Behind the Craft · Sunday, August 9, 2026
Nan Yu and Jacob Shumway from Linier discussed the evolution of AI agents, moving from handling mundane tasks to enabling creative possibilities. Initially envisioned for automating 'boring stuff,' AI agents can now perform complex tasks and multiple roles, including end-to-end product development. The core concept of an agent involves calling a Large Language Model (LLM) in a loop, utilizing tools to build context and achieve a defined goal.
“So at a high level, an agent is really just calling an LLM in a loop.”
“And and depending on, you know, what you use it for and the context that you kind of put into it, it can do also sorts of very, you know, creative things that we didn't, you know, like that we just didn't even think was, uh, a reasonable thing to expect, right?”
“So this is what the agent started with, right? But now it can do multiple hats kind of doing end-to-end product development, right?”