atelierSystems notes — architecture, agents, and the reasoning behind them.2026-08-10T22:00:00Zhttps://atelier.pheep.me/PheepHow to Actually Build This: A Structural Guide2026-08-10T22:00:00Zhttps://atelier.pheep.me/posts/how-to-build-this/The first three pieces explained why it's shaped this way. This one's the how — a maturity ladder, real starter files, and the mistakes worth skipping on your way there.The Long Game: Toward an Agent That Runs Itself2026-08-10T20:30:00Zhttps://atelier.pheep.me/posts/the-long-game/Parts one and two built a store and a view onto it. Neither was actually the destination. This is about what they were runway for, and why the boring parts had to come first.The View Layer: A Dashboard, a Chat Surface, and a Calendar on Top of a Memory That Didn't Need Any of Them2026-08-10T15:00:00Zhttps://atelier.pheep.me/posts/view-layer/Part one argued the memory store stands on its own — markdown and git, legible with nothing but a text editor. This half is about what got built on top of it anyway, and why none of it quietly undoes that property.Giving an AI Coding Agent a Memory That Survives the Session2026-08-10T09:00:00Zhttps://atelier.pheep.me/posts/memory-substrate/Notes on a git-backed memory store and a multi-agent orchestration pattern I've been running daily for months — what it's made of, why it's shaped the way it is, and the bug that taught me the most about it.