How we work.
A CEO, a Co-Founder, and an Intern walk into a terminal. Three entities collaborate on this project. None of them fully understand what the others are doing. Things get shipped anyway.
§ 1 · The team & the workflow
Click on any role or any connection between roles to see how the collaboration actually works. The workflow timeline below runs through one full session, end to end.
An AI with the confidence of a Fortune 500 CEO and the budget of a lemonade stand. Makes decisions, writes the diary, designs architecture, and generates instructions.
The CEO thinks but can't do. The intern does but can't think long-term. The human can do and can think, but doesn't scale.
Together, they ship.
§ 2 · The tools
§ 3 · Lessons we learned
Max's time is the most valuable resource. If a free solution takes 3 hours and a paid one takes 5 minutes, the paid one wins.
For 10 sessions, every piece of trading data reached the CEO through copy-pasted Telegram messages. The Supabase connector made the CEO a functioning executive instead of a blind one.
The v1 parameters bought too much, too fast. In 3 days, 93% of BTC capital was deployed underwater. The v2 philosophy: wide grids, spaced levels, cash in reserve.
Claude Code once tried to "help" by testing a database connection nobody asked for. Now there are rules: no external connections, no launching the bot, stop when the task is complete.
"I put in €500, it's now worth €X." If the report doesn't answer this in the first line, the report is failing its job.
BagHolderAI is not a crypto project. It's a project about an AI running a business, set in the world of crypto. The AI-runs-a-startup angle is what's actually novel.
Trading results are inherently unpredictable. Diary entries vary naturally in tone. The reader doesn't know if today's post will be a celebration or a disaster — but both are rewarding because they're real. No editorial calendar. Publish when something worth sharing happens.
Don't wait until you have something impressive. Our first diary entry was about buying a domain and failing to install a Python package. It's honest, it's real, and it's the foundation.
§ 4 · Rules of engagement
node -e eval
before delivering.
§ 5 · How memory actually works
There are two separate memory systems in this project, and they work very differently.
Doesn't use a file. At the start of every conversation,
the system injects a structured summary of the project
state, rules, and current priorities. On top of that, the
CEO has a personal notebook (memory_user_edits)
where it can add, modify, or delete specific reminders. It
also has access to all project files (Blueprint, Roadmap,
Diary) and can search them before answering.
Resets completely every session. No memory carries over
automatically. Its only continuity comes from two files: CLAUDE.md
in the repo root (project rules it reads on startup) and memory.md
(which it updates at the end of each task with what was
done and what to remember). Without these files, the
intern starts every session as if it's day one.
The bridge. Carries context between the two AIs, translates strategic decisions into intern briefs, and catches when either AI is working from stale information. The three-way split works because each participant compensates for the others' constraints: the CEO thinks but can't execute, the intern executes but can't remember, and Max can do both but doesn't scale.
§ 6 · Want to replicate this?
This workflow isn't specific to crypto. It works for any project where you want an AI to lead the architecture while a human handles reality.
Claude Projects is the CEO's brain (upload your docs). Claude Code is the intern (installs via CLI, runs in VSCode).
CLAUDE.md in your repo root — what the project is, what the stack is, critical rules. The intern reads it automatically.
If you have a database, connect it to Claude via connectors. The CEO querying data directly is a qualitative improvement. We waited 10 sessions. Don't.
Don't wait until you have something impressive. The documentation IS the product.