Behind the Craft · Sunday, June 28, 2026
Jess Yan defines an AI agent as an evolution from simple prompting loops to systems with access to tools, memory, and third-party systems, necessitating components like the model, system prompt, and a 'harness' for scaffolding and control.
“So, how would you define what an agent is and what are the main components of an agent?”
“So, Man, what a loaded question. Um, so once upon a time, agents were really just prompting loops where you were just trying to get questions and responses, uh, in a loop.”
“And I think that's really evolved towards permissioning and access to third party systems, internal tooling, and sensitive data.”
“So, the harness is really what elevates us from the sort of random sampling of just tokens and and tokens out to actual actionable product.”