Lenny's Podcast: Product | Career | Growth
00:46:32 · Andrew Ambrosino, S1
[00:46:32] S0: Yeah. And the app will say it'll set it up for you. If it doesn't have a Slack connector, it'll say, "Can I add the Slack connector? Yes or no?" You can hit yes to that. The least that we can do is make it so that if you don't know how to do something in the app, that you can just ask it. I don't think that's enough, but I think that's the least we can do. [00:46:52] S1: Yeah. A good example of this, I built this little app that filters spammy email from my inbox. So every email that comes in, and I built this in Codex, every email that comes in, it looks at it and decides is this unsolicited, kind of cold emaily stuff that I don't want to look at? And labels it and puts it somewhere else. And to set that up, one of the steps was you have to go into the Google Cloud console and set up all these hub, sub, hubbub, API things, and triggers. I don't know if you've ever used that interface. It's so annoying and slow. [00:47:20] S0: Right. [00:47:20] S1: So I was like, "Wait, what if I ask you to do it?" And I was like, "Okay, cool. Do this for me." And it just... You described computer use. I've never actually seen this happen on my computer before. It just takes over my computer and starts going there. [00:47:32] S0: It's like, "I don't care if you don't have a connector, man, I'll just start clicking." [00:47:35] S1: Yeah. And it figures it out. It's crazy just to watch it doing this thing.
00:47:35 · S1, Andrew Ambrosino
[00:47:35] S1: Yeah. And it figures it out. It's crazy just to watch it doing this thing. [00:47:39] S0: Designing the decision boundary between connectors. When to use the in-app browser versus your Chrome extension that's connected versus computer us was interesting. And all done through just feeling it out. [00:47:52] S1: I saw a great Twitter thread the other day where they describe all these three and what you use it for. So this person described it really well.
00:47:52 · S1, Andrew Ambrosino
[00:47:52] S1: I saw a great Twitter thread the other day where they describe all these three and what you use it for. So this person described it really well. [00:47:58] S0: These personal workflows are really interesting because some of them really click. People are trying all sorts of stuff. Everybody's making these personal systems. You ask everybody here what they do and everything's going to be different. And then certain themes arise and we're like, "You know what? That should be a first class experience on the app. We should take this thing that everybody seems to be setting up and just make that work." And I think memory is sort of in the shape where we've had a lot of people, and a lot of people at other companies too are like, "Well, I set up an Obsidian base or a Notion area. And I tell it how to basically build my mind palace and how to put..." It's like, "I don't know if everyone..." You shouldn't have to do that. There should be a memory feature that does that for you, that's pretty generic. So that's one. But then there are other things like they're your process of your job. And there's something that like, "Yeah, you should set that up." But I think we're constantly wading through what's working for individual people, what should enter the product? Versus stay, no, that's just how you do your job, right? What should become a primitive, what shouldn't?
00:49:06 · S1, Andrew Ambrosino
[00:49:06] S1: Yeah. This is the taste and judgment you spoke of earlier deciding these things. I want to talk about this browser use piece a little bit because I think people don't realize how powerful this is and what it could be used for. Reminds me, I don't know if you watched when Dan Shipper was on the podcast, from Every. He had this prediction that we're going to start using Codex to run our SaaS apps inside out. So instead of going in Chrome- [00:49:29] S0: I know, he Slacks me about this every day asking for stuff. [00:49:33] S1: Do you feel like this is where things go?zeolite Where we're just working within the Codex app using Notion and Linear and Salesforce inside with your agent kind of helping you along? Or do you think that's a kind of a different direction?
00:49:46 · Andrew Ambrosino
[00:49:46] S0: Yeah, it's been really interesting because obviously we've had a few attempts at browser shaped activity. And Operator and ChatGPT agent mode and Atlas. And now we have the in-app browser inside of the desktop app. We also have the ability to install a Chrome extension where the app connects to Chrome. We've had a lot of shapes of this and I think we've learned a lot of different things. There's a lot at play. There's a lot of really boring things at play. We originally launched the app, it's an electron app. The things that you can do with in-app browsers in there, it's kind of janky. So the in-app browser was for development, it was for testing your front end on development. And we were like, "It's not really for anything else, guys. It's a developer tool." And then we switched over to our Owlstack, which had powered the Atlas browser. And so now it multi-tab. And we've got enterprise security so that you can actually log into all your websites if you're... So we've been iterating on this. I think the tough thing has always been, what should the shape of this browser be? Is this something that is only for the agent? That you've got Chrome, you open Chrome, you do your thing in Chrome. If you ask the desktop app, it opens up this browser that it can control really quickly, doesn't have the latency of Playwright, whatever. Or are we trying to say, "This app is for everything and we want you to use this as a browser." And those have a lot of trade-offs. It's not super well-traveled path. Most browsers are browsers at the top level. They've got browser tabs. This creates a lot of really boring but tedious problems like keyboard shortcuts, right? Are we trying to do key mapping to VS code or to Chrome or to our own thing? Or to Linear? We want to have some sort of muscle memory that carries over, but got all these things that have sub-shapes of different products out on the market. What do we do?
00:51:42 · S1, Andrew Ambrosino
[00:51:42] S1: And this just highlights how extra challenging this app is where you have to allow it to work. For somebody that's never built anything from the more basic user, to power like Peter, OpenClaw trying to code with it. [00:51:58] S0: I'm not convinced I'm going to get Peter to use the app. I think he might be the last- [00:52:02] S1: He's a terminal hold out. [00:52:04] S0: ... terminal hold out. [00:52:04] S1: Okay. [00:52:05] S0: But I'm going to keep trying. [00:52:06] S1: Okay. Let me zoom out for a moment and talk about the big picture of where you're taking all this. What's the vision for Codex? Where does this go? What's it going to look like, I don't know, a year or two, 10 years?