i have a spreadsheet where we track all the team's work for for the month or for the week or whatever, And instead of having to bug everyone on the team to fill out the status, what I do is I ask co-work to look at the spreadsheet.
Any column that's not filled out, just message the engineer on Slack.
And it does that really well.
So you know, I just ask it to do that and then I go get a coffee and I don't have to do that anymore.
Do you think that co-work is going to be the gateway drug to cloud code?
Because for a lot of beginners, non-technical people, cloud code feels a bit overwhelming.
But when I'm watching you do this, this feels, you know, approachable.
Yeah, I mean, I think it's like probably two kinds of users.
And it's also, it's funny, cloud code is built originally in a terminal.
And, you know, nowadays it's available in the quad mobile app.
It's available on the website, in the IDE, on Slack, on GitHub.
So, you know, nowadays it's available everywhere, but originally it was built in a terminal.
And I never thought that most engineers would want to use a terminal because, you know, it's scary.
It's like this thing that's sort of hidden away on the computer.
Like you know, only the most hardcore engineers want to actually work in a terminal day in and day out.
And so it's surprising to me that most engineers wanted to use it.
What's even more surprising is a lot of non-engineers started to use it.
And that was the craziest thing.
And you know, looking at like the sales team at Anthropic, like the GTM team, half of them use quad code every week.
And looking at other non-technical people at Anthropic like designers, product managers, data scientists pretty much all of them use quad code every day.
So that's been like pretty surprising.
But my hypothesis is, what they would prefer is actually something a little bit more like this, where you don't have to deal with a terminal and all that kind of thing.
You have a nice UI because you don't need access to Bash and all that kind of stuff, because the model will just do it for you.
Yeah, I think what I would love with something like this is, you know, automating some of these processes.
It's like, instead of doing one-offs, it's like, anytime this happens, I want you to do this.
That's my dream.
Yeah, it's a cool idea.
I'm excited to see like how it's tied into skills also.
I think it's something we're thinking about we haven't quite figured out yet.
Yeah, because like a skill, what is it?
It's essentially kind of a repeatable way to do something.
And so you saw that a little bit earlier up in this conversation, right where um, when quad was generating this spreadsheet um, i don't know if you saw, but it actually loaded the skill and so we pre-packaged the skill for excel and that's the way that quad knows how to do it.
Um, and so if you have some like weird file format i don't know if you work with like autocad or if you work with you know like sales for kind of whatever it is the tool, the tool that you use you just make a skill and then quad can can do it for you.
That's interesting.
So If you have more skills, co-work and you're asking it to do things related to those skills, co-work is more likely to use those skills.
So you might be able to get a better outcome out of co-work if you do some upfront work to actually create some skills.
I think so, yeah.
Wow.
Yeah, I think that's exactly right.
Yeah, okay, well that's good to know.
And what else do we need to know about co-work?
Because I know there's extensions, there's skills.
Walk us through some of.
Is there anything else that we need to know in order to get the most out of the product?
You know, we tried to build core work just to be pretty simple.
When we think about the different audiences we serve for an audience like engineers.
They don't actually like simple.
Simple is good by default, but engineers love to hack their tools.
They love to customize their tools.
That's actually really important.
Quad-code is just the most customizable coding agent.
It has just so many extension points.
There's skills, there's custom agents, there's hooks, there's an insane amount of configuration and settings that you can set.
There's a very sophisticated permission system.
So there's all sorts of ways to customize it.
And this is because we know every engineer works different and everyone has different preferences.
Everyone uses a different tech stack.
Everyone uses a different editor.
Everyone uses a different OS.
So we wanted to make sure it's really customizable.
For some of my core work, I think we're starting in the opposite direction.
And just keep it really simple at the start.
And so if you use core work, I would probably not customize too much.
If you have core work installed and you install the Chrome extension, that's pretty much all you need.
And it'll do everything else for you.
I think, over time, as you find yourself using maybe software that core work is not great at, that's the point to think about writing skills.
But that wouldn't be my starting point.
Just start simple, like, you know, see how it works, see what's useful.
And I think also the other thing, you know, it's just so early.
This feels to me a lot like Cloud Code a year ago. where we released it before it was early.
It was not very good yet.
It was super buggy.
It barely worked.
The model was not very good at coding a year ago.
And it feels like that to me.
But I think Core Work is actually a little bit better than Quad Code was when we first released it, because it's actually useful.
And it's already a thing that I use every day.
And yeah, I think in the first week we've seen so much more growth.
It's been like a multiple of the growth that we saw with Quad Code the first week.
So that's very exciting.
It seems like this is something that people are already finding useful.
You know, we're recording this, what is it, January 2026.
If we come back here in 12 months, it's January 2027.
How do you think people are going to be using cowork, you know?
I know you don't have a crystal ball exactly, but what sort of use cases and what does the product look like?
Describe the world in January 2027 with CoWork.
Oh, geez, Greg.
I plan on a one-week timeline.
Yeah.
The model is just changing so fast.
It's so hard.
And I just feel like the model is advancing exponentially and just my puny human meat brain can't grapple with the exponential.
It's like we think in linears.
And so I think this kind of exponential is just very, very difficult to plan around.
Okay, but if I had to speculate...
A year ago I made and I think Dario also made this prediction that by the end of the year people wouldn't be writing code anymore.
And I think that was like sometime mid, you know, last year or something.
In, you know, I code every day.
I ship, you know, two, 300 PRs every month or something like that.
And in the last two months, quad code has written 100% of my code.
I haven't written a single line by hand.
And this is something like I also predicted this way back middle of last year.
It was sort of not intuitive because if you just think about kind of the experience at the time and you trace it linearly, there's just no way that the model would be at that point.
So you really have to kind of believe in exponential.
And just literally like plot it out and kind of follow the way that the line goes.
That's the only way that you would have predicted this.
And it was just, it was absolutely right.
And so I think, for coding, this is something that we're going to start to see in more and more places for more and more kinds of code, that the model is able to just do all of it.
And when we think about co-work, I think it's somewhat similar.
I think it's a little bit earlier.
And I think what we're going to see is for all this kind of tedious tasks like connecting app A and B or kind of shuffling data back and forth, or whatever the model is just going to be able to do it.
And it's going to get increasingly good at it.
I think in some ways it's a little scary.
And in some ways I think it's really exciting because...
You don't have to spend your time on this toilsome work anymore.
You can just focus on the work that you enjoy.
And also everyone, I think, just becomes much, much more productive because you have an army of clods that can do this.
Okay.
I like that feature.
I like that feature a lot.
It's a hard question.
It's a hard question.
When you, it's sort of like the genies out of the bottle and it's hard to predict like, where the genie is going to go.
So yeah, I believe that cowork is the gateway drug to cloud code.
I think that people are going to start using it and they're going to develop vertical use cases for whatever it is their business is.
You mentioned AutoCAD.
You probably weren't thinking about AutoCAD when you were helping develop cowork.
So I think there's going to be like these verticals.
And I think, I think that co-work is going to be similar to, like vertical job boards, where there's very specific roles that you can hire to people.
And I do think that there's going to be this combination between skills and these like digital teammates that you're going to quote.
Unquote hire
Yeah, that's super interesting.
Maybe we should make a bet and just see where it pans out in a year.
You know, I have no idea, but...
It's definitely interesting to speculate, because I just feel like the way this technology goes is so different than past technology waves.
It's sort of similar to the Internet.
It's sort of similar to computers, you know, like maybe like telephones or something before that.
But the speed is just so much faster.
And because it's kind of piggybacking on all of this, like the Internet could not exist without telephones, telephones and kind of like phone lines being everywhere.
You couldn't have dial up without it.
You know, mobile phones couldn't exist without the Internet existing.
So it's sort of like every layer of the stack.
It just gets more and more powerful and it spreads more quickly.
And so it's like on the back of all of this that AI can exist.
And yeah, it's just going to be very exciting to see where it goes.
I want to shift gears just for the last 10 minutes because we mentioned Cloud Code.
You had a post that went absolutely viral.
I think you know what post I'm going to talk about.
99,000 bookmarks. which is crazy.
And I'm going to share my screen.
I want to go over it a little bit.
This is me learning to use Twitter.
I think I made an account like a decade ago and I haven't really used it.
So it's funny.
Yeah, it's been fun to learn.
You have like just a few tweets, but like this, you know, this one, you figured it out.
You say, I'm Boris.
I created Cloud Code.
Lots of people have asked for how I use Cloud Code.
So I want to show My setup might be surprisingly vanilla.
Cloud Code works great out of the box, so I personally don't customize it much.
There's no one correct way to use Cloud Code.
We intentionally built it in a way that you can use it, customize it and hack it however you'd like.
Each person on the Cloud Code team uses it very differently, so here it goes.
Could you just talk about, Just expand on some of these and what you were saying on here, because I thought it was really interesting.
Yeah, I'd love to.
So this first one.
It's very similar to what I was showing in co-work, where my job now isn't to go super deep on one task.
It's to do a bunch of tasks in parallel.
And so you know, in the when I'm working on quad code, I usually work in a terminal or on the mobile app.
These are kind of the two services I use the most.
But like I said, everyone on the team is different.
Every user prefers something different.
So we build all of these.
And so usually what I do is I'll start a task in kind of one tab.
And once Quad is thinking about it and starting to work on a plan, I'll move on to the second tab.
And I'll ask it to make a plan for the second thing.
Then I'll move on to the third one, ask it to make a plan.
And then finally, like when I've run out of immediate tasks to do, I'll go back to the first tab.
I'll see if the plan looks good.
I might go back and forth a little bit.
And then once the plan looks good, I usually go into just auto-accept edits right away.
Because I think with Opus 45, once the plan is good, the model can just execute it pretty much perfectly.
This is definitely not the case with previous models.
And so I think there was a lot of excitement about Opus 45 in, you know, over the last couple months.
And I think this is kind of one of the big reasons.
It's just gotten very good at coding, but also excellent at planning.
So once the plan is good, the code is good.
And so yeah, my work now is just jumping between tabs, kind of tending to the clods, make sure they're unblocked, answering their questions.
With co-work, I think it's actually quite similar now.
I like that.
I'm going to quote you on that.
Once the plan is good, the code is good.
Because that's so true, right?
Because if you nail the plan...
The code should, you know, the agents should do the work.
Yeah, yeah, exactly.
I think like sometime last year, there was all this buzz about spec driven development.
And you know, it just feels like.
It feels a little like too cutesy and like a little too rigid to me.
But I think this is sort of a form of spec driven development.
It's like there is some kind of spec, you know, I think it's just like a plan.
That's all it has to be.
It's just a text file.
It doesn't have to be in a particular format.
Once you have that, you're good.
Number two, you say, I also run five to ten clouds in parallel with my local clouds.
As I code in my terminal.
I will often hand off local sessions to web using and or manually kick off sessions in Chrome, and sometimes I will teleport back and forth.
I also start a few sessions from my phone obviously from Cloud iOS app every morning and throughout the day, and check in on them later.
What do you mean by that?
This morning, I kicked off, I think, like three quads as soon as I woke up.
I just had some thought in the morning about well, maybe I should build this thing or fix this bug or whatever.
I was checking Twitter, and someone had a bug report.
So I just opened my phone.
And in the quad app, on the left side, you click the little menu, and there's a code tab.
So you can just access quad code there.
That's what I use for a lot of my code.
And it's funny, I never would have guessed that this is the way that I code.
If you asked me a year ago, I would never have predicted that.
The way I code now is like probably half of it is just on my phone and it sort of just works.
And then web is kind of the other part.
So once I've run out of tabs because it's just like you know, it's kind of a pain to manage a bunch of different Git checkouts because in each tab in my terminal I actually have a totally separate Git checkout.
And I don't really use work trees or anything like that.
I just keep it pretty simple.
And in web.
If I, if I just ran out of terminal tabs, I'll start like overflowing to web and starting tasks there.
Beautiful.
So yeah, I also so recommending use iOS, use web, open multiple like that's, that's.
You'll get the most out of it that way.
Yeah, absolutely.
Yeah.
And we have an Android app now too.
So yeah, just like use the mobile app and see how far that can take you.
If it's not giving you good results.
Also, make sure that you tune the environment setup and make sure that you invest in your quadmd.
That's super duper important.
And I talk about that in number four also.
Mm hmm.
Number three, you say, I use Opus 4.5 with thinking for everything.
It's the best coding model I've ever used.
And even though it's bigger and slower than Sonnet since you have to steer it less and it's better at tool use it's almost always faster than using a smaller model.
In the end,
And cheaper.
It's sort of counterintuitive.
And I had to explain this to people a few times.
But because the model is smarter, it actually uses less tokens in the end.
And it uses so many less tokens.
It's often cheaper than using a smaller, less intelligent model, even though the per token cost for that model is lower.
So a little counterintuitive, but yeah, just use the smartest thing if you can.
Well, we appreciate that, you know, we appreciate that.
Number four, our team shares a single Cloud MD for the Cloud Code repo.
We check it into Git.
The whole team contributes multiple times a week.
Anytime we see Cloud do something incorrectly, we add it to the MD, so Cloud knows not to do it next time.
Other teams maintain their own Cloud MDs.
It is each team's job to keep theirs up to date.
And the QuadMD is just a text file.
So there's no special format.
People ask this all the time.
Is there some special format that it has to be in?
No, it's just like it's just a text file.
So you can put whatever you want in it.
This is a screenshot of our QuadMD.
This is literally it.
So just really simple.
And, you know, you could format this kind of however you want.
Love it.
And then finally, I think, yeah, number five.
Oh, no, you have you got a few more.
So.
Number five, during code review, I'll often tag at dot cloud on my coworkers PRs to add something to the cloud MD as part of the PR.
We use the cloud code GitHub action for this.
It's our version of Dan Chipper's compounding engineering.
What do you mean?
What is compound engineering?
Yeah, oh my god.
So there's actually two bugs in this tweet.
I think Dan actually calls it compound engineering, not compounding engineering.
And then the at dot quad, this is me learning how to use x. But it's actually at quad.
There's no dot.
I think there's an actual user or something whose name is quad.
I didn't want to tag them.
But yeah, so what you do is in quad code, you run this slash command slash install GitHub action.
And what this does is it installs the Cloud app in your GitHub repo.
And what that lets you do is you can then app mention Cloud whenever you want and just have it make changes.
And it can just work on PR.
So it'll push back to your branch and it'll push the changes right back.
You can also tag it on issues.
You can tag it kind of wherever.
I do this multiple times a day.
It's really, really useful.
I think one of the most common use cases is just like little fixes.
I think the other one is updating the QuadMD to keep the knowledge base up to date.
And you should never have to comment about something twice.
Back when I was at Meta.
Something that I did is this is like in a previous life, in a previous job.
Something that I did is every code review that I did.
I would keep a spreadsheet of all the issues that came up.
And whenever the same kind of issue came up again, I would just like tally it up in the spreadsheet.
And whenever something hit, I think like five or 10 tallies or something, I would write a Lint rule.
And what that is is.
It's a way to automate that part of the code review, so I don't have to comment about it again.
And that was back in the days before LMS and before the model was any good at coding.
And so this is the equivalent nowadays.
You just tag quad and you have it update your quad MD, which is your team's knowledge base.
So really simple.
And what this means is you don't have to point anything out twice.
I'm curious to see what this looks like for cowork.
I don't think we figured that out yet, but definitely for quad code.
Quad MD is kind of the.
This is the one, the one thing that you should all be updating all the time.
Love it.
Number six, most sessions start in plan mode.
If my goal is to write a pull request, I will use plan mode, go back and forth with Cloud until I like its plan.
From there, I switch into auto accept edits mode and Cloud can usually one shot it.
A good plan is really important.
Yeah, like I said, planning is just the most underused feature in Cloud Code.
Actually, a lot of people use it, but I would say it's still underused.
I use it for almost all my sessions.
Yeah, it's a no-brainer.
So if you aren't already doing this, please do.
We're not going to have time to do all of them.
I don't think because you have a hard stop.
Do you want to pick one or two to end with?
Yeah, let's do maybe number 13.
Yeah, number 13, I think this is probably in addition to using Opus 4.
When people ask about how to get better performance out of quadcode, There's three things that I recommend almost every time.
Number one is use Opus 4.5 with thinking always.
Don't try to use a different model, because Opus will just give you better results and more efficiency overall.
The second thing is make sure you have a good QuadMD.
And then the third thing is this tip number 13. which is give quad a way to verify its output.
And so we just kind of saw, with co-work, how good quad is at using the Chrome extension in order to write email and in order to work with sheets.
And it's exactly the same thing.
If I'm building an app, I always use the Chrome extension to have quad test its own work.
And if quad can verify its own output, the result is going to be way, way better.
And it's sort of like...
Imagine that you're a painter, and you make paintings, and they have to be pretty good.
They have to be maybe even photorealistic or something, or just some kind of very detailed style.
And you have to wear a blindfold.
You're just not going to be that good.
It's not going to come out that great.
Or it's the same thing for an engineer.
If you have to write code but you can never run the code or you can never see the output and you can never see the website, it's just not going to be good.
And so it's the same thing with Klang.
As the model gets more intelligent, that first shot is going to get better and better.
But really, you want to give it a way to verify the output and it'll be much better.
So this is like running tests if you're an engineer, starting a server.
Also, if you're an engineer or, you know, seeing seeing the output in a simulator or in a browser.
Amazing.
And the ultimate tip, I guess, is just get your hands dirty, right?
Yeah.
I think that's it.
Yeah.
I mean, there's no right.
There's no one right way to use the stuff.
Like, you know, see, see what's useful.
See what's not.
Find your own workflows.
It's sort of I heard someone describing quad code as like a find your own path book.
You know, like one of those books where you have to like do you do?
Do you go to the dungeon or do you explore the forest?
Like this kind of thing or like a like an old like RPG video game.
It's just kind of like that.
It's like it's very free form.
There's no one right way to do it.
So just see what works for you.
Boris, I appreciate you taking the time, the generosity, to spill the sauce and just to share with us how we can get the most out of both co-work and Cloud Code.
Everyone's thinking about it and everyone's trying to, especially on this podcast, the Startup Ideas podcast.
You have millions of people who are trying to figure out how I can be more productive and how I can build businesses around some of these things.
Thank you for the time.
I'll include links on where to follow Boris.
He doesn't tweet a lot, but when he tweets, it's worth paying attention to.
I want to leave with one thing, just because my audience would kill me if I didn't ask this.
As you know, Boris, I'm from French Canada.
We speak French, obviously, in French Canada.
I call Claude, Claude.
Am I the only one?
Oh man, you're probably not the only one.
A lot of the world speaks French.
Which one sounds better?
I mean, to me, Claude sounds better.
It's like Jean-Claude Van Damme, even though people would say Jean-Claude Van Damme.
It's like, that's my take.
That's my hot take.
To me, it sounds better.
You know Greg, today around the office, I'm just going to call it Claude and we'll see what people will say.
I'll report back.
Okay, report back.
All right, sounds good.
Boris, thanks again for coming on and I'll see you next time.
Yeah, thanks so much, Craig.