Transcript: ‘How We Use Proof, a Collaborative Editor for Humans and AI’

The transcript of AI & I with Every’s Brandon Gell, Kieran Klaassen, and Austin Tedesco is below. Watch on X or YouTube, or listen on Spotify or Apple Podcasts.

Timestamps

1. Introduction and the origin story of Proof: 00:02:00
2. From Mac app to collaborative web editor: 00:07:24
3. What makes Proof “agent native”: 00:09:00
4. Live demo—watching an agent join and write inside a shared document: 00:14:30
5. How Austin uses Proof for creative writing and food journalism: 00:20:51
6. The challenge of multiple agents editing one document simultaneously: 00:24:30
7. When AI-written docs are better read by agents than by humans: 00:26:48
8. Brandon’s agent-to-agent collaboration loop: 00:29:30
9. Proof as a lightweight scratchpad versus existing tools like Notion and GitHub: 00:37:09
10. Why Proof is open source and what that means for builders: 00:42:18

Transcript

(00:02:00)

Dan Shipper

Special episode today. We have been building a live collaborative editor for both humans and agents. It works in the browser. We love it. We started using it internally. It’s 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. And we wanted to 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 Cora and also the father of compound engineering. I also want to welcome Austin. Austin’s our head of growth and you’re a Proof fan.

Brandon Gell

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. So what was it originally and how did we get here?

Kieran Klaassen

I know you talked about this for a while, maybe a year already. So yeah, bring us through all the pieces in your brain. And also, Dan is saying “we built this thing,” but really Dan built this thing and we’re just adding thoughts and things. Dan built this whole thing while growing the company, while being a CEO, just on the side coding, and he’s getting the vibes. He’s so happy doing this. Look at him. That smile right now. It’s his baby, so that’s really cool.

Brandon Gell

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 Dan just merged. I just submitted a PR that Dan’s going to—no, look, merge, probably—

Dan Shipper

Obviously straight to production.

Brandon Gell

And so now everybody’s like, “Oh wait, I want this feature.” It’s amazing. But yeah, Dan, why don’t you tell everybody—why did you start building Proof originally?

Dan Shipper

If we want to go way back, we incubated a text editor, a word processor at Every called Lex, almost three years ago, maybe more, which was the first time that we sort of combined text and AI together. That was built mostly by my co-founder of Every, Nathan. We spun that out as a separate company. And that was like your writing, but you’re writing with AI on the side or in line with you a little bit in the actual word processor, but it fundamentally is a word processor.

I think Proof is very different, which is—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. For example, when you’re coding with AI, you make a plan doc. And that document is mostly written by AI. Maybe you’re going in and doing some changes here and there, or asking it to change it for you.

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 the other place where I started to feel the need for this is we did this company planning exercise for our 2026 planning. Brandon set up these Notion agents, which helped us—for anyone who was running a business inside of Every, you get interviewed by an agent and then it turns that into a 2026 plan doc.

I just remember looking at all those plans and being like, wow, these are amazing. But also Austin submitted this super comprehensive growth plan. But has he really looked at every single line of this? Does he really stand behind every single thing? So the original idea for Proof is we needed a good way to tell what was human written, what was AI written, but also how much thought went into everything and what do you actually stand behind versus not.

The original version of Proof was a Mac app and it had a little gutter on the side that showed purple for AI and green for human, which it still has. But what was really interesting is in making the Mac app, I did all this stuff. It had this cool internal agent integration with subagents and all this stuff. But in using it, I was like, actually the killer feature is just being able to share docs. Because what we find is, 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 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. And that was sort of the evolution of it.

Brandon Gell

And I will say when you were building the provenance version of Proof, I was like, this is cool, but I don’t really get it. When you say it out loud, it makes sense. But I wasn’t reaching for it and I don’t think a lot of people were. I think the editorial team was excited about it, but everyone else was like, “Cool. Dan’s off doing this thing. Editorial team likes it, don’t really know 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. So it’s kind of just an interesting story of finding the fit, and now it’s a serious fit.

Kieran Klaassen

It’s also that whenever everyone uses Claude or Claude Code or some kind of agent to do work, we’re at this time where suddenly there is all this work done and there’s all this stuff generated, but how do you share it? It’s like the first step to memory or sharing or collaboration within a team, and it just feels like this is very natural as a glue to bring things together. Because humans can look at it. 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.

It’s equally accessible, and I think this is cool because this is your agent-native philosophy. This app is really built from those principles of agent native. I’d love to hear more—this is your first agent-native app in this way. What did you learn doing it that way? What worked, what didn’t work? Because you say you had all these agents inside, but there are no agents inside. But there are, because there are agents. Can you tell a little bit about what you learned there?

Dan Shipper

That’s a really good question. And yeah, I do think it has been really useful to do this because getting my hands in architecting the code—I mean, they’re not really in the code because I vibe coded this whole thing—but getting my hands in architecting the code has really helped me develop deeper opinions about how, for example, an agent-native product can work and what are the different types of agent-native products.

(00:10:00)

For example, you can be agent native without having an agent in your product. You can be agent native from an internal perspective—you have an agent in your product that can do anything in the product. Or an external perspective—any agent can connect into the product and do anything in the product. Both are valid. And sometimes you can have a product that has both.

I did actually like the internal version. But what I started to realize, especially once we had Claw—once you have a Claw, the Claw has so much context on you and what you’re doing that what you really just want is a Claw in your document with you. You want that co-author hanging out with you. Having an internal agent that doesn’t know any context is just not powerful, not that interesting.

I can imagine there are certain times where you might want a language model inside of it. For example, 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 a nice little LLM summary.

And I think there could be really interesting use cases for LLMs sometimes. Austin, you shared this document, for example, where we were having all of our Claws update the document and it just went nuts. It went crazy. And I think having an LLM playing a little bit of a traffic cop role inside of a document could be kind of interesting.

There’s lots of stuff to do, especially now that text is so cheap to produce. One thing that you care about is provenance, potentially. And I think that was less important than I thought, but you also need—I have this feeling like I need a canonical version of a document that doesn’t get updated unless 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.

That’s what I love about getting to build this stuff—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, and they can write a ton. It opens up all of these different possibilities for what you might want your text editor to be, especially if you’re mostly optimizing it for the agents to do the writing. Humans can write, but usually when I’m writing in Proof, it’s like I feel like I’m God coming down and just giving my little sentence or whatever. Because it’s so rare.

Brandon Gell

I think a couple other things that I realized through using it a bunch—I always knew that giving context to an AI is so important. But through Proof, I realized how important it is to create a really 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.” The other thing that I realized is when Dan first told me about it, I was like, “Oh cool, but we need a place to save these things.” Which is true, and we’re going to launch that. But it actually doesn’t matter that much because the reality is plans are really short. They help you do long-horizon things, but in the grand scheme of things, they’re just a moment. Then they don’t matter anymore. So that’s been amazing.

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 make Proof documents when I want to make a plan. I don’t even need a place to save them because I just say, “Zosia, pull up the Slack to Discord Proof,” and she sends it to me. So those have been interesting experiences that are different from normal working.

Dan Shipper

Yeah, totally. It’s all sort of a function of text being really cheap to produce. It’s really valuable, but it’s also really cheap to produce. And so the way that you might design how you work with text has to change.

So I’m going to share my screen so we can show Proof. This is what it looks like. 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, nothing like that. And I can say “Proof podcast agenda.” And you can see it has this kind of green thing over here, which means I wrote this.

But the cool thing is, what I can do is press “add agent” over here. I can copy that link and give it to my Claw R2-C2, and I can say, “I’m recording a podcast. Can you fill in an agenda? It’s about the Proof launch.” And what you’ll see in a second is R2-C2 is going to actually join this document and write a bunch of stuff in there.

And then you can see R2-C2 here. He’s got a little Claw icon and you’ll see him in a second actually start to write stuff in this document. And then I’m going to share it with the podcast crew here so you can see everybody else here as well.

So if you guys want to join—you can see we’ve got Brandon in here. We’ve got an anonymous collaborator. I don’t know who that is. Hopefully nothing nefarious.

Kieran Klaassen

That’s me, I think.

Dan Shipper

That’s Kieran. And in just a second we’ll have R2-C2 posting a plan doc for us. Let’s hope it works. Live demos, folks.

Kieran Klaassen

It’s not live-live, so—

Dan Shipper

It’s not live-live. That’s true. Thank God. Here we go. We got a Proof launch podcast agenda. We got one thing. Woo. Yeah, go for it, Kieran.

Kieran Klaassen

What is very cool is you pasted this snippet inside your agent there. But you don’t have any skill or anything installed. It’s just copy paste, right? There’s nothing more than copy paste, which is very easy. It’s super low friction.

Dan Shipper

It’s just copy paste. And the idea is to make it as ergonomic as possible. One of my things that I’ve been saying recently, one of my bits, is I think AX is just as important as UX in this new world. AX is 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. So it’s really easy to be like, “How would you have made this better?” or “Why did you get confused? How would you make it more ergonomic for yourself?”

And that lets you iterate the AX so that it’s super intuitive for any agent to use it, and that’s what I’ve tried to do here. It is better if you have a skill, but it is totally possible for the agent to just basically figure it out because everything is available to it.

Kieran Klaassen

Yeah, that’s really cool. And I think because of that, 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.” And then you are already using it and sharing it. So that is very good. I think that is the major strength—that you can just immediately share this with an agent without logging in, creating accounts, anything. That is very good.

Dan Shipper

And here we are, we’ve got our podcast agenda. So you can see it’s all purple. We still have R2-C2 in here. We’ve got Brandon, we’ve got anonymous collaborator, and I can just go in here and say “hello.” Oh, that didn’t work. We’ve got some bugs here, folks. And I can just go in here and do “hello” and it shows up green. And that’s Proof. It has really changed, I think, the way a lot of us work.

Austin, I’m kind of curious from your perspective—on the growth side, are you using this, and if so, how? And how has it changed your workflow?

(00:20:51)

Austin Tedesco

Yeah, I use it in two kind of normal ways. Two of them just happened today actually. One is our colleague Rachel, who produces the podcast, made this Slack-based bot to make scheduling live streams easier. She made it in Cowork, 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 Claude Code 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 who, like me, are not technical but are pushing on these tools. I asked Claude Code, “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 lightweight and easy, and Claude, especially on Opus 4.6, 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 what you did to improve this.”

And it was really funny. Dan, you and I were talking about 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 provenance. You’ve got to send your boss this planning doc and they’ve got to see what you wrote and what the agent wrote.” And I had so much conviction about that. A couple weeks ago on Monday, you were like, “I don’t really care about that anymore. It matters, but actually this thing where it’s one space for agents and humans to work together is really powerful.”

And the other one that I’ve really loved as someone who does a lot of personal creative writing and comes from Substack, where people hold their own voice and writing so precious to them in a way that makes sense—people on Substack post all the time about how they know who’s writing with AI and they’re judging them.

I have loved Proof as someone who writes about food each week for a newsletter, because I am often like, I’ll eat somewhere and then I’ll text my Claw, “Here’s what I thought.” And I’m like, “Keep a running Proof doc of my thoughts from the eating I’m doing,” because that’s the best way to have a running doc. And then I’ll be like, I usually tell it, “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.

And I love that I can see what it wrote 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, have been really powerful for me.

Dan Shipper

I love that. I use it for that all the time. I use it for 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 there’s a lot of stuff happening all the time. 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, what did I do? What did I not do? Okay, R2-C2, my Claw, can you just go take the stuff I didn’t do and push it into the next day? Or can we figure out how to get it done? Can you just do it? It’s really helpful for that kind of async document creation and updating so that by the time you get into it, it’s ready for you to just get started.

Austin Tedesco

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 the GMs were like, “This is insane. I can’t focus, way too much is happening.”

Because what we were trying to do is I was trying to build this landing page that was an always-on reach test for Every—you could always go and see what our team is 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 duplicating and then triplicating the page. But it made me excited because this thing will be there, I think, relatively soon—that 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 as many agents as we have people, and for someone who does a lot of strategy docs in this world, it seems like such an essential way of working now once we get it right.

Dan Shipper

Yeah, that’s so true. And there’s this thing where one agent who does one bad thing can pollute the entire document. And that’s a really interesting problem to solve. You don’t have to worry about that in Google Docs because humans—there’s a big social cost to ruining someone else’s document. Humans are generally smart enough not to do that. But agents, with great power, they have a ton of power and zero responsibility. So they often just do stuff that you’d be like, “Ah, I don’t think I would do it quite that way.” And I think that’s a really interesting user experience challenge to figure out—how could you have 10 agents in a document and make the output actually good?

Austin Tedesco

Yeah, and the human-plus-agent collaboration—I think if it’s like only the agents are working in this and we’ll see what they come up with, that’s one thing. Or only we’re doing this and then our agents read it, that’s another thing. But coming to a future where we’re somehow all working in there together, whether it is a planning doc, a piece of writing—I think we’re headed there and that’s an entirely different way of working that we are breaking so that we can figure out how to make it work for everyone else.

Dan Shipper

Yeah. I think another thing that Proof makes me think about is, as people who love writing—and all of us here are writers—what does it mean for the future of writing? And there it feels to me like there’s a class of writing where 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. If you had written that document, I don’t think that she would’ve wanted to read that.

Austin Tedesco

No, and I think—I’ll share it right here because I think it’s interesting to see. I also don’t really think that she should read it. I think an agent should read it and summarize it for her.

Can you all see it?

Dan Shipper

That’s also probably true.

Austin Tedesco

Okay, cool. So yeah, the agent pushes this—there’s so much stuff in here that I would never write or care about. If I got this—say I built something, say I tried to ship something to prod and Dan, you were reviewing it and then you sent this back to me, a version of this for stuff I should have fixed—I would probably scan the headlines to 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 in how we work. The agents are making big docs. It even applies to the OpenClaw guide that you worked on with Willie the other day. 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. But when you write your essay on the future of agent-native architecture, I do want to sit down and read it. And it feels a little binary in my head, but I think it will keep expanding into more of a spectrum.

Dan Shipper

I definitely agree. I think there’s a lot of writing that is more on the information transfer end of things, and less on the storytelling and personal experience and vibe end of things. That is probably better read by an agent if it’s pure information transfer, because it’s a little bit like in The Matrix where you’re like, “I know kung fu.” That’s kind of the experience—having your agent read a Proof doc is like, “I know kung fu now.” 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.

(00:30:00)

Brandon Gell

I want to show the Proof experience that I just had, because I think it kind of highlights the collaboration between two humans and two agents.

So this is a little bit meta because I had Codex write a Proof doc about exploring the idea of adding a dashboard to Proof so that anytime you make a new Proof or somebody shares a Proof with you, it saves into a place that you can go so that you can see all your Proof documents.

I have zero idea how to code, by the way. I can literally write CSS and HTML. So I basically went back and forth with Codex a bunch and was like, “Okay, put this into a Proof doc.” 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 was I had Codex write this Proof doc. I went to our Proof channel in Slack and I dropped in the link and I said, “R-2C2”—which is Dan’s Claw—“check it out and let me know what he thinks.” R2-C2 knows Dan really well and gave a bunch of feedback, all of which was really accurate.

And then Dan, I think on the side, was like, “R2C2, make those updates.” It made those updates and then Dan came in here, reviewed it, he added a couple comments. So you can see—Proof does great commenting and agents can read the comments. Dan commented on here. I went through, made a couple more comments. You can see on the left side from the blue that this is basically all agent written.

So there’s one comment on this. I told Codex, “Go back in there, read the comments, and then update the plan.” It did that. And then I told Codex to execute on that plan and it did.

I mean, that is just sort of a loop that is kind of on repeat now at Every, where you make a plan, you send that plan to the product owner’s agent. The product owner’s agent does a review, suggests stuff—because agents can suggest stuff in Proof. It does that, then goes to the 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 my feature in Proof.

Dan Shipper

It’s pretty cool. Yeah, I saw that come in and then I talked with R2-C2 a little bit about it and I just had R2-C2 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, “Here’s how I would implement this.” And then that let you take Codex and have Codex just redo the whole thing. And what you ended up building was way more on target with what we might actually use. And it’s pretty cool that you’re just submitting PRs.

I’ve not looked at the PR yet, so it’s possible we need to start over. And that one’s a big feature. But it’s a whole new world that you’re submitting PRs, that I can even build this. This is a very complex app that I just did in my spare time, in between meetings. And not only am I building it—you’re submitting PRs, Kieran’s submitting PRs, Naveen’s submitting PRs. It’s becoming this collaborative thing that we’re all contributing to. Just a totally different way of building products that I’m really excited about.

Austin Tedesco

And it’s the exact type of writing that 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. I think like you said, and 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 something to be protected.

But when it comes to something like this, this is about information and ideas and accelerating how you distill them, accelerating how you implement them. That’s essential to where we’re headed. And I like it. It makes me so excited for how this works. And also for what is still valued and protected—the other kind of writing.

To me it’s easy when you think about this stuff but don’t practice it to think that they’re in conflict with each other and that one’s going to take away the other one. And then when you practice it, you’re like, this is actually a very different thing. They’re totally separate from each other.

Brandon Gell

Would you, Austin or Dan or Kieran, write anything that’s not a plan or something that’s kind of throwaway—it doesn’t have a long lifespan—in Proof, or would you go back to Docs or Notion for that?

Austin Tedesco

I’ll show you one example. I’m trying to write this thing for Saturday that’s an essay about a dinner I had at Squirrel, this restaurant in LA. And so to get there, it’s a bunch of texts between me and my agent to push to this Proof doc. And I like having these three separate sections.

Dan Shipper

And by text you mean you’re literally iMessaging?

Austin Tedesco

I’m iMessaging my Claw because I have these ideas. I actually get most of my ideas when I’m out on a run. And so after I’m done running, I’ll just 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 bank of notes I can go look at so I don’t forget stuff. Give me an outline of ideas to write into if I want to. And then maybe you can draft it for me, but I actually only let the agent draft for me if I monologue into it. Because then I’m like, it feels like 70 to 90 percent my words. I’ll use our speech-to-text tool Monologue so that I can see it.

And then my process here, which I’ve started doing in Proof, is I either rewrite every line or I’m like, “Okay, I can see the essay now.” It’s actually very helpful to see it. This is a lot of what Spiral does as our writing partner. And then I’ll either 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, it speeds up creative writing for me, and two, I think it does make it stronger and better and easier. I do sit here sometimes with some uncomfortable feelings of like, oh, am I taking a line the AI added in? Dan, you and I talked about this—a future version of this that I would love is if it identified what I monologued in, because to me, those are my words. 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.

Dan Shipper

I would love it if you hover over that gutter and it just popped out and said “from monologue” or whatever. I think there’s a lot of interesting stuff to do there eventually, once we kind of nail the most basic experience. This is super cool. I love that you’re using it for this. It’s so creative and interesting. Thanks for sharing.

Kieran, what’s on your mind? What are you thinking about?

Kieran Klaassen

Yeah, what I like about this is—clearly we need something to share stuff, and this is a step. I like how you built something more complex, agent native, and you realize actually we need to just go back to writing and collaboration.

And for me it really feels like a sketch pad or something like that where I brainstorm something, I’m like, “Ah, I don’t know, 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.

One other way I like it is when I do a brainstorm with a 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 tmux over SSH, so then I can just click the link and it works. That is nice. I can share it with people, but also I can just open it, go in, make suggestions in 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.

My question always with these things is like, yeah, but we have markdown files, right? Isn’t this just a markdown file? 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 with CLI and everything like that as well.

And what I like about Proof is—yes, we have all of these, but there are all these connotations around them. What a GitHub issue should be, or 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. 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.

(00:40:00)

Proof’s job is not to organize documents. Proof’s job is to communicate about writing and about ideas and about where it comes from. And I think it’s very strong. 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 a document and seeing this was written by Brandon, this was this agent. Maybe the history 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. We all feel these pains, and we’re just figuring out a new way to do this, and I like that it’s so bare bones.

Dan Shipper

Totally. I was very inspired by Naveen who runs Monologue, where it’s a simple product that does one thing super well. And I think that’s what I was trying to do here. And it’s actually surprisingly hard to make this, even though it’s simple.

Kieran Klaassen

Very hard. Yes.

Dan Shipper

Yeah, it’s hard. And Kieran, I love that you’re kind of picking up that the lightness of it is what makes it good. 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 after.

Kieran Klaassen

I still want to see your inbox feature, Brandon, but I’m just—

Brandon Gell

No, I understand. I totally appreciate that. Because you’re right. And I have five Proof docs open right now, and I really want just a quick place to go and be like, “Yep, that’s it.”

Kieran Klaassen

Makes sense. Yeah. Maybe you promote Proof documents to a special place. Proof documents are always there, but if you create an account suddenly you can say, “Put this in my special place” or something.

Austin Tedesco

I tried to make a big growth strategy plan in Proof. I think actually I was sending it to Dan and Brandon as a Notion doc and a Proof doc because I 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 campaign strategy in Proof, and then when it feels kind of ready—right now I’m using the CLI to move it to Notion, but I think that’s what makes sense to me. Let me actually one-click it into Notion, because that’s where our source of truth for planning and information lives.

And it’s like, okay, now it’s ready for that. It’s actually ready to move from lightweight to heavyweight. It’s ready to move from agent-based to calendar-integrated. And that’s a much more complex product. It’s probably unnecessary for what this project is, but that’s when it’s ready for that. And that started to make more sense to me.

Brandon Gell

Which leads me to ask you, Dan—this is going to be an open source product. Does that mean that people can submit PRs, or that they can just fork the repo and do their thing?

Dan Shipper

Both. But I think the most interesting thing is ideally you can integrate this into whatever app you want to build. We already have this internally. We have Spiral. Spiral needs its own live document editor. And this is just a really easy version that Marcus can just throw into Spiral.

Brandon Gell

It’s in compound engineering.

Dan Shipper

The hosted version is in compound engineering. But I think for any kind of builder—one, 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.”

But hopefully, if you’re making any kind of app that has a text editor in it—which I think anybody who has a Claw right now is running into, “I need a text editor for whatever app I’m making”—hopefully it’s just a really easy drop-in thing that you can use.

So that’s Proof, everybody. I’m psyched that we got it out, and I’m psyched for the future. And thank you all for joining and talking to me about it.

Brandon Gell

Thank you so much.

Austin Tedesco

Thank you so much.

Dan Shipper

See ya.

To read more essays like this, subscribe to Every, and follow us on X at @every and on LinkedIn.

For sponsorship opportunities, reach out to [email protected].