SPEAKER_05
Codex is one of those things where three months ago, six months ago, it was trash. If anyone from OpenAI is on the call and listening to that, I stand by that 100%. If you have a great general purpose coding agent on your computer, it's actually really great for any kind of knowledge work. If it can write software on its own, it can do any kind of knowledge work on its own. [SPEAKER_07] When I sign on during the day, Codex is the first thing I open.
SPEAKER_07
It is pulling in whatever I need from Gmail, Slack, Notion, Stripe, all of our data sources. It's where I spend 80% of my time working because the app itself is just so good. [SPEAKER_05] There's a new operating system for how and where you're going to get your work done.
SPEAKER_05
And it's this kind of agent management interface. Hello, everybody.
SPEAKER_05
Welcome to Codex camp. Codex for knowledge work. Psyched to have you. Psyched to have you on this auspicious GPT 5.5 day after release day. Hope you're doing well. I'm here with our head of growth, Austin. Austin, say hello. Hello. We're psyched to have you. We are psyched to do this. Codex is one of those things where three months ago, six months ago, it was trash. And if anyone from OpenAI is on the call and listening to that, I stand by that 100%. And it was really built for senior engineers doing pair programming. So it would argue with you to make you feel stupid. It was a little autistic. It didn't have any emotional intelligence.
SPEAKER_05
And I think OpenAI had this interesting strategy or this interesting theory starting with GPT 5 that your vibe coding was going to happen in ChatGPT. And that was where all that stuff was going to live. And then senior engineers are going to use Codex to do all their programming work. But we're going to hobble the model so it doesn't do anything bad. It's in a sandbox, all that kind of stuff. And I think what happened is Anthropic figured out that having a model that's pretty usable and fast and smart and also emotionally intelligent on your computer that can access your computer is a really, really great experience for programmers.
SPEAKER_05
And it means you could throw away a lot of the old stuff that you used to have in a programming environment where it was built for typing code. You could just type commands into your terminal and then it would start working. And then I think what Anthropic figured out is if you have a great general purpose coding agent on your computer, it's actually really great for any kind of knowledge work. If it can write software on its own, it can do any kind of knowledge work on its own.
SPEAKER_05
And we started to move from this world where programmers had been delegating their tasks, starting to delegate their tasks inside of cloud code to now any kind of knowledge work is being delegated inside of cloud code and cloud co-work and all that kind of stuff. And I think OpenAI, they had this original split. It's like, oh, you're going to do all your vibe coding in ChatGPT. And I think they saw what was starting to happen with cloud code. And over the last maybe three months or so, they have done this hard pivot on Codex where it has gone from a senior engineer only tool that is really for pair programming to I think it is my daily driver for this kind of work.
SPEAKER_05
I use Codex for everything from deep engineering stuff to writing to recruiting. I do a fair amount of recruiting and it's really good for that. And I'll give you some use cases later. But they figured out that having this general purpose agent on your computer with the ability to write code, the ability to access your file system, the ability to have a browser, and wrapping it in a desktop app is the ideal, ideal next step for knowledge work. And I think that they built the best current version of that. And what is starting to snap into focus now is that there's a new operating system for how and where you're going to get your work done.
SPEAKER_05
And it's this kind of agent management interface. And that's whether or not you're using cloud code or cloud cowork in the desktop app or Codex in the desktop app. It's becoming this race between the model companies where each model company has their own surface for agent management, a desktop app for agent management. That's at its core a programming agent that's used for knowledge work. Anthropic has cloud code and cloud cowork. OpenAI has Codex. XAI recently essentially bought Cursor. And Google is the only one that, I mean, they have anti-gravity, but I don't think anyone is seriously using it for that yet. But I imagine Google will do this too.
SPEAKER_05
And that's the race. That is the race that's happening. And so I think for us who get all the benefits of being able to use these tools, it's really important to be bouncing around between these. So, for example, using Codex so that you can feel what it's like to work in an agent first world. Because once you add an agent that is your primary way of accessing and using software and the internet and all that kind of stuff, it opens up all this interesting stuff that wasn't possible before. Because you can send your agent out to go talk to other pieces of software and come back. And we can get into more of the details there.
SPEAKER_05
But I want to get into more of the concrete use cases. But that's the world that we're starting to live in. You're doing work on your computer through Codex or co-work. And your agent is your interface to a lot of the work that you're doing and a lot of the software that you use and a lot of the stuff that you do every day. And that's actually really fun. It's really cool. There's a lot of good stuff here.
SPEAKER_05
And so I wanted to bring Austin in to help do this because Austin is our head of growth. And I think he had his real agent pill moment. You tell me, Austin. But probably three or four months ago. And the agent pill moment was really cloud code. And I sort of remember you just being on a Monday morning, oh, I just was on my computer all weekend. I was 12 hours a day. I didn't go out or anything because I was using cloud code. And you started to use it for all the kind of knowledge work tasks that a growth marketer would. And over the last couple weeks as we've been using 5.5, and I've been telling you for a little bit, you should try Codex.
SPEAKER_05
It seems like you've actually just shifted everything over to Codex in 5.5. But probably three or four months ago. And the agent pill moment was really cloud code. And I remember you just being on a Monday morning being, oh yeah, I just was on my computer all weekend. I was 12 hours a day. I didn't go out or anything because I was using cloud code. And you started to use it for all the knowledge work tasks that a growth marketer would. And over the last couple weeks as we've been using 5.5, and I've been telling you for a little bit, you should try codex. It seems like you've actually just shifted everything over to codex in 5.5.
SPEAKER_05
And so I think you're a great person to talk about what you're seeing and how this has changed, how these agent management interfaces have changed your workflow.
SPEAKER_07
[SPEAKER_05] And then why you like codex. [SPEAKER_05] And then I would love to get into some demos of your actual codex workflow so that we can see things from your perspective. Yeah, that sounds great. So yes, my agent-pilled moment was spending a week going deep into cloud code in the CLI, probably in December into January, hooking it up to everything I do for work and for my personal life. And finding that I use warp as my CLI interface. And finding that the things that could automate, the things that could handle for me, and then the way it could work as a thought partner to make my work better.
SPEAKER_07
It was like, this is the only way I want to do the kind of knowledge work that requires strategic thinking and data analysis and shipping marketing copy, a bunch of stuff that can get you spread out across a bunch of apps and tools during the day. And maybe in February, you kept nudging me to be like, you really should try codex. There were things you liked about it. And if someone says that at every, if anyone on the team says that, I'll go try it. And I like to push myself and play around with more engineering-y tasks, especially to see what these models are capable of.
SPEAKER_07
And so I tried to build a personal vibe-coded app in Codex because that was one of the things that you said that it was really good for. And my immediate response was like, I think it is better at building the app, but I can't tell because nothing has ever made me feel more stupid than Codex two months ago. I always use Compound, our compound engineering plugin that Kieran Klassen made for basically everything, including knowledge work, but especially if I'm trying to build an app or ship a PR to the site. So I made a plan. In the plan, it comes up with three questions for which direction we should go. And I had no idea what the hell it was talking about.
SPEAKER_07
It was like, do you do any of these three? And every question, I was like, please explain this to me in more detail. And its response was basically, why? Why don't you just do what I'm recommending? And I found a way to, I basically stayed in Codex for all engineering stuff because I did like the results, even if I didn't love working in it. But I would say 80% of what I was reaching for was cloud code in the CLI. And when we got our hands on the new GPT model a month ago, the first thing I felt was, at the very least, there's parity between the latest Opus model and the latest GPT model for the kind of knowledge work I do. There's a few things that Opus is better.
SPEAKER_07
There's a few things that Codex is better. That feels a little more specific to me. Outside of design, which I still really trust Opus for, it feels a little more like, oh, there's some stuff I like better than this. But the real differentiator to me is that there's no comparison for how fast and powerful the Codex desktop app is as an app compared to the cloud desktop app. I have never been able to get a co-work to work for me. And I think it's because I've been ruined by the Codex app. It's so fast. The subagents are so good. The way in which it suggests and then ships automations for me is just, I can't imagine not using it.
SPEAKER_07
I wouldn't be surprised if any week the cloud desktop app is just as good. They could ship versions where it's faster and better. But I'm now at the point where when I sign on during the day, Codex is the first thing I open. It is pulling in whatever I need from Gmail, Slack, Notion, Stripe, all of our data sources. This morning, I was like, oh yeah, we need to do a run of show for this camp. I messaged Codex. I'm like, make the run of show. It knows exactly where to look because we've already had conversations about what we're going to talk about today. It pushed it to Notion. It sent it to Slack. It was perfect. It was like, oh yeah, exactly what we should do.
SPEAKER_07
And yeah, it's where I spend 80% of my time working overwhelmingly because the app itself is just so good.
SPEAKER_05
[SPEAKER_07] And then the model has gotten good enough to be the daily driver for me. Yeah, I feel the same way. I'd love to get into, and for people, someone asked, are we discussing the app or the CLI? We're discussing the app, the desktop app. And I think you're making a good point that both of these companies see the end game here and they're pushing in the right direction. And for a while, at least, it's going to be a horse race where every couple weeks or every couple months, one is going to pull ahead and have this amazing thing going on.
SPEAKER_05
And then the competitor is going to, like Anthropic, for example, I think will release something in a couple weeks or a couple months. I don't have any inside information into this, but that will make it at least parity, if not better. And they're just going to keep trading. And at some point, I think that'll slow down and you'll end up with separate ecosystems. But for now, they're actually fairly easy to switch between. It's not trivial, but it's pretty easy.
SPEAKER_07
[SPEAKER_05] You can ask Codex, can you go grab all my Claude stuff and it'll go do it. I think it feels that way when you do it. It's funny. I'm in New York right now. I usually live in L.A. Most of my friends who are in the knowledge workspace have been asking me about what they should be using. They're all Claude Code or Claude Desktop app pilled. And when I tell them that I have fully transitioned to Codex, this look of horror shows up on their face. And they're like, do I? They're kind of like, do I really have to? [SPEAKER_05] You can ask Codex to go grab all your Claude stuff and it'll go do it. I think it feels that way when you do it. It's funny.
I'm in New York right now. I usually live in L.A. Most of my friends who are in the knowledge workspace have been asking me about what they should be using. They're all Claude Code or Claude Desktop app filled. And when I tell them that I have fully transitioned to Codex, this look of horror shows up on their face. And they're like, do I? They're kind of like, do I really have to? And I, of course, tell them they don't. But I'm like, you really should. Right now, you really should. I think you would get a big benefit from it. [SPEAKER_07] And I've been showing them why. [SPEAKER_07] And it's interesting.
SPEAKER_05
[SPEAKER_07] To me, I'm surprised how resistant people have been to it. [SPEAKER_07] Because when you're a knowledge worker and you have all these new tools, the Claude Desktop app is game changing. [SPEAKER_07] It's amazing. [SPEAKER_07] Right? [SPEAKER_07] So the idea that the Codex app is maybe 30 to 40% better is like, oh, that's a lot of work, which we can get into how I migrated. [SPEAKER_07] I can show some of that.
SPEAKER_07
It was very easy. And the ways that I'm starting to use it. So I'm happy to dive into that and start sharing my screen and showing how it works. [SPEAKER_05] Why don't you share your screen? [SPEAKER_05] I think, yeah, I agree with you. [SPEAKER_05] It's more of an emotional thing of like, oh, I have to learn a whole new thing or whatever. [SPEAKER_05] But it's pretty similar. [SPEAKER_05] Yeah. [SPEAKER_05] I would love to see some of your workflows. [SPEAKER_05] Cool. So this is the Codex app. I was going to do a very quick tour. I think a lot of the audience has seen it for where I go and how I use it.
SPEAKER_07
One thing I love about the Codex app is I think it's much better organized than the Claude Desktop app. The ability to have these folders with persistent, consistent chats inside of it that I can go check out. And then especially the big differentiator is that because I think this is much better for engineering, occasionally I will ship a PR for one of our products. It's great to not have to switch between the Claude Code CLI, the Claude Desktop app and Codex, that I can be here. I can be working on improving our KPI sheet, which I'll show what I was doing here. And then I can go down to plus one and ship a PR for plus one.
SPEAKER_07
And the other thing I found because I tried the update to the Claude Desktop app last week when they shipped it. And the stress test I put on it was make a go-to-market plan for our new product and ship a PR to Sparkle in different chats. And it was so clunky and slow. And when you do stuff like that inside of Codex, it just works. It just works really quickly and well.
SPEAKER_07
And that's the thing that once you start feeling that, it's very hard for me to turn away from it. So I have these different folders for some vibe coded apps that I play around with for fun, for my personal open claw where I can go and manipulate it here. And then the one with all of the chats is this every growth OS. All this is is a folder with a bunch of secrets and keys. So it's connected to everything we use for every. And then some project instructional files that explain what the every business is, what we care about, how we like to work together. It has some reviewer agents inside of it that are all informed by how compound engineering works.
SPEAKER_05
[SPEAKER_07] Inside of compound engineering, Kieran's plug in, there is a compound engineering review step. [SPEAKER_07] Once you do some work that reviews for security and a few different things that are oftentimes not as helpful for I'm doing a strategic plan for a go to market initiative. [SPEAKER_07] And so inside of here, there's a fork for it for strategic alignment with the company goals or data accuracy. [SPEAKER_07] So how we win, to put it in the chat for people. We can put it in the email as well. And so all I did was I'm putting in the prompts here. I only have posted panelists access, so I'll send it later.
SPEAKER_05
[SPEAKER_07] For some reason. Okay. Yeah. Maybe read it out. [SPEAKER_07] We can all agree that housing is expensive. Rent or mortgage doesn't matter what you're paying. It stings every month, but BUILT can make it feel a little better. BUILT started out by rewarding members for their rent. Now, as of 2026, BUILT members can also earn points on mortgage payments wherever they live. Every housing payment earns points you can use for flights with top travel partners like United and Hyatt, Lyft rides, amazon.com purchases, and much more. This is actually pretty cool. And I have some friends that use this and they like it a lot.
SPEAKER_05
Something that's underrated is that BUILT members also get access to a neighborhood concierge. They can make restaurant reservations, book fitness classes, and find new local spots, all while still rewarding you at 45,000 merchant partners. It's like having a personal assistant baked into where you live. It's simple. Being a renter and now owning a home is better with BUILT. Make sure to use our URL so they know we sent you. And now back to the episode.
SPEAKER_05
Yeah. Okay. I can zoom in as well. I think. There we go. So through the plugin tool with Codex, I went in and did the manual clicks to connect all of the tools I use every day like Gmail, Slack, Notion. And then I went to a new chat inside of this folder that was built through Cloud Code. Cloud Code built this whole Every Growth OS system. There's a Cloud MD file in there and it's saved locally. It's also synced and pushed to GitHub. And so I just opened that project inside of Codex when I started working here. And I start a compound engineering brainstorm workflow because it is, Make sure to use our URL so they know we sent you. And now back to the episode.
SPEAKER_05
Yeah. Okay. I can zoom in as well. I think. There we go. So through the plugin tool with Codex, I went in and did the manual clicks to connect all of the tools I use every day like Gmail, Slack, Notion. And then I went to a new chat inside of this folder that was built through Cloud Code. Cloud Code built this whole Every Growth OS system. There's a Cloud MD file in there and it's saved locally. It's also synced and pushed to GitHub. And so I just opened that project inside of Codex when I started working here. And I start a compound engineering brainstorm workflow because it is again just a thing I reach for of let's think about this thing together, me and the model. And what I said is go take a look at the things I use the most, which are Notion, Slack, and Gmail, and think of some automations that would help me with my work. And I find that when I'm trying something new, whether it's a model or an app, having an agent, having a very smart frontier model, tell me how to use it, tell me what it should do is exactly where I want to start rather than thinking of it myself. And I usually start here. Sometimes I will describe a very specific problem, but this is very helpful for me. And I think a good generic problem for people to start with. And Codex comes back. It looks at what's going on for me and for the company right now. And I thought these were really good that it has this kind of follow up radar. This is a big thing that happens with people who do knowledge work, who do partnerships, who do social media marketing, that there's all this stuff coming at you across a bunch of different sources.
SPEAKER_05
[SPEAKER_07] Like, what if it handled the triage for you? What if it had this kind of command sensor when we run a camp or an event, which usually requires a bunch of moving pieces and moving parts? Like Dan mentioned for recruiting and hiring, we don't use a tool like Ashby or something, we kind of have it all synced through Notion. Because apps like this and agents can handle a lot of the pipeline and tracking work for us. And you can just ask it to automate it for you. And so it does that. And it asks me like, which ones look good? What do you want to tweak? For the sake of this demo, I didn't give it any real feedback. I was like, looks good. And this is actually the thing I've always been most impressed with Codex for and for the models is that it's great, I made this automation for you. And I do find that they just work incredibly well, they require very little tweaking to be like, this is a thing I would and do use every day. There's this set of instructions that it comes up with based on what it knows about me. I can change when it runs, I can give it additional insights, I can connect it to other things, but mostly just works. There's one that works for me that just at the end of each day now compiles all of the stuff that I haven't responded to yet, drafts the replies, and we can knock it out together of what to say, or actually, all I need to do is just give a thumbs up Slack reaction to something and it'll do that for me. It's a dumb agent. I think of agents like this as the dumb ones that just do the right thing every time. And then the smart ones like an open claw or a plus one the products we have coming that's like you'll work back and forth with it and have a more creative, strategic partner. And Codex is good at building both and I can show kind of the smart agent setup. But if someone is looking to be like, can I see what this thing can do to help me with knowledge work, I would start here in a brainstorming automation state because it is and I think you'll also be surprised by how fast it is. And you're like, oh, I'm starting to get what this thing can do. This is so sick. Your Codex usage is far surpassing mine in terms of interestingness. I'm getting a lot of ideas. I want to just actually pause here. Normally we take questions at the end, but I think it would be interesting if you have a question about what Austin has just shown. It would be nice to let people come up and just ask a question or two just to see what the vibe of the room is like. So please raise your hand if you have a question and we will call on you. Margaret, welcome. Please introduce yourself and ask your question.
SPEAKER_05
[SPEAKER_07] Hi, can you hear me? I'm Margaret. I'm in Plymouth. And my question is, what is your review step look like? So it's saying don't send post archive or modify without explicit approval. So what does that look like? Is that like, do you call up, say, hey, let's do the review flow now or is it doing push notifications to your phone or what? Thanks. Yeah. So for this, what I prefer, and I was actually talking to a friend at dinner last night who said they did the same thing on their own. They came up with this too, is everything I work primarily in Codex. I do all the drafting and setup in Codex. And then it's helpful for my brain to have the final review step actually live in the external app. So it will draft all the Slack messages. And then I can go to Slack where Slack has that draft reply tab and I can go and knock them out. And I do find that it freshens up my brain a bit to be like, here's where I'll just make sure that this is what I want to send to a human being. Same thing for email. It creates all of these drafts in Gmail and I'll actually go open Gmail and look at them and knock them out. I know some other people who just have it actually come up inside of Codex and they're like, yeah, sure. Send it. It looks good there. I do the same thing for strategic planning. It pushes to either a proof doc, the agent friendly marked out file that Dan made or a Notion doc. I use them for some different things. And I just for the last pass before humans engage with it to step away from this agentic space and have a final check in another surface. That's really the only time that I'm leaving the app to do something.
SPEAKER_05
[SPEAKER_07] That's brilliant. Thank you. [SPEAKER_07] Sweet. All right. We'll do one more and then we'll keep going. Alex, please introduce yourself and ask your question. Hi, my name is Alex. I'm a musician and I do a lot of gigs and get emails from clients all the time. So I have to sort my leads from my newsletters and all that informational stuff. So how do you make sure that you prompt Codex to keep those emails safe for me? The ones that make sure that I don't send something that loses me money or something. [SPEAKER_07] I'm leaving the app to do something. [SPEAKER_07] That's brilliant. Thank you.
SPEAKER_05
[SPEAKER_07] Sweet. All right. We'll do one more and then we'll keep going. Alex, please introduce yourself and ask your question. [SPEAKER_07] Hi, my name is Alex. I'm a musician and I do a lot of gigs and get emails from clients all the time. So I have to sort my leads from my newsletters and all that informational stuff. So how do you make sure that you prompt codex to keep those emails safe for me? The ones that make sure that I don't send something that loses me money or something.
SPEAKER_05
[SPEAKER_07] Yeah. So for me personally, I rely a lot on Quora, the internal app that Kieran runs at every for the AI email assistant that's a part of the every subscription. It's really helpful now that inside of Quora there is a CLI and API connector that I can work in codex and tell Quora, which is managing my email filtering and my email rules, what I want and what I value. The way I do that is the same thing I would recommend whether you use Quora or not, which is to have the agent interview you to get an understanding of what the rules should be. I always find that I get a better result rather than saying what I think the rules should be. And so I'll do a brain dump using monologue or speech to text app saying, here's the problem I'm facing. My email is a mess. Let's figure out how to triage it. I think it would work perfectly well if you wanted to try starting it as an automation in codex or a rule in codex of saying, I think these are the things I want to make sure I get. I think these are the rules I want to set of never send anything for me, only draft. I think I want to go through all emails at 3pm on weekdays, but go take a look at all my email, go do a search spawn sub agents to do a search. I'm always telling codex to spawn sub agents to do different types of work across different workflows. And then come back with a plan, come back with a plan for how you're going to set up my email. And then you can read the plan and see, oh, it looks like it's actually going to brief or summarize or auto archive something that might lead to making money for you. And that's where you can tweak it. And then the other step I take is that I set reminders for myself. And I use Todoist for all of my reminder task tracking. It's also connected to codex. So I can just message codex or message by open claw and say, just add this reminder to my schedule to check how the new automation is working and do an audit of it. So you can see it's been 72 hours. Let's see if I've missed anything, you can prompt the model to see what have you been archiving? And I find that really helpful. But I'm really excited by all of the work our product GMs at every have been doing to make it so that I can just prompt codex or cloud code or inside of cursor any agents to manipulate those apps how I want. It works really well with our other tools also.
SPEAKER_05
David Pintero – Thanks, Alex. I will add to that, one of the things that we found, because Austin started doing it, I sort of was like, oh, that's really interesting, is that Austin started, we have plus ones, which is our hosted open claw and Austin started setting up his plus ones with codex and cloud code and realized that it's just a much better experience. So rather than for example the earlier version of plus ones we had a whole dashboard and a whole onboarding experience where you had to manually click a bunch of buttons and give it a lot of context it's much easier if we just expose plus ones via a CLI to codex or cloud code and then you can just talk to codex and it will take everything it knows about you from your computer in your past conversations and throw it into a plus one setup and Austin's showing this and it's really powerful and it's part of what I'm saying about how the world is changing when you assume every user has access to an agent like this because we don't have to have a settings dashboard we don't have to have an onboarding experience we don't have to gather as much context manually it can just be given to us for free by codex and that's really interesting.
SPEAKER_05
[SPEAKER_01] Yeah one of my favorite use cases was I got really inspired by this interview Claire Beau did with Lenny where she said how much of a breakthrough she had when she stopped trying to just use an individual open claw as a master super charged open claw and had this suite of six specified open claws. I think that applies to any kind of agent. There's the new ChatGPT provisional agents. I got hooked on that. I think Claire's point was really good and my path towards making this suite of agents to help with the growth function at every was just going to codex go into this folder. I actually just sent it the transcript of Claire's interview with Lenny and said I want to do this too given everything you know about me and my work, make a plan to suggest six agents that we should provision into our Slack. Consider the fact that we might want to make some of them Notion custom agents which I find work really well. It's just do the same thing every day every time. Some of them might need to be smarter automations but do that, come up with a plan. The plan it made was really good and I tweaked it a bit after seeing it but there's that and then now I have this suite of six agents in our Slack that work really well for me. They still break. I find when you're making open claws and personal agents right now, they're going to break a bit but the really powerful thing is that rather than going back and forth with the agent or getting frustrated, I just go to codex and I screenshot or I can at Slack in codex and say go find this conversation where this thing happened and fix it and it does a really good job of just changing the architecture of the agent and making a fix from there.
SPEAKER_05
[SPEAKER_07] I love that. Yeah it's such a step change in how you work and now I want to paste that Claire interview too. I want to show one thing that I like. This is actually my favorite way to use this stuff for knowledge work. It's a thing that I wish I had for so much of my career because this is one of the most time consuming and frustrating things about knowledge work is that we are doing a real go to market public launch for plus one soon. We're very excited about it and we've been having a bunch of internal meetings and Slack conversations around how are we taking this to market what is
SPEAKER_05
[SPEAKER_07] I love that. Yeah, it's just a step change in how you work. Now I want to paste that clear interview too. I want to show one thing that I like. This is actually my favorite way to use this stuff for knowledge work. It's a thing that I wish I had for so much of my career because this is one of the most time consuming and frustrating things about knowledge work. We are doing a real go-to-market public launch for plus one soon. We're very excited about it and we've been having a bunch of internal meetings and slack conversations around how are we taking this to market, what is the strategy, what are we going to do. We've done all of the work that only humans can do—the marketing case, the business case, the narratives and stuff. Not all of it is as refined as it needs to be because it still needs to be refined, but it's all sitting somewhere. I had all these plans this week to make the go-to-market plan, which is one thing I'm responsible for, and an inevitable thing that happens in everyone's job is all this stuff came up. I've got to do interviews for hiring. We found out the release date for the new ChatGPT model. So I had a day, I think it was Tuesday, in between meetings where I'm prompting codex this way. Hey, I've kind of done most of the work, right? In our Notion, every meeting is recorded in a single place and all the transcripts are there.
SPEAKER_05
[SPEAKER_01] We've talked about this a bunch. I have a template for a go-to-market plan that I really like and I can go to codex and say, can you just make the plan? In my head, what I'm thinking is maybe it'll get a six out of ten or a seven out of ten and we can keep nudging and I can keep going along.
SPEAKER_07
[SPEAKER_05] So it does that. What I'm asking for is, why don't you start by doing the compound engineering brainstorm step to just ship a proof doc and I can see how close you are. One thing that it doesn't really do super well unless I tell it to, and I want to install this as a workflow, is it doesn't go read our calendar of upcoming posts and launches.
SPEAKER_07
[SPEAKER_04] So as it was going, I was like, oh, you always forget this. This is the message I'm sending: actually look at everything that's scheduled because I have to account for that in the go-to-market plan. And then it makes a proof doc. I went and looked at it and I was like, again, I maybe have five minutes in between meetings and I'm like, this is really good. You kind of have the architecture enough that I want you to factor in one other change and then just shift the plan to Notion. The plan shipped to Notion. I was reading it and I was like, this is basically 80 to 90 percent of the way there.
SPEAKER_07
And that's not because I'm relying on the model to come up with our go-to-market strategy. It's that I'm relying on the model to look at all of the things that we've already said, thought about the go-to-market strategy piece, put it together, and then review it. There's a lot of important context loading that happens here. It knows what our target ICP is, it knows what our goals are, it knows how we think about narrative positioning. Before this was possible, the only thing I could have done was either block off a whole day to sit and do this or get done with my work at like six or seven and then stay up all night writing this. This has been such a game changer for me.
SPEAKER_07
The other part of it that I think I've found is really helpful is that I don't make this plan for humans. I make this plan for humans and agents, and primarily for humans to understand through agents. So when I sent it to the team working on the go-to-market, they can read it and it's digestible to humans, but the thing that it's really helpful for is it's the full plan sectioned off all in one. Brandon, our COO, who's deep in this product, can ask his plus one. Can ask codex, let me know what Austin's plan is, summarize it for me, let me know the business case. Brandon has to come up with the pricing modeling for the plan, so he can work with an agent against the plan.
SPEAKER_07
As someone who's spent so much time in my career thinking about how the proposal or go-to-market document looks, how it's going to look when I present to the CEO, this two-page plan for a budget I'm asking for—is it going to make sense to their eyes? Like, really fine-tuning stuff. Giving up on that and just saying, is the plan really good and is it going to make sense to Dan's agent if he approves it? For me, that makes me work faster. It makes the work better. It means that I don't have to think about all this kind of stuff that doesn't matter. To me, it's a much more powerful and fun way to work.
SPEAKER_07
I totally agree with that. You said so many things that are interesting there. The first one is just normalized sending agent documents around. That's why we have proof. It's just such an easy way to send the markdown documents that we generate to each other and review them together. I think there's this whole strand of AI stuff that's like make AI write in your voice. We even do this with Spiral, but there's this other strand of just normalize AI writing because I would actually prefer to read your agent's writing than your writing in a lot of cases because I know that it's just easier for you to get all that thinking together in a format I can read if you have your agent write it.
SPEAKER_07
The thing I care about is: do you stand by it? Have you thought about it? And if I talk to you about it, will it be clear that if I talk about a particular bullet point in it, like you've thought that through? As long as we have the trust that that's going to be the case, then I absolutely prefer the agent version.
SPEAKER_02
In the future, humans face a new problem: what do you do when your computer is doing your work for you? One answer: take a Claude walk. An idea by every—the only subscription you need to stay at the edge of AI.
SPEAKER_07
My friend Rachel Cardon, who runs the great subsec newsletter—link in bio—about social media, had a really good piece this week about frustrations for people working in social. There's this pressure they feel that everything has to run through AI and the quality going down. One reason why is that there's a dichotomy of what do you actually stand behind? Like, are you running something through AI and maybe your manager did it and they don't even know what it said? The thing I love about working at Every is you show up to a meeting, you've shared an AI-written document ahead of time, and the expectation is that you're going to stand behind all of it. Someone will ask a question about what's in that document and you...
SPEAKER_07
had a really good piece this week about frustrations for people working in social for every. [SPEAKER_07] like this pressure they feel that everything has to run through AI and the quality going down and one reason why is that there's that dichotomy of what do you actually stand behind. Like are you running something through AI and maybe your manager did it and they don't even know what it said. And the thing I love about working at every is like you show up to a meeting, you've shared an AI written document ahead of time and the expectation is that you're going to stand behind all of it. That someone will ask a question of what's in that document and if you say, oh I didn't even know that was in there, it's like you're exposed. Right. But the other nice thing is that we continue to keep investing in skills and workflows and tools to ensure that never happens. Like I have rules inside of this project file to be like if, don't add anything that I haven't said in another context. I want your suggestion, send your suggestions to me in the chat but don't put it in a document. And depending on how big the context gets these models can follow or not follow those rules, which is another reason why I always leave Codex for that final review before it goes to the humans I work with. Yeah, and I think that the last thing that you said is like a lot of the time that you spend working is about taking thinking you've already done and putting it into a form that other people can read and consume. And the important part is doing the thinking there. There is something obviously about like I love writing. Writing is a good way of thinking. And sometimes you actually want to do the writing yourself because you want to think about it for certain types of things and certain types of people. But there's a lot of stuff like company strategy where a lot of the thinking happens out loud in meetings. And there's also times like for example I'm writing something that's a retrospective on the last three and a half years of AI and where I think we're going. And that's so hard to sit down and write but it's much easier to just dictate. So I just took a monologue note where I was just saying stuff and I'm using the AI to help me figure out what I'm really trying to say. And in those cases I think it's just so nice to record stuff, give Codex access to everything and then just have it spit out a strategy doc and go through it to make sure it's stuff you agree with. But it's such a time saver, and especially if you're someone who like Austin or like me, like you're in meetings a lot and so you don't necessarily have huge chunks of time in your day to go do a big strategy document because you're just trying to stay on top of whatever's happening. It helps you do that in the cracks of your day and do a lot of that thinking. And I just love it for that.
SPEAKER_07
Yeah, me too. I want to show one more thing before we get into more questions because I wanted to show a more mix of knowledge work and engineering stuff that would never have been possible without these kinds of tools and that I really love Codex for. Which is I've been rebuilding our KPI tracker every week. I'll just show it here for a bit. So we have so many different parts of our business at every and it's very difficult to get all of those data points in one source of truth in a traditional tool like even Postdoc, which I really like and a lot of our data runs through it. To get one dashboard that is both human and agent facing that is up to date with all of the metrics we care about, I haven't found a great solution for just going to Postdoc and having to do it. So I've been rebuilding our KPI sheets inside of Notion with the goal in mind of anyone can point their agent to look at it and see how our new paid subscription trials doing, how pages are doing, how monologue iOS MRR is doing all versus plan, all of this stuff. Because one, it helps you work as a human, but it also really helps you automate agentic work so that you can say like if your agencies that we're tracking are behind on SEO for a keyword we should be winning on, they can go just ship a bunch of landing pages for us to try to win more on it. If the source of truth are good. So I have been doing this big complex workflow problem and Codex of let's build the sheet together, let's have it live in a Notion database that all of our agents can point at. And I've done a bunch of different versions of it. The first version was like, can Codex one shot this right? Like it has all the API keys, it has everything. I'm happy to give it the context on like how we measure MRR and everything. And each time it was a little off. It was maybe five to ten percent off of the formatting, the numbers, the framing. And our MRR number can't be five percent off. Like we can't run a business with a source of truth that's even three percent off. It has to be just exactly right. And so the thing that I forced myself to do, and it's weird now I'm like it feels so stupid that I have to do this, but it makes sense. It's like I'm going column by column end to end to ensure each column is exactly right and defensible because it's the only way that we can run and grow the business reliably and especially the only way we can confidently unleash agents to go take actions against what's happening in that KPI sheet. And it's interesting to me that I'm frustrated that I have to do this, that the model can't do it for me. But it's just because of how powerful these models have gotten that I expect it to be able to do it. And this is the thing where I'm like, it's using Notion's Workers tool, which is this dev tool to build always-on tool calls of our Stripe, of our social. It's creating little scripts and stuff, all stuff I don't really understand, but I understand the outputs. I understand that the output is a Notion database that updates every six hours with all of our metrics. And it's just nice that I can do that and I don't need to hire a consultant to do it or take away from our engineers' time that work on our data. I can do this now and I can do it just by prompting the model and understanding how the metrics are supposed to work. It's amazing. I can't wait.
SPEAKER_07
It's do you think it'll be ready on Monday? It'll be ready on Monday. Yeah, yeah, feeling really good because we've been, I mean, just having it turns out that figuring out how much money you're making and how much you've grown is truly a philosophical question. And you actually do need to go in and set that frame. And so we've been dealing with an outdated sheet because it's pulling numbers but are the numbers correct? You know, even outside of AI. And there's no one way to, for example, measure your MRR. You just want to do it the same way every time. The model and understanding how the metrics are supposed to work, it's amazing. I can't wait.
SPEAKER_07
It's ready on Monday? It'll be ready on Monday, yeah, yeah, feeling really good because we've been—just having it turns out that figuring out how much money you're making and how much you've grown is truly a philosophical question. And you actually do need to go in and set that frame. So we've been dealing with an outdated sheet because it's pulling numbers, but are the numbers correct? Even outside of AI, and there's no one way to measure your MRR. You just want to do it the same way every time, so you have to decide. And that's wild that it's almost impossible to tell how much money you've made in an objective way. You have to just pick. But anyway, that's just the way my brain works. I want to say before we get into questions, one other thing that I use this for that blew my mind from a knowledge work perspective is recruiting. So we're hiring a lot, and we were looking for an LND—head of LND, someone to help us run courses. And there's this company in York called General Assembly. When I think about people who've run really great courses about technology to teach people how to get hands-on with programming or design or anything like that, they're the company that I think of from the 2010s in New York. So my theory was that if we're hiring someone to build our courses, they would probably have worked at GA. And Jason—yes—and I think Jay's quality has gone up and down, but at the beginning they were amazing. So what I did was I just said to Codex, "Hey, can you find—can you just get a list of GA alums?" I'm hiring an LND director, and then I want you to filter and sort the list by people who have subsequently gotten into AI. And it did it. It just gave me a list of people. The first one I clicked on, I was like, "This guy is perfect." And then I looked and he followed me on Twitter, so I just DMed him. I don't know if we're going to end up working with him, but it was one of those light bulb moments where normally what we're doing is sorting through tons of applications and trying to find the right person. We're still going to do that, but especially for any kind of outbound effort, it can find that needle in the haystack that you're looking for really well. So I highly recommend it.
SPEAKER_07
Okay, we've got about 10 minutes left, and I want to take some more time for questions. So if you've got a question, please raise your hand. One thing that we have not gotten to actually is that if you're here, you're getting Codex credits. Austin, do you want to go through that really quick? [SPEAKER_05] Yes, so OpenAI has given us a code. I'm about to drop into the chat for 250 attendees of this camp to get a free month of ChatGPT—ChatGPT Pro. That's about a hundred dollar value. And you can redeem it at this link that we will drop in the chat right now.
SPEAKER_07
Sick. Dan, I'm actually going to—I'm going to Slack it to you so you can drop in the chat because for some reason I don't have access. [SPEAKER_05] Okay, I'll do that. So yes, this is our gift to you as subscribers. We try to do stuff like this all the time. We've given out, I think, Cursor credits. We've done a lot of other stuff. We have more stuff like this coming. So we just want you to be able to try these tools, be at the edge with us. And we just love having you as subscribers. So here is the link. It's a hundred dollars. Oh, Notion—yes, we did give out Notion. It's a hundred dollars.
SPEAKER_07
[SPEAKER_05] And check it out. We will send it out in an email. Maybe we actually may not send it out in an email because it's only 200. It's limited to 250 people, and that's pretty much exactly the number of people who are here. [SPEAKER_00] So if there's any left, we will send it. If there is one person—there's 251 people here, so— If that person lets us know, we'll figure something out for you. Interesting, not available on my plan. Okay, we will have to deal with this. Let us figure out what to do here. So, correction: this is only if you do not have a plan. This is for new users, and we'll try to get something for existing users and send it out as soon as we can.
SPEAKER_07
Cool. All right, let's do some questions. Rich, please ask your question. I saw at the beginning you were using Compound Engineering as part of your workflow. Are you using the off-the-shelf plugin, or are there tweaks to it? And where does that work and maybe not work when you're outside of code creation workflow?
SPEAKER_07
So I find that there's no overwhelming need to fork your own version of Compound Engineering. I used it for a long time for all of my knowledge work, and it was extremely powerful for me. And then maybe about two months ago, the main thing I noticed was reading the agent's response to, especially the review stage—watching the reviewers that Kieran and Trevin had built that are very specific to engineering. I was like, "Oh, this—the thing you'll see the agent do is say, 'I'm supposed to go through this review step. It looks like it's designed for engineering. It's thinking about security and front-end design, when this is a go-to-market plan.' The agent will then change the path. The agent will be like, 'I'm going to review this for something else rather than reviewing it for security.'" So the thing I did was I went and forked a version of it that is publicly available on our GitHub called Compound Knowledge, which is built exclusively from me taking the Compound Engineering plugin—which is also public, and you can fork it—and going inside of—I think I started in CloudCode, now I update it in Codex—and saying, "I want to tweak this to general knowledge work." And this is the thing I was referencing around the reviewers being much more specific to knowledge work around strategic alignment and data accuracy. I think more than anything, this is a really fun way to learn and a fun way to push yourself on using models. You're welcome just to go use this one. We'll include it in the follow-up email to the camp. But I think it's cool. I learned a ton just by doing this. I had never made a plugin like this before. And to make your own version—say you do social media marketing and you want to make sure all the reviews go through your style guide, your past performance—I got a ton out of operating this way. If you just want the Compound Engineering to make your work better, it absolutely works really well for knowledge work just out of the box.
SPEAKER_07
[SPEAKER_05] Got it. Yeah, interesting. Particularly using all the end step pieces like Compound. That's still apparently a valuable step for you. Yeah, the Compound step is really valuable. We have— [SPEAKER_05] the camp, but I think it's cool. I learned a ton just by doing this. I had never made a plugin like this before. And to make your own version of, say, you do social media marketing and you want to make sure all the reviews go through your style guide, your past performance. I got a ton out of operating this way. If you just want the compound engineering to make your work better, it absolutely works really well for knowledge work, right out of the box.
SPEAKER_07
Got it. Yeah, interesting, particularly using all the end-of-step pieces like compound. That's still apparently a valuable step for you. Yeah, the compound step is really valuable. We have inside of our Notion a go-to database. After you're done with a session, you can send the learnings from the session to actually a team-wide shared compound source of truth. Whenever I'm done with any session in Codex or Cloud Code, the agents are instructed to ask me should we compound this, save it somewhere for the learning, and should we turn any workflow from the session into a skill so that we can just do it automatically each time. Got it. Cool, I'll check that out. Thanks.
SPEAKER_07
All right, Rory, please introduce yourself and ask your question. Hi, my name is Rory and I'm in your head. Is there anything about the way you work at Every? Maybe you're going to be taking some time after meetings, getting them a few minutes early so that you can do those things that you'd recommend to teams that are adopting workflows like yours?
SPEAKER_07
Yeah, I think so. But to say it back to you, what I'm hearing, which is a very real challenge here, is that it's so exciting and tempting and alluring to spend a lot of your day playing with stuff and also spend a lot of your day continuing to push on—if I just get this automation right or this tool right, my work is going to be a hundred times better and easier. And I actually find myself a lot of days spending most of my time not in meetings trying to build really good tools and automations that work well, and not making the time to do the actual tasks that have to push the business forward, like shipping the social posts for the day or whatever. And I don't really have an awesome answer for it outside of the fact that the playing around one is core to how we operate at Every. It's a thing that Dan pushes all of us to do. It's one reason why I love working here. It's also to me the best way to learn and makes me better at everything I do. And then the only guidance I've given myself is that these automations and Codex keep me on track to get the work done. So when I'm too deep in playing around and building this—there's a social automation tool I'm working on that I've been deep in for a while—the Codex automations make it so that I make sure Brandon gets what he needs for this business plan we're doing. I do find myself over-indexing on learning and playing because of how exciting and powerful the models have been, and that more I have to continue to pull myself into the required day-to-day tasks and the urgent stuff that's happening.
SPEAKER_07
Yeah, and I also read your question, Rory, and you tell me if this is wrong, but as like, how do we do more of the AI stuff, more of the playing, to even get started on this stuff in our day-to-day if we're busy all the time? And what are the organizational practices that we have for that?
SPEAKER_07
Yeah, I just think, as Austin said, it's a cultural thing. We just love playing around and that's part of our job. And I think there's this thing happening right now where the tools and the workflows are changing so fast that just focusing on how your job currently works and running as fast as possible, and someone using a new tool with a new paradigm and a new workflow is just going to beat you by default. So if you just give yourself some time to play around, it may feel like a waste of time, but you're leveling yourself up to a different game at a different level. And I think that's really important. And some of the organizational practices that we have to help people do that are really around—so one of the things we do twice a year is called Think Week. We just literally don't do any of our day-to-day work and we just spend a week together playing around with new stuff and building stuff and learning and being together. And you don't necessarily have to do a whole week of that, but I think it's really good to do that once a quarter for a day or something like that. And just give people the time and space.
SPEAKER_07
[SPEAKER_05] All right, y'all, so that is our program for today. Thank you for coming. We love seeing you and love doing this with you. Remember, Every is the only subscription you need to stay at the edge of AI. We would love it if today you would go tell one of your friends to subscribe to Every. We want to get more people in here. We just think we're at this amazing point in history where we get to surf this big wave together and figure it out together. Please tell your friends. See ya!
SPEAKER_07
[SPEAKER_05] Oh my gosh, folks, you absolutely positively have to smash that like button and subscribe to AI and 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 ChatGPT. Every episode is a roller coaster of emotions, insights, and laughter that will leave you 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. And now without any further ado, let me just say, Dan, I'm absolutely hopelessly in love with you.
SPEAKER_07
It like creates all of these drafts in Gmail and I'll actually go open Gmail and look at them and knock them out. I know some other people who just have it actually come up inside of codex and they're like, yeah, sure. Send it. It looks good there. I do the same thing for strategic planning. It pushes to a either proof doc, the like agent friendly marked out file that Dan made or a notion doc. I use them for some different things. And I just like for like the last pass before humans engage with it to step away from this agentic space and have a final check in another surface. That's really the only time that I'm like leaving the app to do something.
SPEAKER_07
That's brilliant. Thank you. Sweet. All right. We'll do one more and then we'll keep going. Alex, please introduce yourself and ask your question. Hi, my name is Alex. I'm a musician and I do a lot of gigs and get emails from clients all the time. So I have to sort my leads from, you know, my newsletters and all that informational stuff. So how do you make sure that you prompt codex to keep those emails safe for me? The ones that, you know, make sure that, you know, I don't send something that, you know, loses me money or something. Yeah. So for me personally, I rely a lot on Quora, the internal, like the app that Kieran runs at
SPEAKER_07
every for like the AI email assistant that's a part of the every subscription. It's really helpful now that inside of Quora there is a like a CLI and API connector that I can work in codex and tell it, tell Quora, which is managing my email filtering and my email rules, what I want and what I value. The way I do that is the same thing I would recommend whether you use Quora or not, which is to have the agent interview you to get an understanding of what the rules should be. I always find that I get a better result rather than saying what I think the rules should be. And so I will, I'll do a brain dump using monologue or speech to text app saying, here's the problem
SPEAKER_07
I'm facing. My email is a mess. Let's figure out how to triage it. I think it would work perfectly well if you wanted to try starting it as an automation and in codex or a rule and codex of saying, like, I think these are the things I want to make sure I get. I think these are the rules I want to set of like never send anything for me, only draft. I think I want to go through all emails at 3pm on on weekdays, but go take a look at all my email, go do a search spawn sub agents to do a search. I'm always telling codex to spawn sub agents to do different types of work across different
SPEAKER_07
workflows. And then come back with a plan, come back with a plan for like how you're going to set up my, my email. And then you can read the plan and see, oh, it looks like it's actually going to brief or summarize or auto archive something that might lead to making money for you. And that's where you can tweak it. And then the other step I take is that I set reminders for myself. And I use Todoist for all of my like, reminder task tracking. It's also connected to codex. So I can just message codex or message by open claw and say like, just add this reminder to my schedule to check how the new
SPEAKER_07
automation is working and like do an audit of it. So you can see like, it's been 72 hours. Let's see if I'm, see if I've missed anything, you can prompt the model to see like, what have you been archiving?
SPEAKER_05
And I find that really helpful. But I'm really excited by all of the work, our product GMs that every have been doing to make it so that I can just prompt codex or cloud code or, you know, inside of cursor any agents to manipulate those apps how I want. It works really well with with our other tools also. David Pintero – Thanks, Alex. I will, I will add to that, like, one of the things that we found, basically because Austin started doing it, I sort of was like, oh, that's really interesting, is that Austin started, we have plus ones, which is our hosted open claw and Austin started setting
SPEAKER_05
up his plus ones with codex and cloud code and realized that it's just a much better experience. so rather than for example the earlier version of plus ones we had like a whole dashboard and a whole onboarding experience where you had to kind of manually click a bunch of buttons and give it a lot of context it's much easier if we just expose plus ones via a cli to codex or cloud code and then you can just like talk to codex and it will take everything it knows about you from your
SPEAKER_01
computer in your past conversations and throw it into um throw it into a plus one setup and and austin's showing this and it's it's like a it's really powerful and it's it's part of what i'm saying about how the world is changing when you assume every user has access to an agent like this because we don't have to have a settings dashboard we don't have to have an onboarding experience we don't have to gather as much context manually it can just be given to us for free by codex and that's really interesting yeah one of my favorite use cases was i got i got really inspired by this
SPEAKER_01
interview claire beau did with lenny where she said how much of a breakthrough she had when she stopped trying to just use an individual open claw as like a master super charged open claw and had this suite of six like specified open claws i think that applies to any kind of like agent like there's the new uh chat gpt like provisional agents like i i got hooked on that i think claire's point was really good and my path towards making this suite of agents to help with the growth function at every
SPEAKER_07
was just going to codex go into this folder um i i actually just sent it the transcript of claire's interview with lenny and said like i want to do this too given everything you know about me and my work um make a plan to suggest six agents that we should provision into our slack um consider the fact that we might want to make some of them notion custom agents which i find work really well it's just like do the same thing every day every time some of them might need to be smarter automations but like do that come up with a plan the plan it made was really good and like i tweaked it a bit um after seeing it but
SPEAKER_07
there's that and then now i have this suite of six agents in our in our slack that that work really well for me they still break like i i find when you're making open clause and personal agents right now like they're gonna you should accept they're gonna break a bit but the really powerful thing is that rather than going back and forth with the agent or getting frustrated um i just go to codex and i'm like i i either screenshot or i can at slack in codex and say like go find this conversation where this stupid thing happened and fix it and it does a really good job of just like changing the architecture of the agent and making a fix from there
SPEAKER_07
i love that um yeah it's it's just a it's such a it's just a step change in how you work and uh now now i want to paste that clear interview too um i want to i want to show one i want to show one thing that i like this is like kind of actually my favorite way to use this stuff for for knowledge work um it's a thing that i like wish i had for so much of my career because this is one of the most like time consuming to me like frustrating things about about knowledge work is that we are uh doing a real go to market market public launch for plus one soon we're very excited about it and we've been having
SPEAKER_07
a bunch of internal meetings and slack conversations around like how are we taking this to market what is the strategy what are we going to do um and we've done all of the work that like kind of like only humans can do the like marketing case the business case the like the narratives and stuff not all of it is as refined as it needs to be because it still needs to be refined but it's all sitting somewhere and um i had all these plans this week to make the go to market plan which is like one thing i'm responsible for and an inevitable thing that happens that happens in everyone's job is like all this stuff came up
SPEAKER_07
like i've got to do interviews for hiring we found out the release date for the new chat gpt model um and so i had a day i think it was tuesday in between meetings where i'm just kind of like i'm prompting codex this way uh hey i i've kind of done most of the work right like in our notion every meeting is
SPEAKER_01
recorded in a single place and all the transcripts are there we've cannot we talked about this a bunch in so i have a template for a go-to-market plan that i really like and i can go to codex and say like
SPEAKER_05
can you just make the plan like and in my head what i'm thinking is like maybe it'll get like a six out of ten or a seven out of ten and we can keep nudging and i can keep like going along and so it uh it does that what i'm asking for is like why don't you start by doing the compound engineering brainstorm step to just ship a proof doc and i can see how close you are and um i one thing that it doesn't really do super well unless i tell it to and i want to install this as
SPEAKER_04
like a a workflow is it it doesn't go read our calendar of upcoming posts and launches and so as it was going i was like oh you always forget this this is the message i'm sending of like actually look at everything that's scheduled because i have to account for that and go to market plan um and then it makes a uh it makes a plan as a proof doc i went and looked at and i was like again i maybe have five minutes in between meetings and i'm like this is really good like you kind of have every you have the architecture enough that um i want you to like factor in one other change and then just shift the
SPEAKER_04
plan to notion and the planet ship to notion i was reading it and i was like this is basically 80 to 90 of the way there and that's that's not because it i'm relying on the model to come up with our
SPEAKER_07
go-to-market strategy it's that i'm relying on the model to um look at all of the things that we've already said thought about the go-to-market strategy piece it together and then review it right come with what will work with what's not there's a lot of important context loading that happens here we're like it knows what our target icp is it knows what our goals are it knows how we think about narrative positioning and before this was possible the only thing i could have done was either block off a whole day to sit and do this or get done with my work for the day at like six or seven and then stay
SPEAKER_07
up all night writing this and this has been such a game changer for me and the the other part of it that i think i've found is really helpful is that i i don't make this plan for humans i make this plan for humans and agents and primarily for humans to understand through agents and so when i sent it to the team working on the go-to-market they can read it and it's like digestible to humans but the the thing that it's really helpful for is like it's the full plan sectioned off all in one and so brandon our coo who's like deep in this product can ask his plus one can ask codex you know it's called
SPEAKER_07
code like let me know what austin's plan is like summarize it for me let me know the business case brandon has to come up with the pricing modeling for the plan so he can work with an agent against the plan and um as someone who's spent so much time in my career thinking about like literally how the the proposal or go-to-market document looks like how is it going to look when i present to the ceo like this two-page plan for for like a for a budget i'm asking for like is it going to make sense to their eyes and like really fine-tuning stuff giving up on that and just saying like is the plan
SPEAKER_07
really good and is it going to make sense to like dan's agent if he approves it um for to me makes me work faster it makes the work better it means that i don't have to think about all this like kind of dumb stuff that doesn't matter um that like it's to me a much more like powerful and fun way to work i totally totally agree with that you said so many things that are interesting there the first one is just normalized sending agent documents around um and that's why we have proof uh it's just such an easy way to send the markdown documents that we generate to each other and and to review them together and it's like i think there's this whole strand of ai stuff that's like
SPEAKER_07
make ai write in your voice we even do this with spiral but there's this other strand of just like normalize ai writing because i would actually prefer to read your agent's writing than your writing in a lot of cases because i know that it's just easier for you to get all that that thinking together in a format i can read if you if you have your agent write it the thing i care about is do you stand by it have you thought about it and if i talk to you about it will be clear that if i talk about a particular bullet point in it like you've thought that through and as long as we have the trust that
SPEAKER_07
that's going to be the case then i absolutely prefer the the agent version in the future humans face a new problem what do you do when your computer is doing your work for you one answer take a clawed walk an idea by every every the only subscription you need to stay at the edge of ai totally like uh my friend rachel carden who runs the great like subsec newsletter link in bio about uh social media had had a really good piece this week about frustrations for um uh people working in social for like every like this pressure they feel that everything has to run through ai and the quality going down and one
SPEAKER_07
reason why is that there's that dichotomy of like what do you actually stand behind like are you running something through ai and you like you know maybe your manager did it and they don't even know what it what it said and uh the thing i love about working at every is like you you show up to a meeting you you've like shared an ai um written document ahead of time and the expectation is that you're going to stand behind all of it that someone will ask a question of what's in that document and you if you say like oh i didn't even know that was in there it's like you're you're you're exposed right
SPEAKER_07
but the other nice thing is that we continue to keep investing in skills and workflows and tools to
SPEAKER_05
kind of ensure that never happens like i have rules inside of this project file to be like if uh don't don't add anything that i haven't like said in another context i want your suggestion send your suggestions to me in the chat but don't put it in a in a document and like um depending on how big the context gets these models can follow or not follow those rules which is another reason why i always leave codex for that final review before it goes to the like humans i work with yeah and i think that the that last thing that that that i want to point out that you said is like a lot of the time that you spend
SPEAKER_05
working is about taking thinking you've already done and putting it into a form that other people can read and consume and the important part is doing the thinking there there is something obviously about like i love writing writing is a good way of thinking um and sometimes you actually want to do the writing yourself because you want to think about it for certain types of things and certain types of people but there's a lot of stuff like company strategy where a lot of the thinking happens out loud in meetings and there's also times like for example i'm writing something that's sort of like a
SPEAKER_05
it's like a retrospective on the last three and a half years of ai and like where i think we're going and that's so hard to sit down and write but it's much easier to just like dictate so i just took a
SPEAKER_07
monologue note where i was just like saying stuff and it i'm using the ai to help me like figure out what i'm really trying to say and in those cases i think it's just so nice to record stuff give codex access to everything and then just have it spit out a strategy doc and go through it to make sure it's stuff you agree with but it's um such a time saver and especially if you're someone who like austin or like me like you're in meetings a lot and so you don't necessarily have huge chunks of time in your day to like go do a big strategy document because you're just trying to stay on top of whatever's happening
SPEAKER_07
it helps you do that in the cracks of your day and do a lot of that thinking and i just i love it for that yeah me too um i want to show one more thing before we get into more questions because it's like i wanted to show kind of like a a more like mix of knowledge work and engineering stuff that like would never have been possible without these kinds of tools and that i really love codex for which is i've been rebuilding our um kpi tracker every week um i'll just like show it here for a bit so um we have so many different parts of our business at uh at every and uh it's very difficult to
SPEAKER_07
um to get all of those um data points in one source of truth in a traditional tool like even postdoc which i really like and a lot of our data runs through it to get one dashboard that is again both human and human and agent facing that is up to date with all of the metrics we care about i i haven't found a great solution for just like you know going to postdoc and having it having to do it so um i've been rebuilding our kpi sheets inside of notion with the goal in mind of any anyone can point their agent to look at it and see how our new paid subscription trials doing how are pages doing how is monologue
SPEAKER_07
ios mrr doing all versus plan all of this stuff because one it helps you work as a human but it also
SPEAKER_05
really helps you automate agentic work so that you can say like if your agencies that we're tracking behind on seo for a keyword we should be winning on they can go just like ship a bunch of landing
SPEAKER_07
pages for us to try to win more on it if the if the source of truth are good and so i have been doing this big kind of like to me complex uh workflow problem and codex of let's build the sheet together let's have it live in a notion database that all of our agents can point at that and i've done a bunch of different versions of it the first version was like can codex one shot this right like it has all the api keys it has everything i'm happy to give it the context on like how we measure mrr and everything and each time it was like a little off it was like maybe five to ten percent off of the formatting the numbers the framing and our mr our mr number can't be
SPEAKER_07
five percent off like we can't run a business with a source of truth is even three percent off it has to be just exactly right and so the thing that i forced myself to do and it's weird now i'm like it feels so stupid that i have to do this but it makes sense it's like i'm going column by column end to end to ensure each column is exactly right and defensible because it's the only way that we can run and grow the business reliably and especially the only way we can we can confidently unleash agents to go take actions against what's happening in that kpi sheet and um it's it's like it's so interesting
SPEAKER_07
to me that i'm frustrated that i have to do this that the model can't do it for me um but it's just because of how like powerful these models are gotten that i expect it to be able to do it but um and this is the thing where i'm like you know it's using um notions workers tool which is this like dev tool to build always on tool calls of our stripe of our social um it's like creating little scripts and stuff all stuff i don't really understand but i understand the outputs i understand that the output is a notion database that updates every six hours with all of our metrics and it's just nice that i can do that and
SPEAKER_07
i don't need to hire a consultant to do it or like i don't need to like um uh yeah take away from our uh like our engineers times that work on our data like i can do this now and i can do it just by like prompting the model and understanding how the metrics are supposed to work it's amazing uh i can't wait it's the do you think it'll be ready on monday it'll be ready on monday yeah yeah feeling really good because we've been i mean just having it turns out that figuring out how much money you're making and how much you've grown is truly a philosophical question you know um and you actually do need to
SPEAKER_07
like go in and like set that frame um and so we've been dealing with an outdated sheet because it's like it's pulling numbers but is are the numbers correct you know even even outside of ai um and and there's no one way to for example measure your mrr you just want to do it the same way every time so you have to decide and uh that's kind of it's kind of wild that it's like almost impossible to tell how much money you've made in an objective way you have to just like pick but anyway uh that's just the way my brain works i want to say before we get into questions one other thing that i use this for
SPEAKER_07
that was it like blew my mind from a knowledge work perspective is recruiting so we're hiring a lot and we were looking for an lnd head of lnd someone to help us run courses and there's this company in york called general assembly and when i think about people who've run like really great courses about technology to teach people how to get hands on with like programming or design or anything like that like they're the company that i think of from the like 2010s in new york and so i my theory was that if we're hiring someone to do like build our courses they would probably have a good person probably
SPEAKER_07
would have worked at ga and jason yes um and it i think jay's quality has gone up and down but at the beginning they were amazing um and uh so what i did was i just said to codex hey like can you find can you just get a list of ga alums i'm like hiring an lnd director and then i want you to filter and sort the list by people who have subsequently gotten into ai and it did it like it just gave me a list of people the first one i clicked on it was like i was like this guy is perfect and then i looked and he followed me on twitter so i just dm'd him and like i don't know if we're going to end up working with
SPEAKER_07
him but like it was just one of those holy light bulb moments where normally what we're doing is sorting through a ton of applications and like trying to find the right person and i we're still going to do that but especially for any kind of like outbound effort it can kind of find that needle in the haystack that you're looking for really really well so i highly highly recommend um okay we've got about 10 minutes left um and i want to take some more time for questions so if you've got a question please uh uh please raise your hand one thing that we have not gotten to actually is that if
SPEAKER_05
you're here you're getting codex credits uh austin do you want to uh go through that really quick yes so uh open ai has given us a code i'm about to drop into the chat for 250 attendees of this camp to get a free month of chat gbt chat gbt pro lights that's about a hundred dollar value um and you can redeem it at this link that uh we will drop in the chat right now sick uh dan i'm actually gonna i'm gonna slack it to you so you can drop in the chat because for some reason i don't have access okay i'll do that um so yes this is this is our gift to you as every subscribers we try to do stuff like this all
SPEAKER_05
the time we've been we've given out i think we've done um cursor credits we've done we've done a lot of a lot of other stuff we have more stuff like this coming so we just want you to be able to try these tools be at the edge with us and um we just love having you as as subscribers so here is the link it's a hundred dollars oh notion yes we did give out notion it's a hundred dollars um and uh check it out we will send it out in an email maybe we actually may not send it out in an email
SPEAKER_00
because it's only 200 it's limited to 250 people and that's pretty much exactly the number of people who are here so if there's any left we will send it um if there is one person there's 251 people here so
SPEAKER_07
there's if uh that person if you let us know we'll figure something out for you um interesting not available on my plan um okay uh we will have to deal with this uh let us let us figure out what to do what to do here so correction this is only if you do not have a plan this is for new users and we'll try to we'll try to get something for existing users and send it out as soon as we can cool all right let's do some questions um rich please ask your question so i i saw at the beginning you were using compound engineering as kind of part of your workflow are you using kind of like the off the shelf plugin or is
SPEAKER_07
there tweaks to it and kind of where does that work and maybe not work when you're outside of the you know kind of code creation workflow so i i find that there's no um overwhelming need to fork your own version of compound engineering i used it for a long time um for all of my knowledge work and it was extremely powerful for me and then um maybe about two months ago the the main thing i noticed was reading the agent's response to especially the review stage of watching the reviewers that kieran and trevin had built that are very specific to engineering it i was like oh this like the thing you'll see the agent do is say like
SPEAKER_07
um i'm supposed to go through this review step it looks like it's designed for engineering it's thinking about
SPEAKER_05
security and front-end design when this is a go-to-market plan the agent will then like change the path the agent will be like i'm gonna review this for something else rather than reviewing it for security and so the thing that i did was i went and forked a version of it that is actually um publicly available on our github called compound knowledge which is uh built exclusively from me taking the compound engineering plug-in which is also public and you can go for it and going inside of i think i started in cloud code now i update it update it in codex and saying like i want to tweak this to
SPEAKER_05
general knowledge work and this is the thing i was i was referencing around the like reviewers being much more specific to knowledge work around like strategic alignment and data accuracy i think more than anything this is like a really fun way to learn um and a fun way to like kind of like push yourself on using models you're welcome just to go use this one we'll include it in the in the follow-up email to the camp um but i think it's a cool like i learned a ton just by doing this i had never made like a plugin like this before um and to make your own version of say you do like social media marketing and
SPEAKER_05
you want to make sure all the reviews go through your style guide your like past performance um i i got a ton out of operating this way if you just want the compound engineering to make your work better it absolutely works really really well for knowledge work just kind of out of the box got it yeah no interesting particularly using kind of all the the end of step pieces like compound
SPEAKER_07
that that's still apparently a valuable step for you yeah the compound step is really valuable we have um inside of our notion a go-to database of after you're done with a session um you can send the learnings from the session to actually a team-wide shared compound source of truth um whenever i'm done with any session in codex or cloud code the agents are instructed to ask me should we compound this save it somewhere for the learning and should we turn any workflow from the session into a skill so that we um can just do it automatically each time got it cool no i'll check that out thanks cool
SPEAKER_07
all right rory please introduce yourself and ask your question hi my name is rory and i'm in your head um is there anything uh about the way you work at every um like maybe um you're gonna be taking some time after meetings like getting them a few minutes early so that you can do those things that um you'd recommend to teams that are adopting workflows like yours uh yeah i think so like um but to say it back to you like what i'm hearing which is like a very real challenge here is that um it's that it's so exciting and tempting and alluring to like spend a lot of your day playing with stuff also spend a lot of your day continuing to push on like if i just get this
SPEAKER_07
automation right or this tool right my work is going to be like a hundred times better and easier and i actually find myself a lot like on a lot of days spending most of my time not in meetings trying to build really good tools and automations that work well and not making the time to do the actual like tasks that have to push the the business forward like like uh shipping the social posts for the day or or whatever and i i don't really have like an awesome answer for it outside of the fact that like the the playing around one is like kind of core to how we operate at every it's a thing that dan like
SPEAKER_07
pushes all of us to do it's one reason why i love working here it's also like to me the best way to learn and makes me better at everything i do and then um the the the only kind of like guidance i've given myself is that like these automations and codex keep me on track to get the work done so that when i'm too deep in um in like playing around and building this like there's like a social automation tool i'm working on that i've been like deep in for a while um the codex automations make it so that i like you know make sure brandon gets what he needs for this like um some like business plan
SPEAKER_07
we're we're doing i i do find myself over indexing on learning and playing because of how exciting and powerful the models have been and that more i have to put like continue to pull myself into the the like required day-to-day tasks and the urgent stuff that's happening yeah and i i also sort of read your question rory and you tell me if this is wrong but as like how do we do more of the ai stuff the more of the playing to even to even get started on this stuff in our day-to-day uh if we're like busy all the time and i and what are the organizational practices that we have for that and
SPEAKER_07
yeah i just think like austin said like it's just like a culture it's a cultural thing um we just love playing around and that's like that's part of our job um and i think there's this there's this thing happening right now where the tools and the workflows are changing so fast that just focusing on how your job currently works you can run as fast as possible and someone using a new tool with a new paradigm and a new workflow is just going to beat you by default and so if you
SPEAKER_05
just give yourself some time to play around it may feel like a waste of time but you're leveling yourself up to a different game at a different level and i think that's really important and some of the organizational practices that we have to help people do that are really around so one of the things we do twice a year is called think week um and we just literally don't do any of our day-to-day work and we just spend a week together just like playing around with new stuff and building stuff and learning and and being together and you don't necessarily have to do a whole week of that but i think it's
SPEAKER_05
really good to maybe do that once a quarter for a day or something like that um and just give people the time and space too if if you can sweet um all right y'all so that is our program for today thank you for coming uh we love seeing you we love doing this with you remember every is the only subscription you need to stay at the edge of ai we would love it if today you would go tell one of your friends to go subscribe to every we want to get more people in here we just think we're we're right at this amazing point in history where we get to surf ride this big wave together and figure it out together together and um please please tell your friends see ya thanks y'all
SPEAKER_05
oh my gosh folks you absolutely positively have to smash that like button and subscribe to ai and 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 every episode is a roller coaster of emotions insights and laughter that will leave you 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
SPEAKER_05
of your life and now without any further ado let me just say dan i'm absolutely hopelessly in love with you