Claude Code + Codex Can FINALLY Work Together (Buzz AI) Transcript, AI Summary & Key Points

00:00 Today, we're talking about Buzz, a new free version of Slack that allows you to create teams of AI agents that work with your existing AI agent subscriptions like Codex and Claude Code. It was created by Jack Dorsey, the founder of Twitter, and it's free and open source. And I've been using Buzz to allow all these different agents to collaborate as a team on different tasks that are critical to my business, and I'm blown away by how well this actually works.

00:28 And by the end of this conversation, you'll be able to create a team of AI agents that collaborate to do your work. You'll also be able to connect your existing Claude Code and Codex accounts, and you'll understand how to use the main features of Buzz like creating new agents with specific models, how to create custom workflows, and how to use the iOS app that lets you control your team of agents from your phone.

00:48 So, this video is going to be all about Buzz. And as you can see here, I can type a message and send it to Claude Code, Grok running on Cursor, Kimmy running on Kevin, and Codex at the same time. You can see all of them read it, and all of them are now making a response. And now Grok responds first because it's a really fast model. Codex responded. And there's Kimmy.

01:15 And as you can see here, all of my agents responded inside Buzz. And so, this video that you're about to watch is divided into two parts. In part one, we're going to talk with Vinnie, an expert on Buzz. He made this video that went super viral on X, and we're going to talk about a bunch of different things why it's going viral, connecting all of your existing tools.

01:31 We're also going to talk about the mobile app and some other advanced topics. And we're also going to talk about automations, workflows, and agent reliability. And after this conversation, at the end, it might be 10 to 15 minutes, I'm going to talk about my workflow. I'm going to talk about exactly how to set up these AI agents inside Buzz. I'm going to show you my Buzz setup, and I'm just going to riff and talk about basically how I've been using Buzz and why I think it's so cool.

01:58 Let's hop into Buzz. Vinnie, super excited to have you on today. Um yeah, so this is Buzz and your video, I think it got over a million views, right? >> Yeah, pretty crazy. >> Yeah, pretty crazy. Why is this platform going so viral? What is it and what makes it so interesting to people, do you think? >> Well, I think first of all, people are very interested in seeing something that could replace Slack.

02:24 People want to replace Slack, but that is like a very superficial reason. There's two things. There's you have this thing of context. Like Buzz is a giant context harvester and and a place where like all your context lives and and can be shared between your teammates and your agents and your agents just kind of function as teammates. And in a nutshell, it's the openness, the ability to swap out models and have all this context in one central place so you don't have to go between a million different tools.

02:53 >> Great explanation. I want to just make sure that I fully understand and I want to make sure the audience understands what this actually means. Buzz is basically a clone or a somewhat of a clone of Slack. And when you first sign in and it's completely free, you can either choose to create an organization or a team and then you can add your agents.

03:15 And the coolest part about this is not only is it free, but you add your existing Claude code and your existing Codex setup. And my a lot of my audience uses Codex. A lot of my audience uses Claude code. And when you use those agents or or those tools, you have skills that you've already created. What's cool about Buzz is as you can see here, I said to Codex, if I zoom in here real quick, I said, "Take the lead on a new educational page for Buzz.

03:42 This should be a landing page that is deployed to Vercel." And then I said, "Consult with Claude code first." And so basically, Codex said, "I'm taking the lead on it." And then it asked a few questions to Claude Code. Claude Code reviewed its idea, came up with a bunch of ideas, and because Codex has access to my notion, my notion has notes for this episode of what I think is interesting about Buzz, and then eventually it deployed this link to Vercel.

04:10 I've never opened this up. So I'm going to go ahead and open this up, and this is what it created. This is just a demo for something that like I wanted to show something tangible here. This is kind of cool. >> Wow. >> created this based on some information that I already have. One thing I want to make clear for the audience here is when I add Codex, it literally shows up in the Codex or the the chat GPT app.

04:30 You could see here that the sessions that I have, like when I message Codex through Buzz, it shows up here in the recent chats. And so it basically Can Can you help me explain this a little bit? Like I'm I'm trying to wrap my head around this. >> It uses something under the hood called um agent client or agent connect protocol. I'm not sure exactly what the acronym stands for, but it's a an an open way for them to communicate with the different harnesses.

04:58 So it's basically just running your, you know, it's it's communicating All these are CLI tools, so they're running in the terminal, and you are connecting to them, and you're running the Codex commands in the terminal, and that's why it'll show up here. >> So it like injects all of the context that Codex might need in order to like create a good response, and then that that's what shows up in Buzz.

05:19 And they're able to collaborate. >> how much historical context it has, but that's like the great thing like I was talking about earlier. You just If you have an agent, for example, you made Harry your agent, and Harry is a has a system prompt to do, I don't know, copy editing and marketing stuff. Now you you don't really like Claude Opus for that, and you just go into the preferences, and you switch it to Codex, and you like Soul for that, it works better you think.

05:46 It's going to have all that context that Claude Code had and Opus, and it'll just automatically transfer over and and pass that context over to Codex. That's the really cool part is that having the chat sessions in here, doesn't matter how often you switch, which models you choose, which harnesses you choose, the context will always get passed over to those those new harnesses.

06:07 >> Yeah, makes sense. And yeah, you're right. I did kind of take a straightforward naming approach. I do have an agent called management, and it is also powered by Codex. But I do just kind of have like a Codex and Claude Code agent that I like to have, which kind of has no underlying system prompt. But correct me if I'm wrong here, an agent that you create, and let's say I created a new agent powered by Codex, it's basically just Codex with a with an added system prompt to it.

06:32 Is that basically it? >> Yeah, that's that's what I get. I mean, obviously this is a layer on top of the agent, and there's stuff going on in Buzz where that, you know, it's telling it, it has its own system prompt so that it knows how to use Buzz and how to leverage the tools within Buzz. But yeah, essentially, it's just a layer on on top, right? Did that answer your question?

06:53 >> yeah, 100%. And so, what's cool about what I found to be really cool about Buzz is that you can create channels, you can create agents, and you can do all of this by asking an agent inside Buzz, which is really cool. And so, I can say, "Fizz, can you please create a new agent named Harry, who does research on the best models and AI tools in the world?"

07:16 I can specify that I want it to be powered by Codex, and also make a new public channel called research where that agent will exist and put its work. And you can just like fire this prompt off. I don't know who Fizz is. So, when you first join Buzz, there's these like preloaded agents. I I I don't know who I think they're powered by Codex, maybe. I don't know.

07:43 I actually have no idea. >> When you sign up and are you install the app, um it'll so it'll already detect which harnesses you have installed on your system. And then if if you have, you know, one or two, you can click install. And so it will whichever one you install the ACP, this connector for, to speak with the the agents, it will use that one by default, yeah.

08:04 >> Got you. Okay, yeah. So whenever I need to like configure anything, I don't know why, I just talk to this yellow guy named Fizz, which is super funny. Um >> And so yeah, so right now I I think we'll we'll let this run in the background. It should do it. I like how before it creates like an agent, it'll just kind of pop up on my screen and then I can like approve it, which is really cool.

08:23 But yeah, it's like a fully agent native Slack. I'm curious I'm curious how have you been using it? I know it's only been out for a week. What would you say your go-to workflow is within Buzz? >> I mean, the the real the I'm kind of a I do things pretty vanilla. Like I I keep things pretty simple. Um like you, I don't go crazy with uh system prompts.

08:46 Um I haven't really given agents any specific roles. Like I'm using the default agents. I just the first thing I did was pin them to certain models. So I have I took Fizz and I just gave Fizz Fable cuz I wanted it to have a powerful model. And I the other one, I think Honey or whatever, I gave it uh Sonic because I want one that, you know, good for really simple tasks like just reviewing things, giving me summaries.

09:10 But if I want to plan and code and maybe, you know, come up with more complex tasks, then I'll use the better model, the more powerful model. So that's pretty much what I do. The the powerful thing for me is that everything is, like you're doing, like you can get the agents to create uh different kind of workflows for you, start channels, da da da. And then, you know, you go into those channels.

09:30 But basically what I'll do is a channel will kind of be like a feature or or idea or uh maybe a task. So, let's say I'm brainstorming something, like let's say a new landing page design. I'll start a new channel and then I'll start a um add an agent and start a conversation with the agent there. If I were to be working with other people, add them to the channel, we would brainstorm, then we tag the agent, like, "Hey, we like these three ideas.

09:54 Go off in parallel and make these three landing page designs, for example." >> That makes sense. And so, you just brought up working with other people. And this is actually where I like I think it starts to get a little confusing because um I've just used this as a personal kind of a way for me to interact with agents in a very novel way. Like you, I create threads for certain things and the agents will just kind of collaborate.

10:16 What I love about Buzz, and I think it's just their system prompt and kind of the way they set up Buzz, it's really good at just saying, like, "Hey, I I oftentimes I'll just say, "One of you take the lead, figure this out." And then Codex will be like, "Okay, I'll take the lead." And then it'll ask a question to Fable. The And then they'll kind of go back and forth twice and then start working on it.

10:34 So, that's like really fun to work one one human, many agents. My question is, where where it starts to get confusing is how to invite other people. You know, this isn't it's just like how do you host this, right? When when my computer is off, obviously my agents won't still exist, right? Like my agents are running they're running locally. They're using my skills that are located on my computer.

11:01 How does hosting work and like how would a team use this if you could break it down in like simple terms? >> Sure. So, uh when you start up, you each get um there's a there's a really core concept of openness to Buzz that might be hard for people to kind of wrap their head around, but plainly, I could I can say that in it's it it's very different to Slack in that Slack is the company that controls the data.

11:27 All your data is going in and out of Slack, right? They have the servers, they have the databases. When you write a message, it gets stored on their database. The approach that Buzz takes is that you use your either a hosted relay, it's called, but if you think of it, it's just a server, it's a database. So, what what Block will do or Buzz will do for you is they will spin up one of these servers with a database for you.

11:50 So, all the information that's happening on your in your instance of Buzz or in your community is going to whichever relay or server that you either can self-host or that you let Block self-host. So, that's like the main difference. If you let them self-host I'm sorry, if you let them host that relay for you, it's functioning pretty much the way that Slack would function, but you have more control over that data.

12:16 And we don't need to get too deep into that, but then inviting someone is pretty similar. You send them an invite list and they get added to your community and it all functions like Slack would function. >> That makes sense. That makes sense. I want to go back to the prompt that I ran a little bit earlier. So, I basically said, "Hey, can you please create an agent named Harry who does research on the best models and AI tools in the world powered by Codex.

12:39 Also, make a new public channel called research." And while you were talking, I quickly approved these screens that popped up which were to create the new agent. And so, if we come to the research thing and I think we can add people, it should have created an agent called Harry and it has the Codex logo. I'm typing out this prompt here. So, I'm just going to say, "Harry, take the lead.

13:02 Talk to the agents here. Come up with the best way to structure automation so that this research channel is the most productive for finding ideas for my podcast Agent Native. Take turns discussing ideas. Don't be afraid to disagree." And you can just tag all of the agents and then you can just fire it off. And what I really like is that they'll immediately react.

13:27 And so I think if they've seen it, it'll show the eyes. If they're actively working and responding, it'll show this. And then if you hover over this, you can actually see all of the agents that are working. And not only can you see which ones are working, you can actually click and see their activity. So this is Claude code, I believe. And you can just kind of see what each agent is doing.

13:48 And yeah, I think this is this is so much fun to kind of interact with all the agents. Uh >> Yeah, this is cool. This is This is why Riley is the man, because he's thinking of cool stuff like this. I saw you posted this on Twitter. I hadn't even thought of of trying to you know, like have them interact with with each other like that. Um I didn't think it would actually work.

14:08 I thought because of the way you have to tag agents for them to even contribute to the conversation, I thought they would not allow that. But that's like the super cool way to use these different models, right? Like each agent uses a different harness and maybe a different model. And you might have them be able to kind of just like duke it out and come up with really cool ideas that way.

14:27 >> Yes. And one thing I figured out um or at least I've tried this before in in many different ways. Like I tried to hack together my own solution. And one of the main problems is that they would get into these not infinite loops. They would stop at some point, but they would talk for way too long. And I found that Buzz, however they set up their harness, they usually just do like the minimum amount of turns based on my request.

14:47 So it's like very concise. You know, I was drafting up like a legal contract. I actually can't even show it, cuz it is like with sensitive information. But I had Fable and then 5.6 Soul Ultra, they were like discussing all of these different clauses, while also going through the contract in my email like a previous contracts in my email. And they went on for like 30 minutes like discussing all of the different clauses.

15:13 And then Codex found something and it was like, "Okay, we should do this." And then Claude searched the internet, searched the old contract that we've signed earlier, and then like came up with a counterpoint and it was just so fun to see them and then they settled on this like final agreement and I've just found that Buzz does a really good job of like allowing these agents to like concisely discuss and then it'll create the thing and then the thread just stops.

15:38 Uh which is >> which is not easy to do. >> Yeah. That's some singularity stuff right there. >> 100% and it kind of reminds me of like do you remember Multibook? Like they like >> Yeah. >> It's like a more structured productive Multibook kind of. But anyway, yeah, here Harry said I'll I'm taking the editor role and it can it mentions the other agents in its response and it's just kind of working.

16:01 Um and then it's just it's just fun to see I've never put this many agents, but they're just having a conversation. And >> Yeah. >> Harry >> it's important to mention that like some people might not have um uh lots of uh you know, unlimited plans for different hardnesses and different uh models and stuff and there is an a feature that you can um when you create the agent or edit the agent, you can select how many levels of parallelism.

16:31 Um so you can uh yeah, if you go to agents, you can allow them to work on task multiple tasks at the same time. So therefore if you only have like if you only have Codex, you can allow it to spin up like multiple sessions and work in parallel and you can set that somewhere in the settings like say uh five max or something like that or you want to let it go crazy, you can do 10, 15, 20, you know.

16:52 >> Oh, I see. >> customize the agent under advanced parallelism >> Very cool. Oh, so I I have it set to one. Is that >> Yeah. >> So is that >> know if it if it really honors that, but um for example, if you just like I was saying, you only have Codex, you could bump it up to 10 and you could do the same thing that you're the same thing you're showing here with the with that feature on with just Codex.

17:13 Yeah. >> That makes sense. Very cool. >> Maybe you won't be able to have Codex talking to itself, but you could have one feature saying like, "Do this research." and then you could say in another channel, "Codex, you know, work on this app." or something. >> Makes sense. That's very cool. Yeah, what other settings can you do? So, you can create an agent, you can create a channel.

17:34 Have you tried the huddle feature? >> Yes, and I didn't know how to get it working until just a minute ago, so I can run you through it if you want. >> Let's do it. So, obviously for those of you who've used Slack, you've probably have used the huddle feature, which allows you it's basically just like a quick Zoom call, and I think it's just voice for now, but I think I can just like huddle.

17:54 >> Yep. >> Let's see if this works. So, I can huddle with the different I think. Like, I need to like >> Yeah. >> add them. I tried this, and it just like Okay. Oh, is it like cuz it's working maybe? Actually, let's just add Codex and Claude Code for now. >> Yeah, it should be enough. >> So, we have four >> to get it working is that there's that little keyboard button next to the agent button there in the huddle.

18:19 >> There's a keyboard button. >> Yeah, or that start transcript, go ahead and start that. Now, go to the research huddle temporary channel underneath there, and start talking. >> Oh, I see. >> Yeah. >> I never pressed this button. Hello, guys. Can you guys let me know what we've done today? Don't include any sensitive information. >> And then, stop the transcript by clicking stop.

18:44 >> Oh, I see. Okay. Oh, okay. >> answer. >> And so, they just respond, and what's really cool is I said three different four different messages to them, and they're only responding to the one that would require a response, which is really cool. They're They can quickly see whether a response is necessary, which is which is I think it's pretty cool. >> I wasn't able to get it to work with Fable, maybe because it just took too long, but with Sonnet, so the agent that that had running on Sonnet was able to reply in voice

19:12 channel. So, you know, you get a you get a voice talking back to you. >> So, okay, I actually haven't set a model yet. So, if I wanted to create a new agent, could I just ask it to create a new agent powered by Claude Code, but it's Sonnet? Could I just ask >> Probably. Yeah, I've never tried it, but you could say, "Yeah, pin the model to Sonnet." >> So, I could just say, "Create Can you create a new agent called Sonnet that uses Sonnet 5."

19:42 Because I do know that Claude Code uses Fable out of the box, so >> Mhm. >> Is that it? Is that how we would do it? >> I would maybe be explicit and just say like that uses Sonnet as the uh only, you know, as the underlying model. >> Only model that it uses always. >> Yeah. >> Okay. And then So, yeah, I guess let's a lot of our audience are they're you you know, they're they're uh token budgeting, not token maxing.

20:08 And so >> Mhm. >> Um you can add other harnesses to this. I've only added Claude Code and Code X. Can I add Cursor to this, for example? Do you know? >> I don't know, but anything that uses this agent client protocol can, and I know that open source My guess is now that Cursor has their agents workflows and tools as well, so probably. Things like open code for sure.

20:31 It might not be as easy as uh click install when you start up Buzz at the first time, but it is possible. And of course, we got agents to help us do that, so >> Yeah, yeah, exactly. I was about to say. >> Yeah. >> So, yeah, if you downloaded open code, my I think you would just Sorry to interrupt. I would I would probably just ask Claude Code. I said, "Hey, I have open code downloaded on my computer.

20:52 Can you please set it up inside Buzz?" I'm sure it would probably work. >> Yep, it probably would, yeah. >> And so, open code I think is one of the best ways to get access to all the different models. >> I've never used it, and that would be a nice thing to check out next. But, but they also have these like subscription models open code go and Zen. Not affiliated with them, but I really like what they're doing.

21:12 People want choice and um, this is kind of the same principle that Buzz is built on. So, you know, you can choose those models underneath and I I would assume that you can use those open source and those other models like Kimmi with those plans. >> And then, um, what we should talk about, I think, is incredibly fun and incredibly effective, which is their mobile app.

21:31 Have you tried the mobile app? >> No, not yet. >> Yeah, so when you you can download the Buzz mobile app and again, it's free and it works from my perspective, it works very similarly to the the Codex remote or the in the ChatGPT app. You can very easily connect to Codex through the ChatGPT app. All you do is scan a QR code and boom, you have it connected.

21:49 Do you use your phone for like coding tasks at all? >> Definitely. I have the Claude code subscription, so I can do remote control in any session that's running. I can access on the on the mobile app and I really like that. That's a cool feature. >> So, here's Buzz on my phone and it took, you know, and like I was worried. I was like, oh no, is this going to take 20 minutes to set up?

22:12 It's like one QR code, one scan, now I have it all lined up and so I can just go into my coding channel and I can very easily at mention Claude code and I can say, I'm just going to say hi guys and they will respond and it's like very they're like perfectly in sync, which is really cool. Um, so yeah, highly recommend the iOS app. Um, I remember, I think it was you and Greg Eisenberg and a few others, you guys were talking about payments um, and some implications in the future about how they're going to implement

22:45 payments into this. I know that payments are going to be really important with agents. I'm curious how you see that kind of taking shape within Buzz or platforms like Buzz. >> Yeah, so you're talking about token budgeting or token efficiency, you know? And um, if you want to go down to your handle there, it says Riley Brown, and you can go into settings and go to the compute setting on the bottom left under agents.

23:09 >> Go to compute. >> Um there is this option [clears throat] there, and you can it says share compute, share this machine with your relay. When on, other members can run their agents here. So, uh what is basically allowing you to do is the local models and the open-source models are getting very good, and you can download it selects one it checks out what the specs on your machine gives you a model that would run, like probably the the most powerful model that would run on your machine.

23:34 And then when you share that on there, um you can then allow other people in your community to use that model running on your machine. So, if you create uh add an agent just like you did before, and when you select the harness, instead of selecting Claude code or or Codex, you select Buzz agent, and then there'll be an option to select the shared model that you're that you're using.

23:55 And um what that then allows is other people in your community can at or, you know, mention your agent and get that agent to do work, and that work that's being done is running on models on your machine. And that right there is already very impressive and very cool. But, you see where the option to then maybe charge small fees for uh for tasks exist.

24:19 You know, you maybe like you've got these these frontier models are running on in data centers that have, you know, the the the uh most powerful GPUs, the most powerful processors that are on the market at the moment. Um so, even a really powerful local model is going to take a lot of resources, electricity, and a really powerful computer. So, you could be maybe the person that invests in that, and you might have community members all over the world who don't usually have access to those kind of resources who might

24:50 want to get a task done, and they only want to pay, you know, per task. It's like a paper task model. They could pay you, or they could pay the agent or perhaps even agents could pay other agents. So, you have a lower level model that pays a higher level model to do a task for it. So, you know, we're talking about you you're already looking at the agent-to-agent economy by giving tasks to more multiple agents and telling them to delegate, figure stuff out, and get it done for you, and they're doing a really good job.

25:19 But, that's because you have access to these plans and they're probably being subsidized to a certain extent, so the prices will probably go up in the future. And as that stuff could start to get prohibitive, the the expenses get too high, then stuff like this will make it um will be a very cool solution. So, that's really interesting. >> What other features?

25:36 I see some things I've never opened this tab before. All I've done is kind of create agents. I see experiments. So, we have work Have you tested any of these? >> Yeah, I have. Workflows I haven't gotten to work um very well for me. In fact, there's something missing there. There's probably some bugs, but there's also um some implementation stuff they could work out.

25:56 So, workflows aren't the greatest, but I can live with that because a lot of the stuff, you know, you know, workflows you can set up like kind of recurring tasks. I'm sure they'll work that out, but um projects I think is very cool because under the surface what they're not really talking about as much is that they're also kind of looking to not only be a Slack killer and this agent orchestrator and manager, but also maybe a GitHub killer.

26:19 So, I'm not sure how familiar everyone in your community is with GitHub. So, we're going to go into that. >> Yeah, we should absolutely go into that. You can think of GitHub, at least the way I conceptualize it, it's almost like a Google Drive for coding tasks. It it it saves the different versions of your code, and all code is is just like a folder of files, which is called a repository.

26:39 And um I think that might be enough precursor into where we're going. >> Yeah, yeah, I think you're right. It's it's the place to put your code uh remotely. And but Git itself is a is a tool to, you know, because code is something while you work, you might want to work on many different versions, try out different features, try out things. So, you can work in different branches and different and and test out things um and always come back to like the main working code that you have already.

27:08 So, Git is that tool and GitHub is one of the most popular like the main default hosting solution to put it somewhere online so that you can collaborate with others or share the code with others. >> Sure. And so, you said they were trying to be a GitHub killer. What did you mean by that? >> So, I can't speak for them, you know, I don't work for for Buzz, but I do believe that they're trying to go after too many tools at once in a way.

27:36 Uh I think their focus, knowing Jack and um his philosophies, there openness is a big part. So, this idea of choice, like you said, I think the future of being able to run and share compute on local models is a big driver behind the behind Buzz. And um basically, because what we talked about earlier, when you start Buzz, that it creates a server and a database for your community that you create.

28:00 Well, that is something that Block, the company that creates Buzz, is is taking care of for you. They host that and they put your data there, but what as a side effect, you have a server and a database. You can now push your code with Git there instead of GitHub. >> So, >> this projects thing, it allows you to work with GitHub still, but um you can also push your code to your relay, what is what it's called.

28:27 To basically to the server that is running and storing the data for your community, you can push your code there as well as a as a remote cloud hosted uh solution. >> Cool. >> Yeah. >> That makes sense. And so, like yeah. >> back to your app, um you'll see projects now, a projects tab under inbox on the top left there. >> Oh, projects. >> Yes, and there should be a button maybe when you uh code.

28:52 >> I don't think I've set up the relay. Um I don't think I've I've I haven't fully set this up. It's just running locally on my computer. Wouldn't I need to set up the hosted community? Would I need to do that first? >> that might be. Um there should be It doesn't matter though because if it's running locally on your computer, yes, then it might not show that.

29:08 But um what it's doing is it's every time you create or you code or create an app or something, it'll create a folder on your computer and create like copies of that folder and so you can have like three agents working on, you know, three different uh ideas on that one app at the same time and they will be all managed by your agents and by Buzz. And then when you set up uh most people will go the shared uh server relay route.

29:33 So your code they'll be able to push the code and save it to the cloud on your relay on your data community's database and relay. Yeah. >> Gotcha. That makes sense. And so you're able to just like create a bunch of different versions of whatever app you're creating and the agents can collaborate and they might not like step on each other's feet or like mess up someone else's project.

29:53 They can um >> They'll do that locally on your computer and then they'll have access to, you know, with that project's thing you can tell them upload to GitHub. They might need you to give them um uh to they might need to install and log you in um to GitHub or whatever or you can just say yeah, upload to my relay. >> Got you. That makes sense. I I think So I'm obviously in marketing, content, and more like business operations than like technical side and I kind of want to talk a little bit about kind of what I hope

30:22 this platform turns into and I'm curious to get your thoughts. So, you know, I spent a year in Silicon Valley and there's a lot of people right now talking about creating like an open co-work, right? Or an open codex, you know, codex is this kind of super app that you can interact with an agent. It can do knowledge work for you. And what I'm hoping, and I think the coolest part about Codex is their in-app browser and just kind of that side panel.

30:46 So, if you were to create a PowerPoint, if you were to create a slide deck, if you were to create a video, if you create an image, it kind of it can open up in this kind of artifact view. And I notice here that they actually have like a little canvas feature. It's very bare-bones and minimal. I forget where it is. There's like can It's just like a text Yeah, it's right there.

31:04 Yeah, yeah. Where is it? Oh, yeah, canvas. And so, opens up a canvas and when I saw this my first instinct was like, "Oh, it'd be super cool." And then this is what I I I was like, "This is probably what an open co-work type app would be." It would be like many agents can operate in an interface that many people already understand. And then ideally, it would just be able to create any type of document, whether it's like a PDF, uh slide deck cuz like a lot of people like me who do knowledge work, like we're creating

31:33 documents and I'm trying to outline different things, sending like That's what a lot of knowledge workers do, spreadsheets. I think it'd be really cool if the agents could create different types of documents and it would just open it up here in the side in canvas similar to Codex. I'm curious about your thoughts there. >> Someone It's open source software, so someone's going to build it.

31:52 Maybe that person will be you, Riley. >> Oh, so it's open source software. So, I've never contributed to an open source project before. That sounds scary, but like I could in theory fork this and just tell Claude I could do it inside Buzz. Right? I could just say, "Can you fork Buzz?" >> to make new features for Buzz, yeah. >> So, okay. Please fork Buzz, run it locally.

32:17 Okay, I'll do that after this episode. >> you do that, well, if it works, that'd be cool. It might be able to find it. Um but if it doesn't, you just go Buzz like Buzz GitHub, look for the Buzz GitHub. >> Sure, sure, sure. >> And then you can get it and fork it there. >> This is good. Like you can always just fire off like um uh context as a secondary message um search this is Jack Dorsey's project search internet find the actual project.

32:47 I forgot that it's open source. I can just kind of add my own features to it. That'd be kind of cool. >> Yeah, you could have your own um like custom version. You don't ever have to submit a PR, but if you wanted to try and get like kind of like you said like a browser view in there, it might be able to you might probably be able to pull it off with uh a frontier model yet.

33:06 >> Pretty cool. I'll work on that after the after the episode. What else do you think people will find interesting? Is there anything else that like you've been testing that you think is just like super cool about Buzz? >> I think we pretty much hit on it. I think one thing to to note is like you're you're thinking ahead. I think that's right. I think it's um I think they've scoped the feature set in the beginning here to let people kind of play around with it and see what people really want.

33:29 But I think there's a lot of stuff that's going to come out of this in the future that will make it even more powerful than it is at the moment. And I would say like uh it's probably for for your audience, it's probably a great thing to try out already. It's not perfect. I don't know if you've run into some kind of like rough edges here and there, but I have.

33:47 But I'm sure they're really trying to push it with like workflows and stuff like that. But the really cool thing is is that because it's built on this open protocol and it's not stuck on you know just some one company's uh controlling all the data and and the shape of everything, makes it really easy to integrate stuff with. So what I did with that was pretty cool.

34:07 I did it in a in a second tweet uh with a video that I made where it's just like I'm publishing data from an app that have really strict guardrails. I don't need an agent to do it, right? It's like scraping getting information from the X API and stuff. But it'll send it over every day to Buzz. So because it has this relay that like kind I'm kind of in control of and it's an open protocol, it's very easy for me to integrate solutions, my own custom apps that send information over to my Buzz relay, and I can get Buzz to

34:37 make this stuff for me, right? It does all the coding, it makes it, and then, boom, in the morning, I have stuff in Buzz that I can then chat with agents about and start working on right away. So, this like unifies all of your context into one area, into one app, so that I'm not going to Twitter, copy and pasting something into ChatGPT, trying to come up with tweet ideas, I don't know, trying to analyze tweets.

35:05 It's all like this circular, closed, giant context window, and that's what's so cool about it. >> That is really cool. And I think one thing you touched on earlier is like I don't know if you use the term automations or webhooks or triggers. Are there ways that I could get some external thing to like trigger a prompt being sent into Buzz? Because I think that's what a Go ahead.

35:29 >> Yeah, that's something Sorry, that's something I I tried where it wasn't really working well. So, I originally I was trying to get the agent to you know, find this information from my app and then kind of summarize it, and it wasn't working and maybe you're pretty good with getting the agents to communicate with each other and stuff and doing it agent first.

35:51 So, that I would maybe try that, but I do think there's potential there. I think it's a bit buggy at the moment. So, yeah, it's starting Docker for you. So, there you go. Um >> Cool. >> Um but yeah, there is ways there are the workflows they're called. So, you could say like um uh in the in your channel, you know, tell me ping me every day to yeah, let remind me to to do something.

36:17 I don't know. >> It's like a say something with those word fun. >> Yeah. >> So, I could tell Harry, who's my research agent, I said like every day, please search Wait, which model is Harry again? Oh, no, Harry's Codex. Please every day search um the 25 creators in my niche uh for AI news and use scrape creators, which is a skill that I've set up. It's literally scrapecreators.io or something.

36:44 I forget what it is. That allows you to just scrape from any social media platform with one API key. Um and it's like uh please find those creators now based Ooh, Buzz is doing something. Um creators now um based on me, Riley Brown, on X. I don't know. But the point is here is like I want to be able to like create a new channel. There's things that I do every day, things that I check every day, things that need upkeep every day.

37:20 I would love to be able to just tell an agent to like handle something every day at a very specific time and then like have trust that it solves it. I think that's the one main limitation I'm running into right now as I'm using the all of these different agent tools. It's like every new task that I create create has like a like hidden tax on my brain because I'm worried it's not going to succeed.

37:42 And like the point that I hope we get to is like I could just fire up an agent with Fable 6 uh and or it's like Fable 6 on continuous mode and I could just say, "Hey, like for these hours I need you to constantly check on certain things um and like here's the end goal every day for this thing and just trust that it'll get done correctly." Cuz that will just give me just [clears throat] an insane amount of leverage.

38:04 Cuz right now like it does things that surprise me in a very good way, but I just don't have trust in my AI agent team. That's what I lack. Like sometimes it doesn't fire off. It'll just like some and I've actually tried this already. I don't know if you've seen this where I said like every um like at 9:00 a.m. I need you I in this management chat. I have it check my emails.

38:23 And then this morning it just said it literally just said, "It's 9:00 a.m. I need to do this. I need to check Riley's email." and it listed out the task instead of doing the task, which is super annoying. I I don't know if you've run into >> That's the problem I've run into with workflows, exactly. So, um there I think that's a bug uh that they'll probably end up working out.

38:48 >> Maybe maybe the the the the current fix might be to like um whenever you do this task, ping Claude Code, and then tell Claude Code to make sure that it does it so that like Claude Code will just do a check, and if it doesn't do the task, it'll tell Codex to finish the task or something. I don't know. >> That's what I was trying to do before I hopped on here was like get it to I had that app and it's pushing tweet stats.

39:13 It's getting all the stats on um the my the team I work for, the all of our tweets, the impressions number, the tweets themselves, and like I want push it every day and automatically I want it to give me a review of like, "What's the common thread between the uh stuff that's working? Where can we improve?" You know, something like that. And it was doing the same thing.

39:32 And I would My idea was to to have it um mention another agent and get it to do that, but I haven't found a way to get it working really reliably reliably, yeah. >> My brain immediately goes to like creating an agent called task checker, and its only role is to like make sure that the agents that do tasks are >> are done. And then but on every recurring task that you create, the agent that runs will ping this task checker every time no matter what.

40:00 Maybe that's like the first thing it does is ping it, and then the task checker will do nothing if it does it, but if it doesn't do something, it'll be like, "Hey, you didn't finish the task." or something. I don't know. >> That's a good idea, or just like run have it run every 15 minutes, and if there's a task that didn't really fire, get nudge them or something.

40:18 Yeah, stuff like that. >> That's really good idea. Yeah, very interesting. Um Yeah, dude, this is incredibly informative. I'm super excited to dive into workflows and kind of figure that out and I'm actually going to fork Buzz. I'm going to see what I can add on with this canvas thing. I think that'd be kind of fun. It's just a side a fun side project.

40:38 Maybe I'll make a video on that. I do want to close like is there anything that like what are you what are you working on? Is there anything you want to want to talk about um for stuff that you're working on? I don't know if you're working on any projects or tools. >> Yeah, um so I'm from what I gather most of the audience is focused on like entrepreneurship and and stuff like that, but these these guys are great at coding and making apps and now with these kind of apps that are very open, you can build stuff that like

41:09 that you can build really bespoke tools that integrate with Buzz and you know, close this con close the loop on the context that you're kind of like shuffling around everywhere and um um I'm part of a team and we we're working on a full-stack TypeScript framework that works really well with agents. So in my videos, it's called Wasp the framework, which is kind of funny because we're Buzz and Wasp and um it does a lot of the framework does a lot of the heavy lifting and gives tools back to the agent so the agent can do

41:47 stuff very easily. So like when I tell it use Wasp to build an app like a a CRM for example and deploy it right away so that it's live on the internet, it works really well and I did that in and I've I've I'm using Wasp in the videos and showing that. So that's what I'm working on. We're we're working on a way that like makes it very easy for humans and agents to collaborate to build full stack apps.

42:14 That's kind of my focus at the moment. >> Dude, thank you so much. I really thank you for for kind of talking me through this. I learned a lot. Um and I'm inspired to kind of work on workflows and also like building my own stuff on top of Buzz and kind of see where that takes me. Um >> Yeah, thank you. I'm looking forward to seeing what you build. >> All right, guys.

42:32 You made it to part two of this video and I hope you enjoyed the conversation. I just want to make sure that I pack this video with as much value as humanly possible and I want to talk a little bit about how I've constructed my team of these different agents all running different harnesses. And as you can see here, I got my whole team here. I have them all responding to all of my messages.

42:54 They're constantly checking each other's work and I just want to take 10 to 15 minutes to describe how I'm thinking about this and how I'm going to use this within my startup. And so, I just want to start from the beginning. If you haven't downloaded it, you can download it at buzz.xyz. It's literally free to download and it's free to use as long as you have either Codex or Claude code or any other agent that you've downloaded on your computer, which will actually cost money.

43:18 But once you download Buzz, you should come to a page like this except obviously it'll be empty. And when you're first signing up, you're going to choose a default agent. For me, my default agent is Codex. You could use Claude code if you have a Claude subscription as well. And so, when you're creating an agent, when you click new agent and create from scratch.

43:38 And what you can do is you can use your harness defaults and my default harness is Codex. I can customize this or for this agent and I can change to any other harness that's running on my computer. Now, there's a certain list of tools that will automatically show up if you have them downloaded on your computer. For instance, Devin is not one of those tools or at least it wasn't yesterday.

44:02 So, I actually had to ask Codex within Buzz to configure Devin Because I have a Devin subscription, I said, "I need you to configure Devin so it's viewable within the Buzz app." And it can do that. And if you have Cursor downloaded on your computer, it should show up here. For instance, I've downloaded Grok Build, which is uh Grok's CLI tool, and I can select Grok Build.

44:24 And I've actually never done that. So, we can actually configure a Grok Build agent, and we'll just call this Grok Build agent. And so, let's say I wanted to create a Cursor agent. And you The reason you might want to create a Cursor agent is it allows you to create use of like from a very long list of models, right? Let's say I wanted to create one with like Sonnet 5.

44:43 We want to save money, and we can just do Sonnet 5 thinking true context 300K, and we could just create this Cursor agent. And I could just call this Sonnet, and I could just type in Cursor. And so, I could choose any image I want. In this case, I'm going to be using this little quad icon here, and I could just create this Sonnet agent. And as you can see here, I now have added a new agent, which is just Cursor, which runs Sonnet as the default model.

45:11 Once you create a new agent, it doesn't automatically enter all of your channels. You can add them in two ways. One way is you can manually Actually, three ways. One way is you could look for them. And so, I'm going to add Muse open router to this channel. So, this is Meta's new model that I've added. I could also um just at mention um I could just at mention Sonnet, and I could just say, "Hi."

45:35 And when you do this, it should automatically add it to that channel. So, all you have to do is mention it. And so, the main reason people don't like to switch from Codex to Claude Code to Cursor to Devin to all these different harnesses is because usually your skills just live in one place. And yeah, you can find ways to like merge the skills, but they don't work in the same exact way.

45:56 And so, that's why so far as I've used Buzz, I will kind of have a lead agent. And so, my lead agent is Codex because I use it the most and it has all of my skills. Another thing that Codex has is computer use. Its computer use is the best, so I will rely on it the most. So, I just kind of use Codex. And so, let's say and Codex has all of my skills.

46:21 And so, these are all of the skills that you've already added to the desktop app. If you watch my videos and you've used Codex, um and let's say we're using Codex and we have all my skills here, right? I have YouTube researcher skill, I have my thumbnail, I have all of my different skills. I have many different like Notion research skills, probably 30 different skills.

46:44 And so, Codex really knows me. Codex has all my memory, I use it the most. And so, that's also why I rely on Codex the most. But sometimes you want them to work together and so, I'll make sure to always start off with Codex if I need to use one of my skills. For instance, I can use Buzz and I can say like, if we are in our content channel, I can just say, "Hey Codex, uh please I need thumbnails for today's uh episode on Buzz.

47:11 I need five options. Use sub-agents and um and make these thumbnails using the correct skill and I will just tag in. Let's go Claude Code and Codex or and Cursor. And uh let's say Grok. Maybe Grok has a good sense of what would look good. Uh please provide feedback. Then Codex, do another five thumbnails. And so, I can just fire these off and then all of these agents are going to work.

47:54 As you You see here, we have Claude Code and Codex beginning some activity. There's Grok. X should take the lead. It'll generate some thumbnails. It's going to ask Claude Code and Grok for their feedback. And then Codex will do another five. And then I can just include like based on their feedback. But I think that was implied. And now I'll just go I'm going to go get fill up my water and I'll be back in about 5 minutes.

48:21 Okay, so it used my skill. And here's round one. Here's five thumbnails that it created. And all of them have my face because it found an image on my computer and it uses it as an input image. It's very white. So it says, "Please rank these one through five." It tagged Claude Code and Grok five. And uh I'll use both critiques to make the next five. And now we can see that uh Grok and Claude Code are now working, which is really cool to have these agents work together.

48:51 While this is loading, I do want to show you how I added Muse Spark, powered by Open Router. So Muse is Open is Meta's new uh agentic model that they've created. Um as you can see here some uh feedback just came in from Grok, which is pretty cool. But if we're going to our agents page here and we want to create a new agent, create an agent, you can customize this agent and you can create a buzz agent.

49:16 And so I think this is their default harness or something. I actually don't fully know how it works. I just know that you have to do this to use Open Router. And the way that I created this one, if we go to edit, we can see that we chose buzz agent. We use an LLM provider, which is OpenAI compatible, right? This is the one that I selected. And then you need to go to Open Router and get an API key.

49:38 So Open Router allows you to use all these different AI models. And so you need to select OpenAI compatible, paste the API key. And then you need to go down to advanced because this model actually won't show up here. What you need to do is you need to paste this exactly like this. You need to paste I'm going to copy this this is exactly what you need to paste into this right here is _base_url.

50:04 And then you're going to paste this exactly. If you ask Claude Code or Codex what you need to paste into use you like your AI agents will tell you exactly what to paste in. They actually can't do this for you. Um and then for thinking effort you need to put inherit agent default, inherit agent default, inherit agent default, inherit agent default. Once you do that you will be able to click on this model and you'll be able to choose from any model and you can create a Buzz agent with any AI model that exists right now.

50:37 And I did it with Muse and that's how I added Muse. So that's just one thing that's pretty interesting. Okay, it looks like it's done. Round two is done. Five revised. There we go. Team it's not bots my AI team. Oh, look there he is. There's Vinnie the guy we interviewed. Right? He they put him in. This changes everything. Look at how it did that. It started off with these thumbnails right here very mid.

51:04 Now Grok and Claude Code gave its feedback and then look at what it created. 1.2 million views, one team chat, my AI agent team. This one might be the best one. Um but it inserted me into all of the thumbnails and this is just one way that you can collaborate with AI agents. And remember on the free iOS app all of this works, right? I can see all of the images that it just created and I can provide even more feedback and I can say I love five.

51:33 Let's make three variations and then I'll just at and I can fire this prompt in. And now you can see Codex is typing and so I can control this from my phone when my laptop is open. Okay, to kind of close out this video, I do want to talk about one specific channel that I've created. I can't open it up because it's so personal to me. It manages my email.

51:56 It manages my uh Slack. It manages my communication with my sponsorships team. And um it also has access to my texts, as well. And so, I created a new agent powered by Codex. And if you've used Codex, the Codex app on your computer, remember it's like basically the same thing. You're just kind of communicating with the same underlying agent. And this agent can access your text messages.

52:20 And so, this management agent, basically every morning it reads all of my stuff, and then tells me a ordered list of things that I should take action on. So, if it reads an email that I've got that requires like an urgent response, it'll put it at the top. And it does this every 3 hours. So, 9:00 a.m., 12:00 p.m., 3:00 p.m., and 6:00 p.m. every day it kind of analyzes everything and tells me exactly what I need to do.

52:43 And these are like really urgent things that I need to get done. And I can just respond. I can say, "Hey, can you write this email back to this person?" And I can just type it directly in the management chat, which is incredibly useful. And so, this management channel has like a narrow version of Codex. And this management agent has one little paragraph that describes exactly what it does, where it can find key information, the exact link to the part of the Notion that I use, right?

53:09 They these it actually just uses all of my management skills that I already have in Codex. And so, when I created this agent, I just asked Codex. I said, "Hey, there are a lot of things that I use to manage my life. There's a lot of skills and memory. Can you please take all of that and like list them all out here?" And then I just told it what parts were important, and of those things to include it in the new management agent.

53:31 And so, now I have this narrow management agent that knows it's a management agent. But it's not a separate agent than Codex, right? It's still the same Codex, just a different system prompt that it runs every single time I talk to it, but at least to keep it it keeps it focused and it just basically lives in my DMs or in the management channel. Those are the only places I really use this management agent and I'm now starting to think about how I want to add teams and I want to add members of my team.

53:56 My content team is like six or seven people now and so I'm starting to think how do I bring them in to this workspace? How do I allow them to use all these skills and these are things that I'm thinking about and so I'm filming a video tomorrow actually with Vishal and we are going to be talking about creating teams, creating agents that don't die within Buzz and we're going to dive even deeper because whenever I find a tool like Buzz that's and last time I had this feeling was kind of open claw back in January where

54:26 I'm like okay, there's something here. There's something novel about this experience. I kind of want to follow it deeper and I I I just I have this instinct that this is like a really important form factor for AI agents. I've never had this feeling of allowing my agents to collaborate in such an easy way that like my entire team would understand. It's it requires like no technical ability and so I'm going to keep using Buzz.

54:50 I'm going to keep learning Buzz and I will do my best to convey this over the next few videos that I make on Buzz. I really want to make it easy to understand and really easy to use. So thank you guys so much for watching. I genuinely am incredibly excited about this this tool. Vinnie was an amazing guest to have on the podcast and I will see you here for the next video.