Now Anyone Can Code: How AI Agents Can Build Your Whole App

Nineteen eighty four, the Mac brought personal computing to to the masses. Twenty twenty four, we have personal software. You actually are going to be able to orchestrate this giant army of agents. And I think of Mickey Mouse and Fantasia just like, you know, like, learning this new magical sort of ability, and suddenly all the brooms are walking and talking and dancing.

And it's this incredible menagerie of being able to build whatever the heck you want, whenever you want. Someone who had an idea for fifteen years but didn't have the tools to build it and was able to build it in fifteen minutes, and he recorded his reaction. I almost shed a tear on that. Welcome back to another episode of the Light Cone. I'm Gary. This is Jared, Harge, and Diana.

And collectively, we funded companies worth hundreds of billions of dollars right at the beginning, just a few people with an idea. And today, we have one of our best alumni to show off what he just launched, Replit Agent. Amjad, thanks so much for joining us today. My pleasure. Thank you for having me. Yeah. So we just launched this product.

It is in early access, meaning it's barely beta software, but people got really excited about it. It works some of the time, so there's a lot of bugs. But we're gonna do a live demo here. And I wanted to, like, build an app, like a personal app that could track my morning mood correlated with, like, what I've done the the previous day.

So I want an app to log my mood in the morning, and also things I've done the previous day, such as the last time I had coffee or if I had alcohol and if I exercised that day. That'll send it to the agent now. You have the Slack chat interface. So you can see the agent just read the message, and it's now thinking. So what we're looking at here is actually how you might chat with another user.

Or is this specifically Yeah. I mean, it's similar. It's very similar to a multiplayer experience on Replot. Got it. So here, it's saying I created a plan for you to log your daily mood. The app will show your mood, coffee, alcohol consumption, and exercise. And it also suggests other features. So for example, it's suggesting visualization, and that sounds good.

Reminders, I don't know. I'll I'll remember. So let's just go with these two steps. I think what was also cool, it picked the tech stack that's very quick to get started. So Flask, Vanilla JS, Postgres, like, very, very good. So now we're looking at what we're calling the progress pane. So the progress pane is you can see what the AI is doing. Right now, it's installing packages.

It actually wrote a lot of code. It looks like it built like a database connection and all of that. And it's now installing packages, and we should be able to see a result pretty soon.

This is really cool because I think a lot of times for new software engineers, one of the annoying parts is just getting all the packages and dependencies and picking the right stuff, and this is just does it for you, the agent. So here we have we have our mood app. I can kind of put that I'm feeling pretty good today. I did have coffee yesterday, but I didn't exercise. I logged my mood.

Go to history. So built a complete web app with just a prompt, like no further instruction from you. Yes. And and it's it has a back end. It has Postgres. And I can just deploy this. So this is already pretty useful. You have this rating, and you have the history.

And it's asking me if it did the right thing. Oh, it actually is asking you to test it for them. Yeah. It actually did some testing on its own. So it took a screenshot here. And so it knows that at least something is presented, but it wants someone to actually go in and do a little bit of QA. Is it using computer vision to look at the screenshot? Okay.

Yeah. And now all the models are multimodal, and so it's fairly straightforward. What's on the back end right now? We have actually a few models because, you know, it's a multi agent system, and we found different models work for different types of agents. The main code gen one is Claude Sonnet three point five, which is, like, just unbeatable on code gen. It is, like, the best thing.

But we use GPT four o in some some some cases. There's also some, like, in house models. Like, we built the embedding model. It's a super fast embedding model, binary embedding model. And the retrieval system and then indexing, this is all built in house.

And a big part of what makes this work is is the sort of retrieval system because figuring out what to edit turns out is the most important thing for making these agents work. You're going a step beyond just Rack because Rack hits hit the limit for this, and you basically have to find a new way to search and find the right places to edit under code Yes.

Which is actually something that I don't think has happened yet, but I think is gonna happen that for all these multi agent system, people are gonna move away from Rag and start building custom orchestration like this. So this is very notable. This is like a very cool thing that you figure out. Yeah.

If just throwing the code base in REG is not gonna work, you actually have several different representations that allow the agents to do better work. That's right. And we have the trends thing working right now. Oh. Nice. So we have we have a couple graphs. We don't have a lot of entries here. I can actually ask it to Oh, yeah.

Change the XaaS XaaS. Create data. Oh, really? You can have it create data as well. Yes. Now it's asking me to deploy because it's done. It's like, how to deploy? And here, we have the activity trends, like how many what am I doing by day.

There you have it. It's going directly from just an idea to a deployed web app that anyone in the world can access right now. Exactly. And one of the things I'm really excited about is, like, this idea of personal software. Nineteen eighty four, the Mac brought, like, personal computing to to the masses. Twenty twenty four, we have personal software. I think we just experienced this.

You know, Karpathy just tweeted about Replit Agent. He said, this is a feel the AGI moment. Mhmm. Did you just feel the AGI? I definitely did. And I I did last night. Spent a few hours last night using Replit Agent to make a Hacker News clone. Nice.

There were a couple moments where, like, I really felt the AGI. Mhmm. The first was it actually had like really good intuition about what you buy to make and how to design it. We saw that there, where you didn't give it the idea to make the slider bar be like emojis. Yes. It just came up with that on its own.

And then the second thing was, when I was using it, it really felt like I had a development partner, where he would ask me questions, he would ask me to change things. At one point, it got stuck, I wasn't sure how to do something, and so it asked me how to do the thing, and then I told it, and then it like, cool, got it. And just like kept going. It it feels great.

And and sometimes you wanna give it some some help. Right? You wanna you wanna go debug if you know how to debug yourself or you go ask ChateapD about something and come back to it. Just give it more information. It'll be able to kind of react to it. You should have it definitely feels like talking to, like, a developer. You should do, like, the grok thing and have different modes.

You could have, like, graphchy programmer where it just tells you, like, ideas are bad. Bad and wants to build something else anyway. Oh, that would be cool. Just, like, have a, like, a toggle, for example, like an overengineer. Yeah. Yeah. Just, like, overengineer everything. Exactly.

So so it added this toggle, but I don't think it works. I don't think it connected up to the x axis. Yeah. Yeah. I I think this is interesting about all these AI programmers, which is that it's not like we created some super intelligence that somehow can just build an entire app perfectly from start to finish without making any mistakes.

It actually codes the way a human does, which is it, like, write some code, this is like, well, I think this is right, but I'm not sure. I guess I'll try it. And then it tries like, oh, no. I have a bug. It's like, it's the same thing. Yeah. Yeah. And and we again, the our our design decision has been always like, this is a a coworker.

And you can just close this. And you can go to the code. And you can code yourself. Just fix it yourself. Fix it yourself. And again, if you don't know how to code, my hope is, as you are reading what the agent is doing, is that you've learned a little bit of coding along the way.

And by the way, this is how I think our generation learned how to code, not through agents, but almost by doing these incremental small things like editing your Myspace page or doing a GeoCities thing. And I feel like we sort of lost that incremental learning scale where now you need to go to get a, like, computer science degree or go to a coding boot camp to kinda figure this out.

But if we made this, like, fun thing that people can go build side projects in and get exposed to what code is, think that would be perfect. And again, my view is that we're still far from fully automated software engineering agents, and people should still learn how to code. You have to do way less coding, but you will be you you will have to read the code. You will have to debug it in some cases.

The agent will get you fairly far, but sometimes it'll get stuck, and you need to go into the code and figure it out. Yeah. I think that that's actually pretty important. I'm I've been meeting a lot of, you know, 18, 19 year olds who are freshmen, and they're like, well, the code will write itself. Right? Like, I don't have to study this stuff anymore. And I'm like, no. That's not true at all.

Like, I actually think that now it is actually more leverage. It is far more leverage to know how to code than ever before. That's exactly right. Actually even more important, and it will make you way more powerful. Like, you don't have to be all the way in the weeds on everything. You actually are going to be able to, like, orchestrate this giant army of agents.

And I think of Mickey Mouse and Fantasia, just, you know, like, learning this new magical sort of ability and, like I love that. You know, suddenly all the brooms are, like, you know, walking and talking and dancing. And it's this incredible menagerie of being able to build whatever the heck you want, whenever you want, just like like literally from any computer, from any web browser. Yeah.

I I try to come up with, like, a Moore's Law type type thing where it's like the return on on learning code is, like, doubling every six months or something like that. So learning code a little bit in, you know, 2020, you know, was not that useful because you would still you well, you get it blocked. You wouldn't know how to deploy something. You wouldn't know how to configure something.

Let's go to 2023 with Chateapiti. Learn to code just a little bit. We'll get you fairly far because Chateapiti can help you. And then 2024, learning to code a little bit is a massive leverage because we have agents like this and others, and there's a lot of really cool tools out there like Cursor and others that will get you super far by just, like, having a little bit of coding.

And and just extend that forward. Like, six months later, you're gonna have even more power. So programmers are just on this massive trajectory of increased power. K. Tell us more about the tech behind this. It's kinda fascinating. At at the heart of it, it is sort of this, as I described before, it's multi agent system. You you have this core sort of React like loops.

So React is a, you know, an agent chain of thought type prompting that's been around for a couple of years now, and most agents are are built on that. But ours is also a multi sort of agent system. We give it a ton of tools using tool calling. And those tools are the same tools, again, that are exposed to people.

And by the way, you you need to be really careful about how to expose these tools and how does the agent see them. So for example, our edit tool returns, errors from the language server. So we have a language server here, a Python language server. It's like a human coding. You know, if if I make a mistake, anywhere here, it will show me. Right?

Similarly, when the agent is coding, it gets feedback from the language server. So again, you wanna treat it as much as you can like a like a real user. And so for for any action, it gets it gets sort of a feedback, and then it can react to that feedback. And so these are the tools. Again, this is package management, editing, deployment, all the database. All those are are tools.

And then there are a lot of things that make sure that it doesn't go totally off the rails because it's very easy. You we've all, you know, used Asians that go off the rails and go into endless loops. This still some sometimes does it, but we have another loop that is doing a reflection that's always thinking, am I doing the right thing? We use a lot of, LangChain tools.

So LangGraph is an interesting new tool, from LangChain that allows you to build agent DAGs very nicely, and they have a some logging mechanism and a tool called Langsmith where you can look at the traces. Looking at the traces for for DAGs is is very, very difficult and very hard.

So debugging these things have been fairly difficult because you you want a tool to actually, like, visualize the graph, and there isn't a lot of tools that do that right now. And so there's this reflection tool, reflection agent, and and the the other thing that we talked about earlier is, retrieval is is crucial. And, this this has to be kind of neurosymbolic.

It it has to be able to do rag style embeddings retrieval, but it has to be able to look up functions and symbols inside inside the code. This is why I do think I may be extrapolating a bit more even if we get into the world of foundation models that have really, really large context windows. I mean, Gemini already is in the millions of tokens.

You will still need very specialized things that do lookups like this because applied to different contexts, knowing the functions and treating it more like how it compiles at the end, like a AST graph. Large context windows are you can totally shoot yourself in the foot with them. Yes.

Because it's easy for the model to it's actually you know, the model will bias a lot more towards whatever is at the end. Kinda like a human. Yes. Exactly. And so you still need to do context management, and you need to figure out what to put on how to rank memories. So this agent, every time it does a step, it it goes into a memory bank.

And then every time we go into the next step, we'll be able to pick the right memories and figure out how to put them in context. If you pick the wrong memories for example, if you pick the memory that that, you know, had a bug or there was an error in it or whatever, it might still think that there's a bug.

But but if you already recovered from that, you wanna make sure that that memory of of having created a bug is is either kind of augmented by another memory of fixing it or entirely removed from the context. And so memory management is is crucial here. You you you don't want to put the entire memory in in context. You wanna be able to pick the right memories for the right tasks.

I feel like this is a really concrete rebuttal to situational awareness and that whole, like, sort of sci fi, you know, AGI is gonna kill us tomorrow kind of argument simply because that all is predicated on larger context window, more parameters, throw GPUs at it, and it's gonna work. Like, you can't just scale it up. Like, you're not going to get what you want from just scaling it up.

There is actually a lot of utility in having these agents work one with one another, with, being actually smart about, what is the intermediate representation and being able to pull back, you know, sort of model what a human would do. Mhmm.

I mean, this is sort of like the the case study and like, oh yeah, you can't just, you know, scale up everything by 50 x and have it work the way that they think it will. Yeah. In many ways, like, building a system like that sort of humbles you. You know, sets sets your expectations, about AI and the progress in AI in in in sort of a different way because, yeah, the systems are very fragile.

They're really still not great at following instructions. People talk a lot about the hallucination problem. I think the bigger problem is, like, just following orders. It's so hard to get them to actually do the right thing. What do you think is the path to AGI?

So my view in AGI is that maybe we'll get to something called we can call functional AGI, which is we automate all those sort of economically useful tasks. I think that's fairly within reach. I think it's almost like a brute force problem instead of the bitter lesson. Right?

Do you think it involves doing a lot of work like what you guys did, like, basically building, like, carefully fine tuning orchestrations of groups of agents for each task? So doing what you did for programming, doing it for customer support and for sales and for every accounting, every function. Yeah. I I think so. And maybe you can eventually put it all into one model.

The history of of machine learning has been we create the systems, we grow these systems around these models, and eventually the model will eat the the systems. So hopefully, like, everything that we did, at some someday, there's like an end to end system, machine learning system that could do it. Tesla, you know, famously, you know, had all these logic and and whatever.

And now, like, you know, I think after v 13, they there's just end to end training. And so, you know, eventually, we'll we'll get there. But but I wouldn't consider it true AGI because you throw something out of distribution at it, and they wouldn't be able to to to handle it. I think true AGI would require efficient learning.

Being able to be thrown in an environment with no information at all, being able to understand the environment by examining it, and learning a skill required to navigate that environment. And LLMs are not that. Maybe they're a component of that, but they're not efficient learners at all. You actually demonstrated this because the way you describe LLMs are intuition machines.

And in order to get them to work in programming tasks, you had to add this layer with symbolic representation, like in programming and ASTs. Like, a lot of concepts in programming and how computation works, Turing complete with DAGs and all that. Right? Yes. Exactly. Those are, like, very explicit classical computer science. Classical AIs. Yeah.

We do backtracking and all that. Yes. That's not generalized. That's specialized. Mean, incredibly useful specialized. Yes. So it's only been live for four days. Yeah.

But already, people have done a bunch of, like, really interesting and impressive stuff with it. Do do you wanna talk about some of the things that you've seen people do with it that are most, like, surprising and interesting? Yeah. One of my favorite thing that I saw was someone who had an idea for fifteen years but didn't have the tools to build it and was able to build it in fifteen minutes.

And he recorded his reaction, and it's like a personal app. He he built an app where he can put memories on a map and attach files and audio files to it. Memories about his life. I went to school here and, like, add a picture, whatever. When the app showed up and he tested it and he was like he was so surprised. I almost shed a tear on that.

I was like, you're being able to unlock people's creativity is is so rewarding. And then I want a integration with Apple Photos or to use it to actually build a a a export tool. Yes. And another user, Meike, built sort of a Stripe coupon tool. So he he has a course. He runs it on Stripe, and he wants, like, to be able to, like, send people coupons.

And so he built it on, like, you know, five, ten minutes. And, actually, I don't you would be able to build something like that in no code. You would struggle really hard. You would probably use two or three no code tools. People use like Bubble on the front end and Zapier in the back end and and what have you.

Sometimes I'm surprised the no code people are actually quite quite smart and quite hardworking because they figure out how to create these systems using no code. But it's just actually a lot easier to just generate the code for it. It's a coding tool for the no codes. Yes. Yes. And so, yeah, we we we're seeing a lot of traction there.

Which is actually a challenge, I think, the no code tools have in general is straddling this line between they start very much no code, and then they find that people keep pushing the limits on what they wanna build in these tools. And then and then the the frustrating part with no code tools is that if you hit the limits, you're just stuck. Like, you you just you can't solve it.

And the cool thing is if you were saying earlier, if you can get the no code people to switch to Replit, maybe initially they don't program at all. All they know how to do is like prompt it. But then, at some point, they're gonna like look at the code, and they'll realize that they can just edit it. Like, it isn't that hard. And then that's how they like gradually become programmers. Yeah.

That's interesting. I played around with it to build just like a simple recruiting CRM, which is actually the kind of thing you would have used Airtable for. Mhmm. And one of the suggested when it told me the plans, one of the, oh, would you like this feature? It was exactly that. It was just like role based permissions and all.

It was like, oh, that's pretty like a sophisticated prompt or suggestion off the bat. Yeah. That's a $10,000 a month enterprise feature right there that you could just prompt and have it work. It's crazy. I mean, this is like the definition of low bar high ceiling. Like, all of the biggest software companies in the world sort of capture that idea really powerfully.

So but my my favorite thing is is these order multiple order magnitudes sort of time difference of building something. Someone said they spent eighteen months building a startup. They were able to generate the same app in ten minutes using Replit. Someone said they they spent a year building a certain app that they were able to build it in an hour with with the Replit agent.

But, yeah, I think it will save, you know, millions of dollars of human hours. What a time to be alive, guys. Can I take a Repla Agent and apply it to my existing coding stack yet? Not yet. Got it. So, again, it's it's sort of super early. We built the again, the the retrieval system that we built is to be able to do this.

We should be able to throw it into any code base, index the code base really quickly, and be able to give it intelligence about the code base. The the system also has, like, summaries of files and summaries of projects. So we use LMs to kind of as we're indexing the system to create these, like, small summaries for the agent to understand what a project is.

So we have the infrastructure for it, but that's that's the next step. And and we also wanna add more autonomy for people who want it. So for the team version of this, we wanna be able to send it to the background. So be able to give it a prompt and then it forking the project, going and working as autonomously as it can. And then when it's done, it sends you a pull request back.

Or if it runs into a problem, it it it come back to you with a problem. The the other thing I I wanna do is, you know, the the vision for for this has been, you know, we we have this bounties program. And bounties, people submit things they want they wanna build or problems they have, and and peep people in our community users help them fix it for a certain price.

And I was thinking, you know, agents are not perfect, and so perhaps the agents can also summon a human. So another tool that it has is be able to summon like a bounty hunter. And so it will go to the market and ask the creator working with it, hey. Like, I'm running into a problem. Do you wanna put some money on it? And we can go, like, you know, grab an expert. And so I was like, yeah. Cool.

Yeah. Put $50 on it, and we'll go to this market. Hopefully, a real time market will say, oh, for $50, we have this problem. Can you come in? A human expert comes in as a as another multiplayer into the system, either helps you by prompting the agent or by going and editing the code themselves. That's so clever.

I mean, this whole thing of getting the human to be another agent in this greater intelligence orchestration system you have. Yes. I'm a big fan of Licklider's sort of human machine symbiosis. Right? That's that's always been the thing. You know?

You know, I like to talk about AGI and and all of that, but I I just feel like, you know, computers are fundamentally better by being extensions of of us and by joining with us as opposed to, you know, being this this, you know, this competitor. % with you. Team human. We need to print T shirts. You had a, I guess, sort of mini Chesky moment earlier this year then.

We're all blown away by this demo and sort of, you know, you've been working hard on sort of remaking the way all software is deployed and written for some time. I mean, what what did it take to, you know, get to this moment? You know, you did have to do a layoff and reset your org. You know? What happened? Yeah. So so last year, we we raised a raised a big round.

We we felt we're making fast progress, and there there was a lot of energy. And I I felt like I needed to, okay, grow the company. You know, for for a long time, Jared knows. For a long time, Raffle is, like, tiny. It was actually run out of your apartment Yes. For how many years? For many years. So like three or four years.

And we're like four or five people for like many years. So we started growing in 2021. Even when you had a lot of users. Yes. Like you were four or five employees when you had like millions of users. Yes. That's right. So we were always kind of lean, but I thought last year, Okay, we have really big ambitions.

We've to go hire people. I've got to hire executives. I've to create, like, a management structure. I've got to, like, grow up. Is that what investors were telling you? It's like, oh, you've to hire people. No. Actually, I I was Oh, were you thought of me?

My own. What you thought? But but it definitely was the prevalent advice. I mean, you were you were absorbing this advice from sort of like, the the world that was that ordinarily advises startups to do exactly that. That's right. That's right. And it just got really miserable. We had, like, you know, multiple layers.

We had different meetings where I'm trying to, like, run the company from. We had, like, a executive meeting, staff meeting, whatever. We had road maps. We had planning sessions. And I just couldn't shake the feeling that it was all LARPing. It was not work. It was LARPing. And but right now, we don't have a road map.

Right now, literally, we work on, like, three or four things. I'm involved in all of them, and I know what's going on there. I know what people are working on. And I think we got a lot more productive by getting smaller, by, you know, flattening the organization. I think one thing mean, that's a story that I think we've heard from many founders.

And one thing I'm curious to see how this plays out is I feel like what actually sparked off a lot of manager mode was feeling that people had more ideas to run with and they had, like, resources to execute on. Yes. And you realize that bureaucracy creeps in, and you actually just can't get ideas done as quickly as you want.

And so now I feel like everyone's getting rid of middle management, like and I'm curious to see if the same the same temptation, I think, will happen again. I think that we felt it a little bit personal even is when you make it easy to go from, like, zero to one, you it actually helps you create more good ideas because you're like, oh, yeah.

It's actually like I can get things off the ground really, really quickly. Mhmm. And so then it'll be interesting to see how people stay. Now you have, like, the smaller flatter org structure. You'll get more ideas for things you want to do and then staying, like, disciplined to not go back into the, oh, yeah.

Like, we should actually do, like, the 10 things we could possibly be doing versus, like, the five or six you can keep in your head, I think, is actually a challenge. I guess that there's a warring idea here because there's Parker Conrad's compound startup.

But the interesting thing about the compound startup is I think they're trying to explicitly make the other product lines feel like a startup and govern like a startup unto itself, which is like sort of the opposite of having like divisional responsibility.

I also think with Rippling and part like, Parker is known for having this hiring tactic of where he only hire or tries to hire a lot of former founders and then, like, puts them in charge of a product line, which has obviously worked really well for Rippling.

I think it's hard for most people to pull that off because you can't hire, like, the quality of former founder unless you have, like I think unless the company's already, like, proven successful or you're just like a top tier, like, recruiter, like, Parker's pretty, like, you know, top point 1% of ability to recruit really great people.

But Parker's totally founder moating, though, because we he gave a talk at YC Growth when we did this a couple years ago, and he was still doing support tickets. Oh, yeah. Yeah. Still is. He he told us that. Hosted him a couple of months ago, actually, right over there. And he said that.

He said basically he loves answering customer support tickets, and he will never let it go, because it's his direct line of information to know what's really going on with the customer. Yeah. Yeah. I mean, that's still fine and rewarding. I think maybe he's he's doing the, you know, compound startup. He's giving them a lot of autonomy, but he's in the details. Know, so.

How did this play out for this AI agent? Like, like, we talked about how you built it technically. How did you build it organizationally? Yeah. Which is a whole big like, a big bet. It was totally new technology that, like, the Reflow team wasn't used to working on. How did you pull it off organizationally? Yeah.

Great question. We tried building agents multiple times in the past, and it's just the technology wasn't there. And finally, when we felt it was there, actually, one of our employees, Zen Li, who who's kinda started this new incarnation of this, made made a demo, and he showed me the demo. And it was so simple.

It was just like the agent, like, calling a couple tools and doing things in ID, but I could see that it's finally almost here. Like, I could taste it almost. And in that feeling, just just like, okay. We're gonna make this big bet. And so created something called the agent task force. So in the in the task force, it's like people from a lot of different teams.

So you have the IDE team present in the task force. You have the dev x team that works on package management and and things like that. You have UX and design component, and you have the AI team. So if the AI team at the center so it's almost similar to the diagram. So so in the we organize it in the same way that the diagram works.

The kernel OS is the sort of the AI team, and then they're connecting out to all these tools that are created by the tool teams. And then you have on top of all of that, you have the product and and sort of UX team that is working on on the entry points and how do you structure this, which was very tough as well. The design was tough. And we we had, like, two meetings every week.

On Monday, we had this four room meeting where Michele, our head of AI, will do, a run, and we'll see what's work broken, what's what's wrong with it. They'll come up with the priorities for this week. And then on Friday, we have the agent salon where I do a run, and I look at what's working, what's broken. I ask them about their priorities. We might reprioritize some things.

I might change some things in the product. We make big changes, like, rapidly. And so every week, we made a ton of progress. What does doing a run mean? Do doing an agent run. Literally actually going through and using the product and seeing where it broke. Seeing where it breaks and figuring out what the priority is in order to fix where it broke. Brilliant.

Yeah. Did each of the team basically build their own agent as well? Some of them did because some of them you had to the screenshot tool was an agent because you had to kind of have an AI look at that screenshot, come up with the thoughts, and then return them to the main manager agents.

So the ID team wrote the screenshot agent, and then the package management team kinda built probably the tech stack setup type of configuration, which is really cool. Yeah. It it worked the org org structure worked out really well. I I mean, surprisingly well because I think it is similar to how we worked when at the at the center was the user, and now the user is the AI.

What's coming next with the agent? Like, what's what do you wanna add to it? What what do you think are gonna be the big next leap forwards for it? Reliability. I think the the most important thing right now is reliability and making sure it's not spinning, making sure it's not breaking, and then expanding it to support any stack you would want.

So right now, we don't really listen to the user when they give us a stack. We we push back. The agent pushes back. It's like, ah, we're just gonna do it in Python or whatever. But if you really want Crafty engineer mode. Yeah. So we wanna be able to accept user requirements with regards to stack. Should have the Paul Graham mode where only write it in Lisp.

Yes. Anything else. This Modes thing is a really, like, a April fool thing. It's like Paul Graham, over engineer. Bad UI. Doesn't care about UI. Everything's literally correct, but very confusing. How about just the interaction?

I mean, you mentioned, like, Licklider and the whole human computer symbiosis theory. Like, is text, like, as far as it goes? Are there other ways that people you think will wanna interact with their AI agent? You should be able to, like, draw in the UI and communicate with the with AI by drawing. Right? You should be able to say, hey. Like, this button's not working.

Maybe move this here or this file, you know, is not you know, refactor this file, whatever. So, you know, if the whole thing is a canvas that you can draw on, you can communicate it a lot more expressively with the agent. And, of course, you're talking, you know, as opposed to typing, being able to talk and draw. It's imagine on the iPad too. We have an iPad app.

It could get really, really fun and creative. Kinda like a full UI mock up that you would do in Figma. You could kinda hand sketch it and get it to to do it. Like like how running a real engineering product team would feel like. That's right. And then we're gonna add, like, more simpler agentic tools. So right now, the agent kind of is you know, takes over, and it's, like, writing everything.

But a lot of people just want more agency, more advanced users. So we wanna be able to do, like, single step or single action agents. So I say, like, I wanna add this feature. Show me what you're gonna do. I'll do a dry run, show you all the diff, show you all the packages it's gonna install, and then you'll be able to accept it or reject it.

And that way, more advanced users will have more control over the code they're writing. Amjad, thank you so much for coming and showing us the future in such a profound way. If I wanted to do this all myself, what would I do? Well, first of all, I want to say it's, again, barely beta software.

If you're brave and you wanna test it and give us feedback, go to Replit, sign up for our core plan because this thing is expensive. We can't give it away for free. And and you'll be able to see that module on the home page that says, what do you wanna build today? And then you can go through that and start working with the agent. Just have an idea in your mind. Just write a couple sentences.

Don't don't make it too complicated or too technical and and get started. You'll get a feel of how to work with the agent pretty quickly. It should be pretty intuitive. And share with us what you're building. Happy to kind of reshare, retweet whatever feel people are building the agent. Amazing. Well, it's time to feel the AGI. We'll see you guys next week.