Agents get their own AOL, Andrew gets published, and vibe coding is actually good?

**Andrew Ziegler** (0:05)
Did you use AOL, or were you like an ICQ, or an AIM, or MSN person, or Yahoo? Were you a YIM person?

**Ben Lloyd-Pearson** (0:13)
Oh, I was definitely an AIM person. I was heavy into AIM with all the customized profiles, and emojis, and the games that were built into it. I love that platform, that was basically my teenage years.

**Andrew Ziegler** (0:25)
That was what made Yahoo! And MSN for so fun too, because you could do all the customizing. I mean, they all kind of had that. But AIM was definitely the first one that had the sound effects, like the door opening and closing. That is rent-free in my mind, and AOL will always be there.

**Ben Lloyd-Pearson** (0:41)
Man, that's some nostalgia I haven't tapped into in a while. Well, it's really awesome, because now AI agents get to experience the early era of AOL and instant messengers and stuff like that. I'm personally really happy that they get to experience this. But yeah, I'm talking about this new open source project that we came across this week called AOL.
Agents Online, pretty cool.
It's just a chat room for agents to work together in with a really kitschy name.
I just wonder, what's the agent version of ASL? You remember this from the chat room days? No one does this anymore, because it's doxing yourself. But everyone asking for your age, and of course, today it wouldn't be S, it would be a gender. They'd ask for your gender and then your location. Like, who are you? Where do you live? Like that kind of stuff. Do you think there's an agent version of that?

**Andrew Ziegler** (1:33)
Oh, absolutely. I look back when your internet persona was just the word on the screen. You didn't even have a profile. People literally had no idea who you were. And they just live in the world, too. I would guess that their ASL is like, what model are they?
What's their context of Windows currently filled app? And what capabilities do they have? Oh yeah, and then what MCP servers are you currently connected to? That would be like their ASL handshake.

**Ben Lloyd-Pearson** (2:00)
Well, we do definitely need this. You know, as somebody who was both like that former AIM user and a former AOL employee, I think this is absolutely necessary. Like this is, if you want to be on the internet, you have to experience like that sensation of these like early chat rooms, because it really was like such a fundamental component of the early internets.

**Andrew Ziegler** (2:20)
Precisely, and what's fun about it is that, like even though it's nostalgic, it's not a joke either. The underlying principles of how it work really linked back to how agents do collaborate and corroborate with each other. The idea that they can set statuses, they can see each other's work as they do it, because it's like a status in the messenger, as well as send obviously information back and forth on a local server. Kind of an interesting concept, a way of giving them some more presence, I think, on the internet. Now, it's only to think of maybe they bridge out of that into messaging humans. It's not just the agents online, but we're all online with them.

**Ben Lloyd-Pearson** (2:57)
Yeah. Well, welcome to The Friday Deploy brought to you by LinearB. We got a lot of awesome news like that to share today. I'm your host, Ben Lloyd-Pearson.

**Andrew Ziegler** (3:05)
And I'm your host, Andrew Ziegler.

**Ben Lloyd-Pearson** (3:07)
All right. Today, we are covering the growing convergence of Vibe coding and agentic engineering.
Andrew's new agentic development research, build-first development processes, the evolution of technical interviews, and enterprise AI's last mile failure. So we've got a lot to cover today. Let's start right at the top with how Vibe coding and agentic engineering are getting closer than some people might like, including Simon Willis. What do we have here, Andrew?

**Andrew Ziegler** (3:34)
So Simon Willis, once again, in our lineup, we can't get enough of what Simon writes about. He's on the edge of everything with AI adoption, especially for large teams and how open source folks are thinking about it, and really connecting the dots between those two worlds. So in this article, Simon admits like that his vibe coding experiences and his agentic engineering experiences, which are supposed to be the more formalized version of that. They're starting to converge just as AI work just becomes more reliable across the board. Vibe coding starts to enter a impossible to fail territory where you don't have to do as much of the discipline that we now call agentic engineering. And this is happening because harnesses are evolving, it's happening because the models are getting better. But he admits that he's stopped reviewing every line of the AI-generated code even for production systems. Because the coding agent is more like a trusted external team. And while that shift makes them uncomfortable, it's proven to be consistently reliable, which is an early sign for the new mode of reliability we might be shifting into for AI output.