In this interview, GitHub engineer John Berryman discusses several forward‑looking AI applications and their broader implications. He describes a therapist‑training simulation built with a multi‑agent system (a Google‑style agent, a human trainee, a coach, and an evaluator) that enables immersive practice in low‑resource settings. Berryman then critiques the common view of Retrieval‑Augmented Generation (RAG) as a monolithic black box, arguing that it should be decomposed into its constituent agent loop and search tool, each of which can be debugged and improved separately. He predicts that traditional landing‑page websites will disappear within a decade, replaced by data‑driven conversational interfaces powered by LLMs that handle search, purchase, and UI generation without a visual front‑end. The conversation shifts to career advice, emphasizing that mid‑career professionals must rapidly adapt to AI‑augmented workflows or risk obsolescence, while those near retirement may ride the transition. Finally, Berryman shares personal practices—farming in West Tennessee, homeschooling his children, and teaching them resilience and a hands‑on relationship with technology—to illustrate how he models adaptability and lifelong learning.
Chapters
A recent client had a really cool application that they were working on, and I was fortunate to help them kind of build up their foundation. And it, it is a therapist trainer application. So they're not replacing a therapist because therapists need to be human, but it was going into places that didn't have the educational institutions to deal with training therapist and he was making a simulation. So imagine like war zones around the world, you know, places with extreme poverty, but places that need therapists, right? And so what we had the agent do was a Google agent and we would place the human therapist trainee into a setting where they're speaking with a client, patient, basically, that's an avatar on the screen that would speak with them. There was also a coach in the room that was watching and making sure that they follow a protocol. And there is an evaluator that's listening to everything and, you know, providing ideas for like how you can improve things. All this stuff was live and it's— we're used to is like, here's an email, pull this structured information out of it. And it would like usually get it right, but sometimes not. And you have to really check. Now it's, it's like, here, we're going to put you in this immersive experience and you just kind of go with the flow. It's just amazing how we can coordinate this stuff. If you, if you were training as a therapist, imagine implementing, implementing this with real humans. That would be a feat. You'd have to have an actor for the client. You'd have to have a trained professional for the, the coach. You'd have to have probably another professional as evaluator. And it's not perfect for sure, but, you know, I was building the thing and was still quite amazed with how intelligent these systems are. That client, for example, one thing that they've come— got in the works, the protocol involves like drawing stuff on a whiteboard. And we decided, eh, just the, the technology's just not there. Except about a month into it, we're like, oh wait, this technology's really close. And by the end of my like 3 months tenure there, I, I think they decided to start adopting some of that technology. Because like, in the span of 3 months, it went from basically impossible to, wow, it seems to just work.
Now, what's broken about this approach?
I come from a search background, and so it's always been a puzzle to me why people choose to cede over control and just leave that inside this black box called RAG. The better approach, the thing that I think is slowly starting to win out, is to not think of RAG as one atomic black box thing, and instead think of it as all its constituent pieces. So RAG is an agent, and it's search, and that's, that's all there is at this level. An agent, all an agent is, is a for loop around a large language model call with a, with a context that, that keeps growing and some tools. Now If the tool is itself a search tool, ta-da, you've got RAG. If RAG isn't working, it's not because RAG is broken. It's because something along the way is messed up. So I'm going to look through all of my common searches. Is the agent itself interpreting the user's information incorrectly? Okay, well, I can fix that. It's prompt engineering, context engineering. Whenever the agent decides to make a query, is the query well-formed? Okay, we can fix that. Whenever the results come back, are they sensible results? So we completely decoupled it into an agent AI problem and a search problem as distinct problems. And that's why I think this idea of RAG as a black box is silly.
Like the other day, I was walking on a street, downtown Castro, and there was like high school or middle school kids, they were walking by. And they were talking to each other. One kid said, oh, let's go to Walgreens. And then the other kid said, oh, let me ChatGPT what's on sale.
I don't think any website is going to exist in 5 or 10 years. I think in the 5 to 10 year range, everything that's like a landing page website is going to go away. And in its place, that website is going to have data that is accessible by search tools and the ability to modify stuff. So at an e-commerce site, it's not a website, place, it's going to have the ability to purchase things. That's like, and you'll have the ability to search for things, but you won't have any UI. Instead, ChatGPT or Anthropic or anybody is going to provide a conversational interface just like the kids had, or live coding is going to be so easy for, for the trivial apps and for UIs that basically you can say, here's what I want and here's how I want you to present it to me. And your own amazon.com that has all the facets that you want and all the stuff that you care about is going to be presented to you and you only. And so that's what's going to happen.
Everybody's company landing page will become this huge Lindsay Lom's text file that nobody will look at.
Yeah, totally a possibility. Yeah.
Oh man.
Yeah. LLMs.txt and a list of tools or something.
How do you think people's career paths are going to change?
I think we are at the fork in the road between utopia and dystopia. I think if you're close to the end of the career, You might be lucky and be able to ride it out. If you're in the middle part of your career, you better be adapting pretty quick so you don't end up in trouble, 10 years left to work and not employable. I think it's important to understand how these AIs work and can augment you because you're going to be competing with people that are augmented by AI. It's just a tool. And there's people that are fretting about like, But there is a group that are thinking ahead. They're thinking, I'm not going to be able to do the things that people were taught to do in my field for so long, but there's so many things more things I can do. And if you have that mindset, the world's your oyster. Love startups, uh, that's— but I would not build a startup today that looked anything like a startup from 2022 because something that you could almost 5-code in like a weekend for those things. But thinking ahead, you got to think about, well, what, what are people going to be doing? How's this technology going to change things? I want to build that, something that is— was utterly unimaginable and unreachable in 2022.
You have kids, right? What are you telling them they should grow up to do now?
We're teaching them how to farm. To hoe crops. I actually do have a farm in West Tennessee. My grandmother had a nice farm. So if the dystopia side wins out, then I still— we've got a tractor. I have an 8-year-old and an 11-year-old, and I'm trying to practice what I'm preaching. Uh, when I became a consultant, I wanted them to see me, um, visibly struggling and failing and being confused and getting up and trying again and succeeding. And they've seen it all because I want them to understand it's okay to try, struggle, fail, and just once you keep going, it— you won't fail for forever. And failure is not the Failure's not really a thing like you thought it was. And then the other thing is just like with the technology and stuff, I make sure that they're very aware of it. My whole family is, my wife actually vibe-coded a Revolutionary War education game. We homeschool our kids. So, we're weird.
