Boris Cherny: Claude Code & the Future of Engineering | Acquired Unplugged
Source
WorkOS
Author
WorkOS
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Straight from the person who built Claude Code, this is less a tutorial and more a mental model shift: treating natural language as the primary interface for shipping software, with the Cowork-in-8-days story as proof of what that unlocks. Worth it if you're an engineer trying to figure out where agentic coding actually changes your workflow — you'll walk away with a clearer sense of what to hand off to an AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → and what still needs your hands on the keyboard.
Key quotes
“I have loops that are running. They're the ones that are prompting Claude and kind of figuring out what to do. My job is to write loops.”
Boris Cherny
“In November I uninstalled my ID because I wasn't using it.”
Boris Cherny
“So if you're working on a project and you're like this feels like it needs like four engineers, put two engineers on it and give them a bunch of tokens and have them figure out how to do it.”
Boris Cherny
“fundamentally you have to study it in the wild to see what it does once it's safe in all these other ways”
Boris Cherny
“I think the final thing that we're going to be teaching the model is values and how to be, you know, the the way that we teach our kids how to be good people.”
