# Anthropic's Boris Cherny: Why Coding Is Solved, and What Comes Next

Markdown copy of https://realalpha.app/v/SlGRN8jh2RI/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

Boris Cherny says coding is solved for his own work and expects AI to make software building accessible beyond engineers.

- Show: Training Data
- Hosts: Lauren Reeder
- Guest: [Boris Cherny](https://realalpha.app/builders/boris-cherny/) is creator of Claude Code at Anthropic.
- Published: May 4, 2026
- Length: 25 min

## The best minutes

- [5:04](https://realalpha.app/v/SlGRN8jh2RI/?t=304) [Coding is solved for the code Boris writes](https://realalpha.app/s/coding-is-solved-for-the-code-boris-writes/) (4 min)
- [10:22](https://realalpha.app/v/SlGRN8jh2RI/?t=622) [AI weakens some software moats but strengthens others](https://realalpha.app/s/ai-weakens-some-software-moats-but-strengthens-others/) (3 min)
- [14:57](https://realalpha.app/v/SlGRN8jh2RI/?t=897) [Software could become as ordinary as reading and writing](https://realalpha.app/s/software-could-become-as-ordinary-as-reading-and-writing/) (2 min)

## Also worth watching

- [2:33](https://realalpha.app/v/SlGRN8jh2RI/?t=153) [Claude Code was built before the model was ready](https://realalpha.app/s/claude-code-was-built-before-the-model-was-ready/) (3 min)
- [13:03](https://realalpha.app/v/SlGRN8jh2RI/?t=783) [Product craft still matters as models improve](https://realalpha.app/s/product-craft-still-matters-as-models-improve/) (2 min)
- [17:18](https://realalpha.app/v/SlGRN8jh2RI/?t=1038) [Anthropic's workflow advantage is organizational, not model access](https://realalpha.app/s/anthropics-workflow-advantage-is-organizational-not-model/) (2 min)

Skip the opening crowd check and career setup, plus the closing questions on local models, Cowork access, and upcoming products.

## Summary

Boris Cherny created Claude Code at Anthropic. He says he joined Anthropic Labs in late 2024, where a small team built Claude Code, MCP and the desktop app; the team later disbanded and has since reunited.

Boris Cherny says coding is effectively solved for his own work: Claude writes all his code, though he notes that complex codebases and less common languages remain harder. He expects agents and recurring loops to change individual workflows, and predicts teams will become more cross-disciplinary as software building spreads beyond engineers. He argues AI will weaken some business moats while leaving network effects and scale economies intact, and predicts more startups will challenge established companies. Cherny compares wider access to software creation with the spread of literacy after the printing press, and says organizational processes—not model access—may become a bigger source of advantage.

### Minute by minute

- [2:33](https://realalpha.app/v/SlGRN8jh2RI/?t=153) **Claude Code began as a bet on models.** Boris Cherny says he started Claude Code after joining Anthropic Labs in late 2024, where the team saw a gap between what models could do and what products offered. Coding tools then mostly completed one line at a time, so his team built an agent to write code; it was barely usable for six months. He says adoption accelerated after Opus 4 and continued to grow with later model releases.
- [5:04](https://realalpha.app/v/SlGRN8jh2RI/?t=304) **Cherny says coding is solved for his work.** Cherny says Claude writes 100% of his code, and that this has been true for his work since October or November of the previous year. He says he usually ships a few dozen PRs a day and once reached 150 in a day. He notes that complex codebases and less common languages remain harder for models.
- [6:47](https://realalpha.app/v/SlGRN8jh2RI/?t=407) **Loops manage work in the background.** Cherny says he now does most of his work from his phone, with five to ten sessions and hundreds of agents running; he may have a few thousand doing deeper work overnight. He uses scheduled loops to monitor PRs, fix CI, and cluster Twitter feedback. Server-side routines keep jobs running when his laptop is closed.
- [8:49](https://realalpha.app/v/SlGRN8jh2RI/?t=529) **Teams will need more cross-disciplinary generalists.** Cherny predicts teams will include more people who work across engineering, design, product and data science. He says everyone on the Claude Code team writes code, including its product manager, designers, data scientists, finance employee and user researcher.
- [10:22](https://realalpha.app/v/SlGRN8jh2RI/?t=622) **AI will shift moats and favor startups.** Cherny says AI will reduce the value of switching costs and process power, while network effects, scale economies and cornered resources will remain important. He predicts the number of startups disrupting established businesses over the next 10 years will increase 10x, because new companies can build around AI without retraining existing organizations or overcoming internal resistance.
- [13:03](https://realalpha.app/v/SlGRN8jh2RI/?t=783) **Product choices still matter as models improve.** Cherny describes Claude Code's success as a mix of model capability and product choices, estimating the balance at roughly 50-50 when asked about a year or six months earlier. He says product details still matter, while stronger models may make the product harness and safety mechanisms less important. He expects loops and ways to run more agents to become more central.
- [14:57](https://realalpha.app/v/SlGRN8jh2RI/?t=897) **Software creation will spread beyond engineers.** Cherny expects software building to become as ordinary as sending a text message. He compares it with the printing press: he says about 10% of Europeans were literate beforehand, more literature was published in the 50 years after the first press than in the previous 1,000 years, and book costs fell about 100x. He argues that domain experts, such as accountants building accounting software, may be better placed than engineers because knowing the domain is harder than coding.
- [17:18](https://realalpha.app/v/SlGRN8jh2RI/?t=1038) **Organizational change may be the bigger lead.** Cherny says Anthropic uses the same models available to other users, with some internal use of Mythos and extensive use of Opus 4.7. He sees a larger gap in how the company works: he says Claude is used for nearly everything, models write the SQL and code, and agents communicate over Slack. He says the advantage comes from changing organizational processes, not exclusive access to the technology.
- [19:14](https://realalpha.app/v/SlGRN8jh2RI/?t=1154) **Models will manage agent orchestration.** Cherny says product teams can prompt models to do more work in parallel, but better models increasingly start loops and coordinate tasks on their own. He argues that users should not have to figure out how to use tools; the model and product should handle that. He predicts models will choose local or cloud compute and set up agents and environments themselves.
- [21:55](https://realalpha.app/v/SlGRN8jh2RI/?t=1315) **MCP and computer use connect work tools.** Cherny says Cowork can use tools such as Salesforce, Google Docs and Google Calendar through MCP connectors. For software without MCP, he describes computer use as a catch-all that can operate applications on a user's computer, though it is slow. He says the model can work with MCP, CLIs or APIs because it ultimately processes tokens.
- [23:41](https://realalpha.app/v/SlGRN8jh2RI/?t=1421) **Loops and computer use have room to improve.** Asked what products could become more useful as models improve, Cherny points to Claude Design and upcoming Claude Code features. He also expects loops and batch workflows for running agents in parallel, along with computer use, to get better.

## Transcript

Training Data, hosted by Lauren Reeder, with Boris Cherny.

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

[0:01](https://realalpha.app/v/SlGRN8jh2RI/?t=1) Okay, I am excited to introduce our next speaker, show of hands, who here uses Claude Code? Okay, show of hands, who here has Claude Code psychosis? Come on guys, okay, it's okay. My team of lovingly says I have Claude Code psychosis, which may or may not be true. We're delighted to have Boris Cherny with us today. Boris is the creator, the father of Claude Code, and in the process of doing that, has just had a front-row seat to reinventing the modern way of software development and we're really grateful to you Boris for taking the time to speak with us today we know that the entirety of software development kind of rests on your shoulders so thank you for taking an hour of your time to be with us today and interviewing Boris is Lauren Reeder from our team thank you you took my you took my opening line I usually ask who here uses quad code But that was a lot of hints.

[1:00](https://realalpha.app/v/SlGRN8jh2RI/?t=60) That's awesome. Thank you for joining us, Boris. It's very special to have you here. As a room full of builders, I think you are changing building entirely. And so I'm very curious to explore how you think about the future of software, coding, and what we should spend all of our free time on. But I'll give you a tiny bit more background on you so that everyone has a little bit more context. So beyond creating cloud code, Boris is very much an engineer's engineer. You were writing a lot of code through your whole career, writing textbooks about code, including programming and TypeScript. And I think last time we chatted, you hadn't written a single line of code in the last year, or at least so far in 2026, which is quite the change.

[1:45](https://realalpha.app/v/SlGRN8jh2RI/?t=105) There's also a little-known thing. Back in middle school, I wrote a guide about writing basic for TI-83-plus calculators. And I just searched it. It's actually still on the Internet. It's extremely embarrassing, so please don't search it. But we will definitely be finding that um, so we're gonna do I'm gonna start with a few questions here Maybe we'll start with a little bit of the history of cloud code How you started it and then we're gonna have a lot of audience Q&A for this one And so start thinking about your questions in the back of your head and would love to turn it over to you all soon Yeah And also real quick so for people that use cloud code do people use the CLA mostly like okay majority CLA That's a lot majority desktop Okay. Majority of VS Code or Jephran's IDE.

[2:30](https://realalpha.app/v/SlGRN8jh2RI/?t=150) Okay. That's actually not a lot. Okay. Other? I'm like iOS mostly these days. Yeah. Okay. Cool. Yeah. So I started QuadCode kind of accidentally in a lot of ways. I joined this team back in late 2024. It was sort of this incubator within Anthropic called Anthropic Labs. And the team kind of served its purpose. We created QuadCode, MCP, and the desktop app. It was a team. It was just a few of us. So very much like innovation team. We built the thing that we wanted to build. We disbanded the team. Now the team's actually back together for round two. Mike Krieger, who's the, you know, like the chief product officer at Anthropic and used to be one of the founders at Instagram. So he's leading that right now.

[3:15](https://realalpha.app/v/SlGRN8jh2RI/?t=195) so the kind of the the the reason that I started to work on coding is we felt like there was this product overhang and I'm guessing people here use that word a lot but we definitely use this word a lot in kind of within the lab there's this idea that the model can do all this stuff that no product has yet captured and in late 2024 when we were looking at coding the way that we did coding the state of the art at the time was type ahead because you open your ID and you press tab and you can like complete like one line at a time. And that was the thing that Sonnet 3.5 enabled for the first time. But the feeling was we could actually go a lot further than that and the model was almost ready for the next big step.

[3:54](https://realalpha.app/v/SlGRN8jh2RI/?t=234) So we don't have to do type ahead anymore, we can just have the agent write all of the code. And so I built it and it just really didn't work for the first six months. It was like not very good, it was barely usable. I used it for maybe 10% of my code or something like that. And even after we released quad code initially, it was not a hit. There's a lot of people that used it, but it did not have this exponential growth that it has today. That started with Opus 4 in May. And I remember that very clearly. That's like when the exponential growth started, and then it kind of inflected with every model release.

[4:29](https://realalpha.app/v/SlGRN8jh2RI/?t=269) Like it started with Opus 4, then 4.5, then 4.6, now 4.7. It just kind of keeps inflecting. But essentially, we were trying to build this thing that was like pre-PMF.

[4:39](https://realalpha.app/v/SlGRN8jh2RI/?t=279) **Boris Cherny:** and we knew that it wouldn't have PMF for six months because we were building for the next model.

[4:43](https://realalpha.app/v/SlGRN8jh2RI/?t=283) And that was the idea pretty much the whole time. And, you know, for Anthropic in general, we've always just been very focused. We've always cared about business and enterprise and safety and coding. That's just always been kind of the way that we wanted to build. And so at some point we kind of knew that we wanted to build a product. We didn't know exactly. So this kind of ended up being the product bet. It's an incredible story, especially that it was an accident. So you've said on the record that you think coding is solved. If this is one of the three bets for Anthropic, can you tell us more about what you mean by that and what might still not be solved or what secondary problems might come?

[5:20](https://realalpha.app/v/SlGRN8jh2RI/?t=320) All right, I can ask another question for the room. Who writes 100% of their code by hand? Who writes 100% of their code using an agent, like quad code? Okay, who's like somewhere in between? Okay, so like 50% solved. I mean, for me, it's like, for me, it's 100%. Like the quad code code base, you know, it leaked, so, you know, people know. It's pretty simple. It's just like TypeScript and it's React. Like, there's no big secret. There's nothing really complicated. The reason we picked TypeScript and React is it's very on distribution for the model. So when we started, you know, building the code base, the model was not as intelligent as it is today.

[6:01](https://realalpha.app/v/SlGRN8jh2RI/?t=361) So the language and the framework mattered a lot. Nowadays, you know, it can write whatever and it can pick up new languages, new frameworks. It hasn't seen. But back then you wanted to do something pretty on distribution. Because of that, I think fairly early, we got to the point where the model just wrote 100% of the code. And for us, this happened sometime in October, November, or last year. And so for me today, you know, like the model writes 100% of my code. I write somewhere, you know, usually a few dozen PRs every day. There was a day last week I did like 150 PRs in a day. That was a record.

[6:32](https://realalpha.app/v/SlGRN8jh2RI/?t=392) I was just trying to kind of push to see how far I can get it. But yeah, it's like for me, it's just solved. But this is not the case everywhere. There's very big complicated code bases. There's kind of weird languages the model's not good at yet. And, you know, as everyone here knows, it's getting there. Usually the answer is just wait for the next model. Can you actually tell us about your personal setup? You walked us through it the other day. It is pretty wild. Yeah. So I shared my personal setup like six months ago or something on Twitter. And it's funny. I actually, I shared it. I didn't realize that it would be surprising for anyone.

[7:05](https://realalpha.app/v/SlGRN8jh2RI/?t=425) That was just like the way that I coded. And it's changed since then. It's changed. And so now actually most of my work I do for my phone. And so I don't know if like you guys won't be able to see this, But I have, so I have like the Claude app and if you open the Claude app, on the left hand side there's this little code tab and I just have a bunch of sessions going. You probably can't see it. How many sessions? Usually I have like maybe like five to ten sessions. And then the sessions usually have a bunch of agents. So I think currently probably like a few hundred agents going. Usually every night I have like a few thousand that are doing kind of deeper work.

[7:47](https://realalpha.app/v/SlGRN8jh2RI/?t=467) There's a few ways to manage it. One is that you ask Claude to use a bunch of subagents to do work. Actually, the thing that I've been finding myself using more and more is loop. So this is slash loop. and it's just like the coolest thing. It's like the simplest thing that works. All it is is you have Claude use Cron to schedule a job for some point in the future and it's a repeat job. And it can run every minute, every five minutes, every day, kind of however often you want to schedule it. And at this point I have like dozens of loops that are running for stuff. So I have one that's babysitting my PRs, like fixing CI, auto rebasing.

[8:22](https://realalpha.app/v/SlGRN8jh2RI/?t=502) I have another one that keeps CI healthy. So like if there's like a flaky test or whatever, it'll go and fix it. I have another one that grabs feedback from Twitter and kind of clusters it for me every 30 minutes. So I just have a bunch of these loops running at any time.

[8:36](https://realalpha.app/v/SlGRN8jh2RI/?t=516) **Boris Cherny:** I sort of feel like loops are the future at this point.

[8:39](https://realalpha.app/v/SlGRN8jh2RI/?t=519) If you haven't experimented with it, highly, highly recommend it. And we also just launched routines, which is the same thing but kind of on the server. So even if you close your laptop, it keeps going. So that's your personal setup. Tell us about what you think teams will look like in the future. How do you extrapolate from all the work you're doing to keep everyone on the team moving forward understanding the context or do you think we need to let go of a lot more to agents to make it work um i think so you know it's so hard to make predictions but um i'm here to make predictions so i'll try to make some i i feel like the way that things are going is generally there's going to be a lot more generalists than there are today and today when we talk about generalists i think largely we're talking about people that are still engineers. So they're still writing code, but maybe they're kind of product engineers. So maybe when we say generalist, it's like, you know, they do iOS and web and server, for example. That's like a generalist in engineering. But I think the thing that we're going to start to see a lot more of is generalists that are cross-disciplinary. So this is engineers that are really good at product engineering, but also really great at design or really great at

[9:45](https://realalpha.app/v/SlGRN8jh2RI/?t=585) product and data science and engineering. I don't know. It's something that we're starting to see on our team. So actually like a lot of people on the Cloud Code team are generalists across disciplines, everyone on our team code. So like... Our engineering manager, our product manager, our designers, our data scientists, our finance guy, our user researcher, every single person on our team writes code. And so, you know, like they're specialists in something, but now also everyone's just coding. And, you know, I'm seeing some nods, but I bet also it's actually not that surprising to people in this room because I bet you're seeing the same things.

[10:24](https://realalpha.app/v/SlGRN8jh2RI/?t=624) I'll have one more thread of questions and we'll open up to the audience. So we talked a bit about what's changing with coding. I'm curious about what you see changing in the world of software or software products. I think as we see AI making writing code 10 or 100x cheaper, what happens to the value of the products that are produced with software? Do we have a Saspocalypse on our hands? How do you think this plays out? And again, you're going to have to make another prediction. The Saspocalypse question is my favorite question. I think there's two things that are going to happen. And I don't think either of them is the thing that people have been talking about.

[11:01](https://realalpha.app/v/SlGRN8jh2RI/?t=661) I think one is, is anyone here an acquired listener, like the acquired podcast? Yeah, it's like the best podcast. I actually, I got to do an Unplugged with them the other week. And I just, I felt like I got to like meet my heroes because they're just like the hosts are the best. So they have this idea of seven powers. And this is like Hamilton, he kind of wrote, he wrote a book about this. And this is kind of the seven moats in business.

[11:27](https://realalpha.app/v/SlGRN8jh2RI/?t=687) **Boris Cherny:** And I think what's going to happen is because of AI, some of these moats are going to get more important and some are going to get less important.

[11:33](https://realalpha.app/v/SlGRN8jh2RI/?t=693) And so, like, for example, one that gets less important is switching costs because you can just use the model and you can kind of port from one thing to a different thing. Another one that gets less important is process power. Because for companies whose moat is like workflows and process and things like this, Quad is getting really good at figuring out process. And especially with 4.7, it can just hill climb anything. So if you give it a target and you tell it to iterate until it's done, it'll just do it. I think this is the first model like that. So I think these are going to get less important, but I think the previous modes actually still matter.

[12:05](https://realalpha.app/v/SlGRN8jh2RI/?t=725) So this is like network effects, scale economies, cornered resources, things like that. These are not really changing with AI. I think the second thing is if you look at the number of startups today or maybe in the past 10 years, I think the number of startups in the next 10 years that are just going to disrupt everything is going to increase like 10x because right now you can be a tiny startup you could build a thing that's as valuable as a large company and you We can actually compete head-to-head. Because the large company has to evolve their business process. They have to evolve the way they work. They have to retrain everyone to use technology. They're going to face a lot of internal resistance to that. But, you know, no one here has that problem. If you're starting fresh, then you can kind of build with AI natively from the ground up. So, I don't know. I think it's the best time to build. It's the best time to be a startup. There's so much disruption coming.

[12:54](https://realalpha.app/v/SlGRN8jh2RI/?t=774) So there is hope for us after all. Thank you, Boris. I would love to open up to audience questions if anyone has anything they would like to ask. Dan? Hi. Yeah, I'm curious. You said that you built six months before there was product market fit, but now, given that the models are good enough, how much do you attribute the success of Cloud Code to the model versus product decisions in the field of the product? I think it's probably a mix yeah I think it's a mix I think if you asked maybe a year ago the ratio was maybe something like 50-50 maybe I don't know if you asked me six months ago the mix would be 50-50 what about in two years oh two I don't know dude we plan on like we plan one week out six months sometime in the future and by the way I think the reason it was 50-50 is you know I I like I did YC back in the day I was like the first hire at a YC company and like I did a bunch of startups and in startups like the thing that they drill into you and especially NYC over and over is build something people love and so it doesn't matter what the product is it doesn't matter like the model and all this stuff you still in the end have to build a thing that people love and I think that's that's why the product matters is we pay so much attention to

[14:09](https://realalpha.app/v/SlGRN8jh2RI/?t=849) the little details so that as you use it all day it's a really great experience

[14:14](https://realalpha.app/v/SlGRN8jh2RI/?t=854) **Boris Cherny:** I think as the models gotten better the harness kind of gets less important and

[14:18](https://realalpha.app/v/SlGRN8jh2RI/?t=858) I think like a thing that we're thinking about right now is like how do we evolve the harness so like how do we make loops more of a first class thing how do we make it easier to run a lot of agents you know beside you know like sub agents is one idea there's a bunch more stuff that we're cooking but I think in a year the model will be much better aligned and so all the safety mechanisms that we have today around prompt injection and kind of static verification of commands and permission modes human in the loop all this kind of stuff it's just gonna be less important because the model will just do the right thing so yeah that's that's That's my prediction.

[14:52](https://realalpha.app/v/SlGRN8jh2RI/?t=892) Thanks. Thank you. Do you want to toss the box, Dan? To zoom out a little bit from software, I think Cloud Code did a cultural change a few months ago where it democratized building software. You can see shop owners building their own software for themselves or even programming microcontrollers to control the light when someone opens the door. Do you see in the future building software becoming a skill like I know Microsoft Office? So it's a thing that everybody can do, not just people in the tech industry? Oh my God, yes, yes, yes. I think it's going to be even more than that. I think it's going to be, I don't know, it's going to be a skill like, yeah, like I know how to send a text message.

[15:40](https://realalpha.app/v/SlGRN8jh2RI/?t=940) I think, you know, like I read, my two genres are essentially sci-fi and tech history. This is what I read a lot of. And I think in tech history, there's one thing which I think to me is the clearest parallel for what's happening right now. And this is in the 1400s, the printing press in Europe. And what happened was before the printing press, essentially 10% of the European population was literate. They knew how to read and write. They were often employed by like kings and lords that were not literate. And their job was to, you know, their job was to read and write. And this is not something that everyone knew how to do.

[16:14](https://realalpha.app/v/SlGRN8jh2RI/?t=974) The printing press was invented. Then there were two more presses.

[16:17](https://realalpha.app/v/SlGRN8jh2RI/?t=977) **Boris Cherny:** And in the 50 years after the first printing press, there was more literature published in Europe than in the 1,000 years before.

[16:25](https://realalpha.app/v/SlGRN8jh2RI/?t=985) and over the same period the cost of literature the cost of a book went down like a hundred x and then you know it took a couple hundred years because you know learning to read and write is hard you need education systems and government and everyone can't be working on farms and so on but over the next few hundred years literacy globally went up to like 70 percent and so you know now we can all read and write and you don't need a degree in reading and writing to know how to read and write although still there are professional writers and that is the thing that you can do. So I think the thing that's about to happen, and it's going to be much faster than 50 years, is software will be a thing that is fully democratized that anyone can do. And, you know, there's a lot of corollaries to this. So for example, let's say you're writing accounting software. The best person to write accounting software, I think maybe even today, is not an engineer. It's a really good accountant. Because they know the domain really well. And coding is the easy part. It's knowing the domain that's the hard part. And I think this is just obviously see the future.

[17:22](https://realalpha.app/v/SlGRN8jh2RI/?t=1042) So one of the things Greg said was that you guys are living in the future a little bit because you get to have access to the models and the agents. There's an internal tool before you released it. Is the gap between where you guys are in engineering and the rest of the world, is that a month? Is it three months, there's six months? And is that gap getting bigger or smaller over time? Yeah, so internally, we use the same model as everyone else does. For us, the dogfooding is really, really important. So we use the thing that everyone else here does. We use a little bit of Mythos to try it, and then we use a lot of Opus 4.7 to dogfood it and to write most of our code.

[17:59](https://realalpha.app/v/SlGRN8jh2RI/?t=1079) I think on the model side, there isn't really a gap. It's pretty much mythos, and some descendant of that will become available at some point to everyone. I think on the product side, there's probably a far larger gap. And that's just related to us changing all of our processes. If you talk to people at Anthropic, we use Cloud for literally everything. And our clouds are talking all day. As my clouds are coding in a loop, they will communicate over Slack to talk to other people's clods that are also running in a loop to kind of figure out unknowns.

[18:30](https://realalpha.app/v/SlGRN8jh2RI/?t=1110) **Boris Cherny:** We have no more manually written code anywhere at the company. All of the SQL is written by models.

[18:36](https://realalpha.app/v/SlGRN8jh2RI/?t=1116) Everything is just built by the models. So I think actually the place that we're ahead is not the technology because the same technology available to us is available to everyone here because fundamentally we are building a platform. And so for us it's really important that developers can use the same thing that we're using and that we dog food everything that we put out there. But I think there's actually a far bigger lead in kind of the organizational structure and organizational process. And this is a place where, you know, hopefully we can talk about it in places like this and everyone can kind of learn from it and also evolve.

[19:06](https://realalpha.app/v/SlGRN8jh2RI/?t=1146) Yeah, and I think that's one of the advantages startups have. It's so much easier to start there. Jaron? Yeah, last time we talked, I think you'd mentioned, we talked a little bit about multi-agent and it was very in-coated at the time at a prior Sequoia event. And you mentioned that there were some things going down the pipeline. There's a thing you're thinking about. Now, obviously, there's slash batch, there's slash loop, there's subteams, there's teams. Can you speak some to either at the model level and at the harness level, how you're injecting priors in the harness level, how the objective function is changing at the model level to kind of make this experience around delegating work, spinning up agents better?

[19:39](https://realalpha.app/v/SlGRN8jh2RI/?t=1179) Because so much of the work is paralyzable. You can do so many things so much faster. And I feel like I have to overlay my own intuition for when to paralyze things rather than the model kind of understanding that you can spin up tens of agents for something. Yeah, I mean, on the product side, it really just comes down to prompting. that's that's how it is and so you know we tweak prompts to kind of help the model do stuff in parallel more but also honestly As the model gets better, it just naturally does this. And so something like loop, I found actually 4.7, it just starts doing, which is really cool.

[20:08](https://realalpha.app/v/SlGRN8jh2RI/?t=1208) It's like it does something like, you know, I'll tell it, go pull this data query. And it's like, hey, I noticed that the data is changing over time. I'll start a loop and I'll give you a report every 30 minutes. And I'm like, great, can you send it to me over Slack? And then it uses the Slack MCP to do that. So I think actually over time, it's not on users to figure out how to hold the tools better. and if that's the case it's actually a product design problem and like I'm not doing a good job. It's really on the model to do this stuff better and on us kind of prompting it so it naturally does this. So right now it seems like a lot of us use like Claude or Codex or these tools in the cloud to do a lot of our computing but then there are some very vocal advocates of have your AI be local and I could imagine over time as open way models and other things catch up that this could be more of a possibility for people to get really high quality coding assistance. So I'm curious your vision of say over the next like years or something like that do you see the trajectory of everyone still really relying on the like cloud centralized compute or is there a pivot to oh we all just have our local agents that we can rely on and they don't get throttled and other benefits.

[21:23](https://realalpha.app/v/SlGRN8jh2RI/?t=1283) Yeah, I think it, I don't know, there's maybe a few ways to answer that. I think maybe like kind of the most fundamental way to answer that is it doesn't matter. Because I think now we're getting to the point where the model is just able to figure it out. So I think like by a couple of years from now, the model is just going to be doing all the code, it's going to be starting the agents, it's going to be building the environments. And so like if it decides like actually I'll use like local models to do this, you know, that's what it'll do. I don't think these will be decisions that we are making as engineers anymore.

[21:50](https://realalpha.app/v/SlGRN8jh2RI/?t=1310) We have time for a couple more questions, so I can toss this out. Jamie? Nester. Thank you. It feels like one of the great decisions with Cloud Code was making use of the fact that a lot of developers' tools and workflows are local, but that isn't necessarily always the case for sort of general knowledge work with, you know, cloud tools. I'm curious how you're thinking about this with Cowork, of how do you give Cowork enough access to the tools that we use to be powerful the same way that cloud code is for developers yeah it's that's a really great question I know I know when I was a when I was at a big company we took like five years moving all the environments to remote It's just like so much work, especially at a big scale.

[22:33](https://realalpha.app/v/SlGRN8jh2RI/?t=1353) But for knowledge work, largely, it's there already with like Salesforce and Docs and things like that. For us, it's always just the simplest answer. It's just MCP. So the same MCP connector that you have in Quad AI, you hook up like, you know, Salesforce, you hook up Google Docs, Google Calendar. And then Cowork can use that, Quad CLI can use it, Quad Code, everywhere can use it. For the systems that don't have MCPs, like, do you think that's where computer use is going to be? a big opportunity? Yeah, I think computer use is kind of a catch-all. So I think currently, as far as I know, I think Anthropic is pretty far ahead on computers, and so if you use it through co-work, it's quite good.

[23:12](https://realalpha.app/v/SlGRN8jh2RI/?t=1392) So it's able to use pretty much any piece of software that you have on your computer. It's very slow, but it does it quite well now, especially with 4.7. Yeah, but I think otherwise, MCP is kind of the answer. And all this stuff just doesn't matter that much. It could be MCP, CLIs, APIs, is just some sort of programmatic access, because the model doesn't care. To the model is just tokens. All right, we have time for one more question. Ryan? Sean, do you want to toss the, thank you. You've kind of alluded to this, but if like some time ago you saw the product overhang and thought to build a product that would then become more interesting once the models got better, could you just talk, even in vague terms about the shape of a product you built today that you think becomes much more interesting as models get better in six months to a year? Yeah, Claude design I think is a really good example. It's pretty good today. It's going to get a lot better. There's also a few things that we're cooking up for Claude code that are going to be landing over the coming weeks, so you'll see those. And then I think loop and batch and things like this around massively parallelizing agents, that's going to get better. I think computer use is another good one. All right, Boris,

[24:26](https://realalpha.app/v/SlGRN8jh2RI/?t=1466) Thank you so much for joining us. I think we'll be here for a little longer if anyone has questions. Thanks, guys.