Agents on the Canvas in tldraw — Steve Ruiz, tldraw
Channel: aiDotEngineer
Published at: 2026-05-01
YouTube video id: sPUjIBH5Cwg
Source: https://www.youtube.com/watch?v=sPUjIBH5Cwg
Hello. Hey, I'm going to I'm going to kick off. Uh Sorry, we're starting a little bit late here. I am Steve Ruiz from Teal Draw. Does anyone know Teal Draw? Yes. Hey, all right, fans fans in the room. Uh if you don't know Teal Draw, Teal Draw is kind of kind of a couple of things. Teal Draw is a online whiteboard. You can go to it. It's free. It's really nice. Um I'm going to be using it for my slides. Uh Teal Draw is also a startup. We're based here in London. And Teal Draw is also an SDK, something that you can use to build other products. So, if you've used uh Replit's new um uh agent canvas, then that's built with our canvas. If you've used uh um Luma AI's new canvas, that's built with our canvas. If you've used Stitches' new canvas, that's not built with our canvas. But, if you go into this like kind of uh um annotate mode, this actually is our canvas. So, we're we're in there somewhere. It's a Angular app, you know. Uh So, anyway, um Teal Draw is again company makes a whiteboard makes whiteboard SDK. Part of the idea with the SDK is that you can build cool things with uh with the SDK, which means it's part of my job to build cool things with the SDK to prove it. Um and a lot of those things recently have have involved AI, right? Hackable canvas runtime built with React. In fact, the canvas is also just React components. So, component component component. Um which means you can do some pretty cool stuff. Uh first one uh I'm going to be at the mercy of the demo gods here in the the internet and and and other things. So, uh bear with me here. Um does anyone remember this app Make Real? Maybe maybe this tweet uh about Make Real. Did anyone Did anyone remember seeing this tweet back in 2023 when the vision models came out? All right, cool. Uh this was one of the first projects to kind of like break containment uh in um in AI. Don't We're going to go to my phone. [ __ ] this. Um which which may may itself be a disaster. Uh So, the the basic idea with Make Real was that you could um use a canvas, draw this and send that to a a model and and have it make it into a working prototype, which sounds very very quaint in 2026. But, in 2023, it was all the rage because there was no lovable, there was no kind of vibe coding hadn't been termed or coined as a as a term. Uh and so, this was one of the first projects where non-technical people could make technical stuff without having to code or to look at code. And so again, we are at the mercy of the the uh several [ __ ] various internet uh internet gods. So, so we'll see. I'm going to I'm going to let this cook for a minute. Um but at the risk of leaking my API keys, I will try and switch to a faster model. Oh, no, it's it's coming. All right. Maybe I just gave it something hard to uh hard to work on. We'll see. Hang on a second. Basic idea, something like that. Uh yeah, there there There's my API keys. I always got to rotate them every time I uh do this demo. Sadly. Uh we'll see how much how much gets spent before I get done with the talk. Um but it is a very simple problem. It's just like go go make this interactive. This is uh this is not what I asked for, but we'll see. All right, good job. Cool. And this is a this is a working working thing, which is great. It's like a real little bit of HTML. But, you could also annotate on top of it. And you could say like, "Hey, uh actually, make this green." And why don't we use these colors? I'm going to make this red and uh and and black. Um Use these colors. Right? And so, you're kind of constructing a prompt here, even the prompt that includes the old uh website. And uh there's not many apps that have actually like kind of use this Only only now, only like the the Google Stitch that I mentioned before, uh this idea of Well, uh it didn't do anything that I asked it for. Terrible demo. We're going to we're going to move on. Things have changed in the last couple of years. Anyway, uh there was another one in Teal Draw computer, which I'm actually not going to go into, but this was uh a couple of like chains of prompts. But, eventually we we were like, "Hey, AI on the canvas actually might be pretty cool. Maybe we should um have the AI kind of work as a collaborator, like work with you on the canvas." So, the first one of those was pretty pretty straightforward idea where you could say like, you know, draw a cat. You could do anything. You could say um draw me a diagram, you know, finish my slides, complete this graph that I'm working on, things like that. Uh and unlike maybe image models uh like diffusion models and things like that, it's not building an image. It is using text structured outputs to to make the same things that I could make, right? So, I have I have tools. I have like circles and shapes and like this. Uh and it's funny to see how these things have changed over Oh, it's sad. Uh but uh the uh you know, the fun of of this is as a way of exploring the model and and what the model knows and how it can comport all that stuff. Uh make the cat blow out the candle. Um It's pretty cool. You could also do something like uh draw a mouse. So, multiple um multiple prompts at the same time on different parts. And so, even though I didn't tell it what a candle was, and I certainly like the application doesn't know what a candle is, uh and I'm not even sure that cats can like blow. But, it's correctly interpreted that and kind of incorporated into the into the design. So, uh with incredible detail as well. Still sad. Uh so, the um this was really fun because this is like solving a lot of problems that might not be obvious. Like like vision models, when it comes to to structured data, um number one, there's much less vision training data than there is for text. Uh number two, a lot of that training data like conflicts in ways that text does not and other other types of things don't. So, for example, the the Y axis on a on a Cartesian graph, as you go up, that number goes up, right? So, 0 1 2 3 4 5. Uh on the web, the Y axis goes up in this direction, right? The top left corner is zero, your top left corner here, but as you go down, the Y goes up. There's left, right, like there's your left, there's stage left, there's all sorts of uh uh things that that conflict within language uh and within images. So, um training the model to kind of behave predictably and and produce things like this is uh was really Well, I used training uh prompt engineering the model to to do it was was really tricky. But, this was fun um but we felt like it it didn't go really far enough because it was just one shotting, right? We wanted to do an agent. So, this is what Cursor looked like back in uh in 2025 or something like that when I did this. Um draw a diagram uh of the life cycle of a butterfly. So, this put it into a kind of like agentic loop, like you might have seen seen elsewhere. Um but I'm sure you you interact with dozens of times a day by by now for this crowd. Um where you have it produce an output and then review the output and kind of iterate until it thinks it's done. Um And we really tried to adhere to the conventions at the time of um you know, coding agents that were where these agents um this agent loop was seen most most often. Where yeah, there's kind of like a lot of sub features like rejection, you know, seeing it's thinking, seeing seeing how it works. Um Great. And now we have the uh the butterfly life cycle on the canvas. Pretty cool. However, this was still not really enough because as as cool as this was, it still felt like I don't know. It felt like I was handing my keyboard to some some other AI rather than someone collaborating with me. Um although this model has been used really well in uh a lot of design apps that use Teal Draw, uh things like Lovelace or Magic Path, um and in in education, especially where you have this kind of tutor of like, "Help me with my homework and help me fill out my um you know, uh Oh gosh, let's see if I can do this on the fly. Steve Ruiz uh class, you know, age, whatever. Um and you can kind of ask it to like uh complete my D&D character sheet. All right. And it'll it'll kind of pick up what you're doing and fill out forms and do it do do fun stuff like this. Maybe I'll come back to that as it as it kind of chugs along. The what I really wanted is like to bring the the agent out of the sidebar and into the the canvas itself. Um Oh, I'm a fighter. Nice. Nice. All right, I'll take that. Uh and so, we did. And we did it with fairies, which maybe maybe you saw, maybe not. Um these are like little little guys on the on the canvas. You can kind of throw them around. Uh they don't like to be held for very long. They'll start freaking out. Uh yeah, okay. So, uh and uh but you can do the same thing like, you know, draw a a draw cat or something like that. Now, putting the agents on the canvas have a whole bunch of interesting things. You can see the state of the agent, right? These are multiple agents that I'm kind of running in in coding terms, these would be multiple terminal windows or something like that. Or this would be in composer composer. But you can kind of see what they're doing in a way that uh uh hang on. I'm zoomed way out. I did all the sprites myself. Um and you know, not only can you kind of see it's thinking, but you can see its action. You can see where it where in the project it's sort of like acting relative to the other um other agents. So, and you know, these other agents can can see each other what they're doing. So, if I ask this one to draw um a hat on the cat, uh and I draw this one uh draw the cat's neck. It looks like we missed the we missed the neck. Uh they'll they'll they'll get to work, right? And they're they're able to kind of work with each other's stuff at the same time. Um but we could also ask them to work together. So, if I grab all three of these uh these fairies fairies, Helen, and Joan, um draw some more animals. Uh one of them will be elected leader. So, this one is is the leader. And it's going to go scout kind of what's going on on the canvas, and then it's going to create a to-do list, and it's going to delegate that to-do list to the other agents, right? Um this is all like we we were doing this in like December October of last year. Uh and we're figuring this stuff out at the same time that a lot of people were figuring out agent orchestration. This idea of like, okay, how do we give them shared state? How do we uh you know, have a leader follower? Like, how do we manage the fact that these things are essentially blind while they're working? And prevent them from kind of overlapping uh in terms of like what they're doing. And so, you can kind of see the the the leader here isn't doing any of the work. Uh but it is going to kind of like observe Oh, no, that's that's the leader. That's the leader. Um it's observing. Uh uh and and judging and and establishing whether this is like done or not and and whether it's done correctly. Um Still not enough. Right? Fairies are fun. If you want to play with this, by the way, this is at fairies.tldraw.com. Um in the same way that Make Real was a really good introduction to um to just AI at all, right? Draw something, click a button. Um fairies is a great way to talk about like multiple agents kind of working together. Uh and they can do real work. Let me try and grab a like this is a big description of like an ebook or something like that. And if I summon my fairies, uh uh make this make the make make the wireframes for this app. Cool. And I'll I'll just kind of let them let them get to work while we keep talking. Um the started 10 minutes later. I'm going to I'm going to take another 5 minutes before I jump. Uh the next step for this one is to to kind of give more access to the canvas to the agents. Um and there's really we started to kind of run into the barriers of of safety. Like, what is actually safe to to do with our hackable thing for for users? Um because we have a runtime API. You can just code against it, right? And AI is really good at coding. So, maybe we could do some sandboxed, you know, stuff. But no, because we need the DOM. We need the kind of the browser as a way to see what's going on. We need to be able to generate screenshots, all this stuff. Um so, we decided to use our uh our desktop app instead. So, I over the holidays I threw together a um an app that does an electron wrapper that wrapped tldraw. Uh and I opened a port essentially. I said, you know, okay, Claude, like make a little HTTP server and and open a put up an endpoint. And anything that gets posted to that endpoint, uh treat it as JavaScript and run it. Which is a terrible idea. Not a good Like, don't don't don't do that on on your app. However, for an an offline desktop app that is file-based, like what's the worst that could happen? You could hurt yourself, I guess, but you're not going to hurt the rest of me. Uh and look at them look at them going. It's building my little ebook reader. It's fantastic. Thank you, fairies. Doing the the Uh so so, what does that What does that give us though? Um I'm going to I'm going to skip the demo where uh as you can imagine, I could I could say, hey, visualize this code. Make a diagram. Cool. All right, I'm going to change the the diagram. Update the code to match the diagram. Easy, right? You can have these kind of like, let's pull up the the level of abstraction that we want. Um but the the more surprising stuff was actually where I was like, you know, okay, like check this out. Uh I'm going to draw a little user interface or whatever, right? And I want this to be uh leg length. And I want this to be a t-shirt color. Uh and even though tldraw doesn't really have the ability to we don't have like primitives for on hover, on click. It's not like it's not a fully thing. This thing can write code against the editor. So, like uh make it interactive. And and we'll see we'll see where it gets to. Um so far, the results on this have been like really really cool in ways that are super strange and disturbing. Uh because like asking like the AIs are like, sure, let's do some scripts script injection, right? Like, that's the way that it documents itself is like, this is how you you should do this. Um it has no qualms at all, by the way, changing stuff that's on your desktop on your computer. If you've ever wanted to like, for example, like we uh one of our team, Max, was like, you know what? I don't like podcasts in my Spotify. I want to get rid of podcasts in my Spotify app. Claude, can you just do that? And it's like, sure. Let me go through the minified code of the bundle of the thing. Let me just rip and tear. Uh and it's happy to do it. It makes them happy. Uh they like it. Um oh, what the [ __ ] was that? Um I don't even know what you did. You made a an HTML What the What? Like, it it created a new HTML site on this? And this is the pointer? It's not even a slider. No, I I want to I wanted in in the tldraw. All right. Yeah, we don't we we love it. It's blinking as well. I don't know if you caught that. Come on, do it. Yeah, there we go. Let's see if it can Come on, let's go. Um So, yeah, like there's really like uh no limit to what what what it can do with the desktop app, and it's happy to do it in a way that um I can almost tell that it it it uh would love to do this to websites. Like, it would love like just Let me just get my get my claws in there. Um all right, come on, come on. Still not working. We're going to we're going to we're we're going to we're going to go. Set up the interactivity. Come on. Um this is going to be really fun. I think we're going to just release this. Uh we're the um I mean, the it is released, but the uh the notion that you can take like I love local-first apps. I love file-over-app. I love There's all these ideas that up to now have kind of been curiosities and uh almost like Hang on. Oh, come on. Oh, that's such a such a disappointment. We're going to have to catch me later. I'll make it work. Uh but now actually the like the idea of a local file-based thing that is is able to expose itself to to um to to Claude and agents like locally in order to to essentially script inject kind of motivates a lot of that that stuff which previously was idealistic into like, well, that's the only way that you could do this. If you really want to maximize the agency in order to maximize what it can do and take the risk uh and take on that risk, then you you kind of just need to hand that to the user and say, good luck. Um I think open Claude does this pretty well. But like, this these are sharp tools. Have fun, you know? Anyway, uh that is my agents on the canvas talk. Uh work continues. If you want to play with the fairies, I highly recommend it cuz it's super fun, and you will find things that surprise you that have surprised me. Uh they have IRC as well. Let me see. Yeah, anyway. Uh and if you want to follow along with tldraw, we are on Twitter X at tldraw, and then I'm at Steve Ruiz okay. I post a lot about this stuff. So, uh thank you for coming. Cheers.