We Made a Document Editor Where Humans and AI Work Side by Side

[00:00] it became clear that what we needed was [00:02] a live collaborative web-based document [00:06] that [00:06] humans and agents could be in at the same time making changes and leaving comments and doing track changes and all that kind of stuff. I'm trying to write this thing for Saturday. That's like an essay about a dinner. I had it [00:16] squirrel. [00:17] this like restaurant in LA. [00:20] And so to get there, it's like a bunch of texts between me and my agent. [00:24] to push to this proof [00:26] Doc. [00:27] using my agent's [00:28] and proof to get here. [00:31] One, speeds up creative writing for me, and two, I think does make it stronger and better and easier. [00:38] And I love that. And I can see what it wrote versus what I wrote for me, which is really helpful and so much better than a Google Doc. [00:58] Work moves fast. And in the age of AI, the pressure isn't just to move faster. It's to make sure what you send really sounds like you. From emails to proposals to stakeholder updates, generic and rush just doesn't cut it. And if you've ever stared at a blank page, knowing exactly what you want to say but not how to start, Grammarly fixes that. Grammarly gives you one place to think, write, and finish your work right where you already write. Most AI tools either take over or stay out of the way. [01:25] Grammarly doesn't either. It helps you break the blank page, adjust your tone so a message lands right for the specific person reading it, and works seamlessly across 500,000 apps and sites you're already in. It's loaded with agents built for every step of your process. 90% of professionals say it's helped them save time. 93% says it helps them get more done. This is AI that works with you, not over you. In a world of generic AI,

[01:50] Don't sound like everybody else. [01:52] With Grammarly, you never will. Download Grammarly for free at grammarly.com. That's grammarly.com. [01:58] And now, [01:59] Back to the episode. For a special episode today, we have been building a live collaborative market editor for both humans and agents. [02:07] It works in the browser. Um, [02:09] We love it. We started using it internally. It's like really kind of taken off inside of every. And so today we are launching it as a full product that you can go use. It's totally free at proofeditor.ai. It's also open source. [02:23] And we wanted to just do this episode to talk a little bit about proof, what it is, why it's cool, how we built it, all that kind of stuff. So for people who don't know, Brandon, you are the COO of Every. And Kieran, you are the GM of Quora and also the father of Compound Engineering. I also want to welcome Austin. Austin's our head of growth and your proof fans. [02:46] I think we should go back to you, Dan, and be like, why is it even called Proof? Because it's not called Proof because of what it is now. It just happens to sound good. [02:57] And so what was it originally and how do we get here, too? I know you talked about... [03:02] this for a while, maybe a year already. So yeah. [03:07] Bring us through all the pieces in your brain. And also, Dan is saying... [03:12] we built this thing, but really Dan built this thing. And we're just... [03:19] Adding thoughts and things. Dan built this whole thing while growing the company, while being a CEO, just at the site, vibe coding, and he's getting the vibes. He's so happy doing this. Look at him smile right now. It's his baby. So that's really cool.

[03:38] Yeah, so the CEO built a new product on the side that now everybody uses that's sick. And Naveen just submitted a PR that... [03:48] Dan just merged. I just submitted a PR that Dan's going to no look merge probably. Obviously, straight to production. And so it's like now everybody's like, oh, wait, I want this feature. And... [04:01] Um... [04:03] It's like kind of, it's amazing. [04:05] um but yeah dan why don't you tell us why don't you tell everybody [04:09] Why did you start building proof originally? [04:11] I mean, if we want to go way back, you know, we incubated a text editor, a word processor at Every called Lex, like almost three years ago, maybe more, which was the first time that we sort of combined... [04:25] Um, [04:27] text and AI together. And that was built mostly by my co-founder of Every Nathan. We spun that out as a separate company. And that was like, you're writing, but you're writing with AI on the side, or in line with you a little bit in the actual word processor. But fundamentally, as a word [04:50] very different, which is [04:51] Um [04:53] It's for this mode of writing that I've started to feel like a lot of us internally at Every are starting to do, which is, for example, when you're coding with AI, you make a plan doc. [05:05] And that document is mostly written by AI. And maybe you're going in and doing some changes here and there, or asking it to change it for you.

[05:15] And that's a whole different way of interacting with writing. I think a lot of people have said for a while, oh, I'll never read AI writing. And it's like, actually, I read AI writing all the time. And actually, the other place where I started to feel the need for this is actually we did this. [05:30] company planning exercise for our 2026 planning Brandon set up [05:36] these notion agents, which helped us for anyone who's running a business inside of every, you get interviewed by an agent, and then it turns that into a like 2026 plan doc. And I just remember looking at all those plans and being like, wow, these are amazing. But also, Austin submitted this like super comprehensive growth plan, but [05:55] Has he really looked at every single line of this? And does he really stand behind every single thing? [06:03] And so the original [06:04] idea for proof is like we needed [06:07] a good way to tell [06:09] what was human written, what was AI written, but also like how much thought went into everything and what do you actually stand behind versus not? [06:17] And, um, [06:18] Thank you. [06:20] And so like the original... [06:22] version of Proof. It was a Mac app and it had a little gutter on the side that showed like purple for AI and green for human, which it still has. But what was really interesting is in making the Mac app [06:37] I did all this stuff. It was a sick Mac app. It had this cool internal agent integration with sub-agents and all this stuff. [06:44] But in

[06:45] using it, I was like, actually, the killer feature is just being able to share. [06:49] Thank you. [06:50] It's just being able to share docs. [06:52] And because what we find is, you know, if I'm working on a little thing with an agent and I make a plan, I really want Kieran to be able to look at it. And I really want Kieran to be able to leave comments. And I really want Kieran's agent to be able to look at it. And so it just sort of became clear that what we needed was... [07:09] a live collaborative web-based document that humans and agents could be in at the same time, making changes and leaving comments and doing track changes and all that kind of stuff. [07:20] And [07:20] That was sort of like the evolution of it. [07:23] And I will say, when you were building, like... [07:28] the provenance version of proof [07:30] I was like, this is cool, but I don't really get it. When you say it out loud, like it makes sense, but I wasn't like reaching for it. [07:38] And I don't think a lot of people were like, I think the editorial team was excited about it, but like everyone else was like, [07:43] Cool, Dan's off doing this thing. The editorial team likes it. Don't really know exactly what's going on. And then the second you made it a web app and you made it a collaborative thing that agents and humans could work on together, basically every single one of us started doing everything in there. [08:02] um [08:03] So, [08:04] It's kind of just an interesting story of like finding the fit and now it's like a serious fit. [08:11] And it's also whenever like everyone uses clothes or clothes or some kind of agent to do work. So we're also at this time where suddenly like,

[08:22] there is all this work done and there's all this stuff generated, but like, how do you share? It's like the first step to like, [08:30] memory or sharing or collaboration within a team. And it just feels like this is very natural as a glue. [08:37] to bring things together because humans can look at it. Like I can look at it, I can open it, which is nice. I can trust it by looking at it. And an agent can do it as well. Like it's equally. And I think this is cool because this is your agent native philosophy. Like this app is... [08:57] really build from those principles of like agent native and, [09:03] Yeah, I would love to like, this is your first agent native app in this way. Like, what did you learn doing it that way? Like, what works? What didn't work? Because you say, I had all these agents inside, but there are no agents inside. But there are, because there are agents. Like, can you tell a little bit like what you learned there? That's a really good question. And yeah, I do think it has been really useful to... [09:28] do this because getting my hands in the code [09:33] I mean, they're not really in the code because I vibe coded this whole thing, but getting my hands in architecting the code, I'll say that, has really [09:43] help me develop like deeper opinions about [09:46] how, for example, an agent native product can work and what are the different types of agent native products? So like, for example,

[09:52] Um, [09:54] You can be agent native. [09:56] without having an agent in your product. [09:59] because you can be agentated from an internal perspective. You have an agent in your product that can do anything in the product. [10:06] or an actual perspective, any agent can connect into the product and do anything in the product. [10:11] and both are valid and sometimes you can have a product that has both. [10:14] Um, [10:16] And I did actually like the... [10:20] the the internal version but i think what i started to realize especially once we had claws once you [10:25] The Claw has so much context on you and what you're doing [10:28] that [10:30] what you really just want is a claw in your document with you. You want that co-author hanging out with you. [10:37] And having an internal agent that doesn't know any context, it's just sort of it feels like not [10:44] It's not powerful. It's not that interesting. [10:46] And I can imagine there are certain times where you might want a language model inside of it. Like for example, we have this [10:53] way to, um, [10:54] We're working on a way to summarize the document for the social share. So when I share it with you, you kind of get a little bit of a preview. And that's like a nice little LLM summary. And I think there actually could be really interesting use cases for LLMs on [11:08] sometimes you know austin you shared this document for example [11:12] where we were having all of our clause update the document and just went, it just went nuts. It went crazy. And I think having an LLM playing a little bit of a traffic cop role in inside of a document could be kind of interesting. Like there's lots of stuff to do.

[11:27] especially now that there's, um, [11:31] Thank you. [11:32] Now that text is so cheap to produce, [11:35] one thing that you care about is provenance potentially. And I think that was less important than I thought, but like you also need... [11:42] I have this feeling like I need a canonical version of a document that like doesn't get updated in less... [11:49] I really say yes. And then I want the agents to have all these other versions that they can mess around with. And we can take what's good about each of the different versions and put it into the canonical version. So that's what I love about getting to build this stuff is you start to get intuitions for-- now that we've relaxed this constraint, now that agents can write inside of a text editor super easily, [12:10] and they can write a ton, it opens up all of these different possibilities for what, you know, what you might want your text editor to be, especially if you're mostly optimizing it for the agents to do the writing and humans can write but like, usually when I'm writing in proof, it's like, I feel like I'm God like coming down and just like giving my like little sentence or whatever. Because it's so rare. [12:32] Yeah. [12:34] I think we should, I think a couple other things that I realized through using it a bunch is like, I always knew that giving context to an AI is so important. [12:43] But through proof, I realized how important it is to create such a good plan, how much more effective it is to create a good plan, and then say, "Go do that plan." Proof is a place where you can do that. You can work on the plan together and then say, "Go do that plan." And I know we all have really good examples of that. The other thing that I realized is, like, Dan, when you first told me about it, I was like, "Oh, cool, but we need a place to save."

[13:10] These things, you know, which is true. And like, we're going to launch that, but it actually doesn't matter that much because the reality is like plans are. Yeah. [13:21] really short, like they help you do long horizon things, but in the grand scheme of things, they're just like a moment. [13:28] And then they don't matter anymore. [13:30] So that's been amazing. Like I have five proof documents open right now. And especially because I make them with my claw, because my claw has a skill. And she just knows to like make... [13:44] proof documents when I want to make a plan. I don't even need a place to save them because I just say, "Zosha, like pull up the Slack to Discord, Discord to Slack proof," and she sends it to me. [13:55] So those have been like interesting experiences that are different than, you know, [14:01] Normal. [14:02] working. [14:03] Yeah, totally. It's all sort of a function of text is really cheap to produce. It's really valuable, but it's also really cheap to produce. And so the way that you might design... [14:15] how you work with text has changed. So I can [14:20] I'm going to share my screen so we can... [14:22] we can show proof [14:25] Um... [14:26] So this is what it looks like. [14:28] It's just, this is the landing page. It will actually be different by the time this episode airs, but this is the landing page and it's super simple. You just press start writing. And now you're in a document. That's all you have to do. There's no login or nothing like that. I can say,

[14:44] Proof, Podcast, Agenda, and you can see it has this green thing over here, which means I wrote this. [14:51] I can do a little title. [14:53] But the cool thing is, [14:55] And I probably have to change my sharing settings in order to show you this. [15:00] Thank you. [15:01] The cool thing is that what I can do [15:05] is [15:06] Um, [15:08] I'll show you. [15:12] what I can do is I can press Add Agent over here, [15:15] And I can copy that link and post and give it to my claw or two and I can say I'm recording a podcast. [15:22] Um... [15:25] Can you fill in an agenda? It's about the proof launch. [15:30] And [15:32] What you'll see in a second is R2 is going to actually join this document and write a bunch of stuff in there. And you can see R2 here. R2 is right here. He's got a little claw icon. [15:45] And you'll see him in a second actually start to write stuff in this document. And then I'm going to actually share it with the podcast crew here so you can see everybody else here as well. [15:56] you can see [15:57] We've got [15:59] Brandon's in here. [16:01] We've got an anonymous collaborator. I don't know who that is. Hopefully it's [16:06] Nothing nefarious. [16:08] Um, that's me. I think that's Kieran. [16:12] And in just a second, we will cut through this, but in just a second, we will have R2 posting a plan doc for us.

[16:22] And [16:24] Let's hope it works. Live demos, folks. [16:28] it's not live live so [16:31] It's not live live. That's true. Thank God. Here we go. We got a proof. We got a proof launch podcast agenda. We got one thing. Woo! [16:42] All right. We're going to go for it here. Yeah. What is very cool is you pasted this... [16:49] snippet inside your agent there. [16:53] But you don't have any scale or anything installed. It's just copy-paste, right? There's nothing more than copy-paste, which is very, very... [17:02] easy it's super low friction it's just copy paste and the idea is to um yeah make it as ergonomic as possible one of my things i've been saying recently one of my bits is um [17:15] I think AX... [17:17] is just as important as UX. [17:20] in this new world. And AX is just agent experience versus user experience. And what's really interesting about AX is if you want to optimize it, all you have to do is ask the agents. [17:30] So it's really easy to be like, [17:32] How would you have made this better? [17:35] Um, and, or how would you, why did you get confused and how would you make it more ergonomic for yourself? [17:41] And that lets you iterate the AX so that [17:45] Um, [17:45] it's super intuitive for any agent to use it. And that's what I've tried to do here, where it's, it is better if you have a skill, but it is, um,

[17:57] it is totally possible for the agent to just basically figure it out because everything is available to it. [18:03] Yeah, that's really cool. And I think because of that, [18:07] Like I started using it immediately because it was so easy to get started. And then you feel it. You're like, oh, this is super handy. And you're like, oh, but I want some refinement here. Let me create a skill around this, do something like that. And then. [18:21] you're already using it and sharing it. So that is very good. Like, I think that is the... [18:26] the major strength is that you can just... [18:29] immediately share this with an agent without logging in, creating accounts, anything that is very good. [18:36] And here we are. We've got our podcast agenda. And so you can see... [18:42] You know, it's all purple. We still have Archie in here. We've got Brandon, we've got anonymous collaborator and I can just go in here and say hello. [18:52] Oh, that didn't work. [18:55] Wow, we've got some bugs here, folks. [18:57] And I can just go in here and do hello, and it shows up green. And that's proof. [19:03] And it has [19:05] really changed, I think, the way a lot of us work. [19:08] Austin, I'm kind of curious from your perspective, [19:12] you know, on the growth side, like [19:15] Are you using this? And if so, how? [19:17] Um, and, and how does it, yeah. How has it changed your workflow? We like to move really fast at every, we're always shipping new features and we run five products internally with just 20 people. It used to be that updating any of our landing pages was a huge time suck, but then we started to use Framer. Framer is a website builder that works like a design tool, which means that the people who are closest to your brand and your customers can shape your landing pages themselves. Non-coders on our team use it all the time to ship website updates. And the results honestly

[19:47] easy to use. There's real-time collaboration, which means your team can design together, see changes instantly, and ship faster. A robust CMS gives you everything you need for great SEO and content management. [19:57] It also has advanced analytics with integrated A-B testing that lets you optimize and improve continuously. Then it's just one click to publish. Your changes go live in seconds so you can iterate at the speed of your ideas. And it's not just us. Companies like Perplexity, Miro, and Mixpanel trust Framer for their websites because the tool is enterprise-grade. They offer premium hosting, enterprise security, and 99.99% uptime SLAs. Whether you're launching a new website, testing landing pages, or building out your full site, Framer gives you the tools and support to move fast and build something great. [20:27] Everyone on your team can use it. [20:29] Learn how you can get more out of your dot com from a framer specialist or get started building today at framer.com slash Dan for 30% off a framer pro annual plan. That's framer.com slash Dan for 30% off. Rules and restrictions may apply. Seriously, we use this tool all the time. You should really check it out. And now back to the episode. Yeah, I use it in two like normie ways. I really like two of them just happened today. [20:59] made this Slack-based bot to make scheduling live streams easier. She made it in CodCowork, sent it to me, and was like, hey, can you install this into Slack for me since I have admin permissions? And it didn't quite work right away. So I went into CodCowork and the CLI and made some changes to it until it started working. And then at the end of the session, it's a thing I started doing with a bunch of people on our team

[21:29] tools, I asked Cloud Code, like, hey, can you make a proof doc for Rachel so that she can see everything we did and just send it to her? And especially because it's so... [21:40] so like lightweight and easy and clod especially on opus 4-6 like knows how to recap that really well i sent it to her and she was like wow this is so helpful that i can see like what you did to improve this and it was really funny dan you and i were talking about like how we were going to launch this thing i think on monday and i had this whole plan in my mind of like oh it's all about providence it's all about you got to like send your boss this like planning doc and they [22:10] about that a couple of weeks ago on Monday, you were like, I don't really care about that anymore. Like it matters, but it's like actually this thing where it's like a, it's like one space for agents and humans to work together is really powerful. So there's that. And the other one that I've really loved as someone who does a lot of like personal creative writing and comes from a place at Substack where people like hold their own voice and writing so precious to them in a way that [22:40] still the time of like, I know who's writing with AI, and I'm judging them, right? [22:45] I have loved proof as someone who writes about food each week for a newsletter, because I'm often like I'll eat somewhere and then I'll text my claw. Like, here's what I thought. And I'm like, keep a running proof doc of my thoughts, like from the eating I'm doing, because that's the best way to like have a running doc. And then I'll be like, I usually tell it like, make me an outline. And then I get an outline. It's always updating. And then I'll go in and write into the outline myself.

[23:15] versus what I wrote for me, which is really helpful, and so much better than a Google Doc. I was doing that in Google Docs, and one, it's really clunky with agents in Google Docs. I'm not smart enough to figure it out. But also, I can't track what's me and what's the agent, which is really important to me. So those two, which are a little more personal work [23:33] stuff has been really, really powerful for me. I love that. I use it for that all the time. Like I use it for basically my daily to do list. I just do it in proof. And every week I make a new document, I pin it in Slack. And then I'm just, you know, we're doing a lot. There's a lot of stuff happening all the time. And anytime something happens, I'm just like, cool, throw it in my to do doc. And that makes it really easy for me to make sure, okay, at the end of the day, [24:03] to my claw, can you just go take the stuff I didn't do and like push it into the next day? Or can we figure out how to like get it done? Can you just do it? You know, that kind of stuff. It's really helpful for those like kind of async document creation and and updating so that by the time you get into it, it's ready for you to just like get started. [24:21] Yeah, I got really excited yesterday during the madness of all of our agents trying to update that doc for us, because I think Kieran, like you and actually it was funny, all of the engineers, all the GMs were like, this is insane. I can't focus. Way too much shit is happening. Because what we were trying to do is I was trying to build this like landing page that was an always on. [24:43] reach test for every of like, you could always go and see what is our team using for vibe coding, for writing, for research. And I was like, Oh, can our claws just update it themselves? And it's not quite there yet. They kept like trying,

[24:58] duplicating and then like triplicating the page. But it made me excited because it's like, this thing will be there, I think, relatively soon, right? That it's like your agents can go in and update stuff. And my agent can read what Kieran's agent wrote. And then I can read the changes. And for a company that's using like, as many agents as we have people, and for someone who does a lot of strategy docs, like in this world, it seems like such an essential way of [25:28] true. And yeah, there's this thing where it's like, one agent who does one bad thing can pollute the entire document. [25:34] Mm-hmm. [25:35] And that's a really interesting problem to solve. Like you don't have to do that. And you don't have to worry about that Google Docs because like humans, [25:42] there's a big social cost to like ruining someone else's document. And humans are generally smart enough not to do that. But like agents, [25:51] With great power, they have a ton of power and zero responsibilities. So like they often like just do shit that you would be like, I don't think I would do it quite that way, you know? [26:00] And I think that's a really interesting... [26:02] user experience challenge to figure out how do you, how could you have 10 agents in a document and make the output actually good? [26:10] Yeah. And the like the the like humans plus agent collabs. Like I think if it's like only the agents are working in this and we'll see what they come up with is one thing or like only we're doing this and then our agents read it is another thing. But coming to a future where like we're somehow all working in there together, whether it is like a planning doc, a piece of writing like stuff.

[26:33] I think we're headed there and that's entirely a different way of working that [26:38] We are breaking so that we can figure out how to make it work for everyone else. Yeah. I think another thing that proof makes me think about is... [26:45] As people who love writing and all of us here are writers... [26:49] Um, [26:50] What does it mean for the future of of writing? [26:53] And it feels to me like there's a class of writing where [26:59] you actually want to read it from the AI more than you want to read it from the human, which is kind of surprising and interesting. Like that document that you made for Rachel Austin... [27:07] If you had written that document, [27:10] I don't think that she would have wanted to read that. No, and I think the... I'll share it right here. I think it's interesting to see. I also don't really think that she... [27:22] should read it. I think like an agent should read it and summarize it for her. Can you also that's also probably true? Yeah. [27:28] Yeah. Yeah. [27:29] Okay, cool. So like, yeah, the agent pushes this like there's so much stuff in here that I [27:35] would never write or care about. If I got this, like, say, say I built something like, say, I tried to ship something to prod and Dan, like you were reviewing it. And then you sent this back to me, like a version of this for like stuff I. [27:48] should have fixed, I would probably scan the deadlines to like loosely see what this thing is. And then I would ask my claw to summarize it for me. And actually, there's been a lot of that now and how we work of like, okay, the agents are making big docs. It even applies to like the open claw guide that that you worked on with Willie the other day of like, I didn't read that whole thing. I had my agent recap it for me. And for something like that, that's what I want to do.

[28:18] do want to sit down and read it and um it's going to be like it feels a little binary in my head but i think it will keep expanding into more of a spectrum in that range of what is what [28:30] I definitely agree. I think that there's a lot of there's a lot of writing that is [28:35] more on the information transfer end of things and less on the storytelling and like personal experience and like vibe end of things. [28:44] that is probably better read by an agent. [28:46] if it's pure information transfer, because it's a little bit like in the Matrix where you're like, I know Kung Fu, you know? Like, that's kind of the experience that like having your agent like read a proof doc is, is like, I know Kung Fu now. And, um, [29:02] Yeah. [29:03] It's just harder. Like you actually don't need to know Kung Fu if your agent knows it. And you can save your brain for things that you're good at. [29:11] I want to show my the proof experience that I just had. [29:16] Thank you. [29:17] Because... [29:20] I think it kind of highlights like the collaboration between like two humans and two agents. So this is like a little bit meta because I wrote a proof doc about how [29:30] or I didn't write it. I had [29:32] Codex write a proof doc about... [29:36] Exploring the idea of adding a dashboard to proof so that any time you make a new proof or somebody shares a proof with you, it saves into like a place that you can go so that you can see all your proof documents.

[29:51] I have zero idea how to code, by the way. [29:55] I literally can write CSS and HTML. [29:59] Um... [30:00] So I like basically went back and forth with Codex a bunch and was like, okay, put this into a proof doc. [30:07] and then it made this proof doc. You can see the only thing in this entire document that has been edited by a human is Dan came in here and commented. So basically what happened is I had Codex write this proof doc [30:23] I went to our Proof channel on Slack, and I said, and I dropped in, [30:29] the link and I said R2C2, which is Dan's, uh, uh, plus one, uh, [30:36] to check it out and to let them let me know what uh [30:40] he thinks r2c2 knows dan really well and gave a bunch of feedback all of which was like [30:46] really accurate. [30:49] And then I think Dan on the side was like R2C to make those comments, make those updates. It made those updates. And then Dan came in here, reviewed it. He added a couple comments. So you can see. [31:03] proved us great commenting and agents can read the comments. [31:07] So Dan commented on here. I went through, I made a couple more comments. You can see on the left side from the blue that this is basically all agent written. [31:17] Um... [31:19] Yeah, so there's one comment on this. I told Codex, go back in there, read the comments.

[31:26] Um, [31:27] and then update the plan. It did that. And then I told Codex to execute on that plan, and it did. [31:35] So, [31:37] I mean, that is like just... [31:39] sort of a loop that is kind of on repeat now at every, where you make a plan, you send that plan, [31:49] to the product owner's agent. The product owner's agent does a review, suggests stuff, 'cause agents can suggest stuff and proof. [32:00] It does that, then goes to their owner who owns the product, in this case, Dan, says, hey, Dan, I did that. I made some edits. Can you review? Dan reviews, gives a thumbs up, and then I go back and I do it because this is like my future and proof. [32:14] It's pretty cool. Yeah, it's like I saw that come in. And then I talked with R2 a little bit about it. And I just had R2 write you a little letter at the top being like, here's what I like. And here's what I don't like. And then a technical appendix at the bottom being like, [32:30] here's how I would implement this. And then that let you take codecs and have codecs just like redo the whole thing. And [32:37] what you ended up building was way more on target with what we might actually use. And [32:42] It's pretty cool that you're just submitting PRs. And I've not looked at PR yet. So it's possible. If possible, we need to start over. And that one's a big feature. But it's... [32:53] It's a whole new world that you're submitting PRs and that I can even build this. This is a very, very complex app that I just did in my spare time in between meetings. And...

[33:04] And not only am I building it, like you're submitting PRs, like Kieran's submitting PRs, Naveen's submitting PRs, it's becoming this like collaborative thing that we're all contributing to. Just a totally different way of building products that I'm really excited about. [33:18] And it's the exact type of writing that like makes so much more sense to be summarized by agents to flow in between the three of you rather than any human reading the whole thing. Like I think like you said, like we're all people who care a lot about writing and good writing, the quality of it, the production of it, the consumption of it. And that's like something to be protected. But when it comes to something like this, this is about information and ideas. [33:48] And both like accelerating how you distill them, accelerating how you implement them is is like essential to to where we're headed. And I like it makes me so excited for how this works and also like what what is still valued and protected and kind of like the other kind of writing. Right. Like to me, they're like it's I think it's easy when you think about this stuff, but don't practice it to think that they're in conflicts with each other. [34:18] And then when you practice it, you're like, this is actually a very different thing. [34:21] they're like totally like separate from each other. Yeah. Would you, Austin or Dan or Karen, would you write, [34:29] Would you write anything that's not a plan or something that's like, I don't want to say throwaway, but like kind of throwaway, like it doesn't have like a long lifespan in proof.

[34:41] Or would you go back to like Docs or Notion for that? [34:43] I'll show you I'll show you one example. So like I'm trying to write this thing for Saturday. That's like an essay about a dinner I had at Squirrel, this like restaurant in L.A. And so to get there, it's like a bunch of text between me and my agent to push to this proof doc. And I like having these three separate sections. [35:13] I'll just like text everything so I don't forget it so they don't escape me. And I like having these three different sections where it's like, give me this like bank of notes I can go look at so I don't forget stuff. Give me a outline of ideas to write into if I want to. And then like maybe you can draft it for me. But I actually only let the agent draft for me if I monologue into it. [35:38] Because then I'm like... [35:39] It feels like it's like 70 to 90% my words that I'll use our speech to text to a monologue so that I can see it. And then my process here, which I've started doing in proof is I either like rewrite every line. [35:53] Or I'm like, okay, I can like see the essay now. It's actually very helpful to see it. This is a lot of what Spiral does to our like writing partner. And then I'll either like start fresh or I'll just copy paste the outline into somewhere new to get it. But using my agents and proof to get here, one, speeds up creative writing for me. And two, I think does make it stronger and better and easier.

[36:23] I added in and I Dan you and I talked about this like a future version of this that I would love is if it I if it identified what I monologued in because to me those are my words right like if I monologue something into the agent and it uses it those are my words and I want to know but I've started doing this a lot more. [36:40] I would love a little bit like if you go if you hover over that gutter, it just like popped out and said like, you know, from age from, you know, monologue or whatever. Like, I think there's a lot of interesting stuff to do there eventually once we kind of nail the most basic experience. This is I love this. This is super cool. I love that you're using it for this. It's so creative and interesting. [37:00] Yeah. Wow. Thanks for sharing. Awesome. [37:02] Yeah. [37:04] Kieran, what's on your mind? What are you thinking about? [37:07] Yeah, what I like about this is like... [37:10] Clearly, we need something to share stuff. And this is a step. [37:17] I like how you build something very more complex, agent native, like the way, and you realize actually, [37:26] we need to just go back to, it's just writing and collaboration. And for me, it really feels like, [37:34] It's... [37:35] It's like a sketch pad or something like that, where I brainstorm something. I'm like, oh, I don't know, like just put it there. And then I text it to you or you send something to me and you can kind of share thoughts or nuggets with each other. I like it for that a lot. [37:50] One other way I like it for is when I do a brainstorm with the compound engineering plugin, there's a step called brainstorm. At the end, it will say share to proof, you just do that, and then it will automatically share to proof and you have a shareable link. I run in T-Mux over SSH. So technically,

[38:07] thanks, then I can just click the link and it works. So that is nice. I can share it with people, but also I can just open it, go in, make suggestions. [38:18] in like an actual document and then just tell the agent, hey, made some comments, go work on them. So I also like it for iteration with the agent itself, just for myself. [38:34] My question always with these things is like, yeah, but we have markdown files, right? Isn't this just a markdown file? And we have GitHub. Isn't this just a gist or isn't it just an issue? We have linear, we have Notion, we have all these tools and they're pretty good CLIs and everything like that as well. [38:52] And what I like about proof is, yes, we have all of these, but there are all these commentations around and what a GitHub issue should be or like what a Notion page should be. And you don't want to contaminate everything. So I love actually that we don't have a place where you can see all your proof documents. So I would even argue we shouldn't have an index with all your proof documents because the point is that if you think it's important, you keep that link somewhere. [39:22] organized documents. Proof's job is to [39:25] communicate about writing and about ideas and about where it comes from. And I think that [39:35] It's very strong. And it's super seamless. Just that it's so seamless to share it with your agent. And we don't know what's next. But the cool part is Austin is saying, yeah, I want to see what I monologued into. And I also like going into document CA. This was written by Brandon. This was his agent. These were the history maybe on the document. I'm like, well, let's see what we need to add. And let's add that. So for me, it's very exciting because we have all these things.

[40:05] and they're like, we're just figuring out... [40:08] a new way to do this. And I like that it's so bare bones. Yeah. Totally. It's I was very inspired by Naveen, who runs monologue where it's like, [40:19] It's a simple product that does one thing super well. [40:22] And I think that's that's what I was trying to do here. And it's actually surprisingly hard to make this, even though it's simple. It's very hard. Yes. Yeah, it's hard. And Kieran, I love that you're kind of picking up the lightness of it is what makes it good. [40:38] Like you don't have to think about anything. There's no, where does this go or anything like that? It just works. And that's what we're, that's what we're after. [40:48] I still want to see your inbox feature, Brendan, but I'm just arguing that... [40:56] And [40:58] I have like five proof docs open right now. And I really want to just like a quick place I go to be like, yep, that's it. Makes sense. Yeah. Maybe you promote a proof document to like a special place. Like proof documents are always there. But if you create an account, suddenly you can say, put this in my special blah, blah, blah or something. Yeah. [41:17] I like, I tried to make a big, like, gross strategy plan in proof. I think actually I was sending it, Dan, to you and Brandon, as a Notion doc and a proof doc, because I, like, couldn't really craft it or figure it out. But I liked going back and forth in proof. And the thing that felt intuitive to me was, like, let me and either one or multiple of my agents jam on this, like, campaign strategy in proof. And then when it feels kind of, like, ready, right now I'm, like, using the CLI to move it to Notion.

[41:47] that's what makes sense to me is like, let me actually one click it into notion for us for notion, because that's where like, our source of truth for planning and information lives. And it's like, okay, now it's like, ready for that. It's actually ready to move from lightweight to heavyweight. It's ready to move from age from agent based to like calendar integrated. And that's like, not with this, that's a much more complex product and probably unnecessary for what this project is. But like, that's when it's ready for that. And that started to make more [42:17] - I'm gonna ask you Dan, this is gonna be an open source product? [42:20] Does that mean that people can submit PRs or that they can just [42:25] fork the repo and do their thing? Both. Both. But I think the most interesting thing is... [42:33] Ideally, you can integrate this into whatever app you want to build. [42:36] We already have this internally. We have spiral spiral needs its own. [42:40] like live document editor. And this is like, just a really easy version that Marcus can just like throw into spiral. It's the incumbent engineer. [42:50] It's in combat engineering. Well, the hosted version is in combat engineering, but I think for any kind of builder, A, it could just be a good example of this is what you can make and how you might want to architect things. If you're vibe coding, I know if you're a professional engineer, you might look at it and be like, holy shit, I can't believe this works.

[43:11] But B... [43:13] Hopefully, if you're making any kind of app that has a text editor in it, which I think [43:18] Anybody that has a claw right now is running into this. It's like, I need a text editor for whatever app I'm making. [43:25] Hopefully, it's just like a really easy drop in thing that you can use. [43:28] So... [43:31] That's proof everybody. I'm psyched that we got it out. [43:35] Uh, and I'm psyched for the future and, uh, thank you all for, for joining and talking to me about it. [43:42] Thank you so much. Thank you so much. Thank you. See ya. [43:53] Oh my gosh, folks. You absolutely, positively have to smash that like button and subscribe to AI&I. Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard. But instead of gold, it's filled with pure, unadulterated knowledge bombs about chat GPT. [44:15] on the edge of your seat, craving for more. It's not just a show, it's a journey into the future, with Dan Shipper as the captain of the spaceship. So do yourself a favor, hit like, smash subscribe, and strap in for the ride of your life. [44:30] And now, without any further ado, let me just say, Dan, I'm absolutely hopelessly in love with you.