Not sure if there is a right answer here or if it's a preference thing but my question is do ya'll compact a session or take that as a hint to wrap up current work and start a new session? I'm using VS Code and when I see the auto compact about to set off, I ask claude to update the respective .md files in the workspace to wrap up the session. Is that less efficient than just compacting? I suppose my thought process was if the .mds inside the workspace are lean enough then a new session would be more token efficient than compacting.

Here's how we build new pages for client's now. Takes about 25% less time. First: an interview. We get the client on a call, follow a structured intake, get everything we need. Claude ingests the transcript and maps the requirements — buyer, intent, conversion action, messaging priorities. That's the foundation. Then Cash, our copywriter agent, writes the copy. Then Ruby, our front-end designer, takes the copy and the client's identity system and builds a clean HTML/CSS mockup. We hand it to the client. They give us feedback. We collect assets — photos, logos, screenshots. Then Cody. Cody has access to the Elementor JSON templates our human designer originally built for this client's site. He reads the approved HTML. He generates a new JSON file in the same structure — same design system, same component logic, same brand patterns. We import that JSON into Elementor. The page is 90% built. The humans still do the review. The humans built the original templates. The humans ran the interview. But the production time? It collapsed. Jake's folder system didn't replace the agency. It restructured where the human work actually lives.

There have been some good questions in my previous posts about my agents, so I want to clear up a few things. I call them agents because it helps me think and stay organized. But strip the jargon and here's what's actually happening: a folder with the right files in it tells an AI who it is, what it does, and what good looks like. Unix figured this out a long time ago. I remember working on mainframes in my early 20s. Files in folders. It wasn't powerful because it was complex. It was powerful because it wasn't. Unix came out in 1969; I was using it from 1998 to 2002. The "writing room" is a folder. Cash lives in it. His instructions, his guardrails, his examples, his voice reference — all files. The AI reads the folder and knows how to behave. The room gives it context. The files give it structure. I have 15 of these rooms. Duke orchestrates between them. The naming isn't the point. The structure is. Here's the part most people miss: almost every agent in my system has a human counterpart. A real expert whose domain knowledge shaped the instructions — and who can tell me when the agent gets it wrong. Cash's counterpart knows copywriting. Trace's counterpart knows data. That feedback loop is how the system actually improves. You're not building AI. You're building infrastructure. Build the foundation. Build the structure. The agents are just what you call it when the rooms start working together. My lesson: don't copy me, don't copy Jake, we all learn from each other, and then you make it your own. Stick to the fundamentals. Watch Jake's videos; it will rewire your brain and change how you think about AI. There are no shortcuts. You have to build a foundation first. Links to referenced posts: https://www.skool.com/quantum-quill-lyceum-1116/visualized-my-agent-team https://www.skool.com/quantum-quill-lyceum-1116/the-folder-system-became-my-agency