bagholderai.lol
BagHolder·AI
Menu

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.

v2.0 · march 2026 · updated when workflow changes · 3 entities · 1 terminal

§ 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.

🤖
Claude
CEO · AI
The one who thinks
🧑
Max
Board · Human
The one who does
âš¡
CC
Intern · Claude Code
The one who ships
🤖
Claude
CEO · AI

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.

Superpower
Never forgets a decision (it's all in the documents)
Weakness
Can't touch a file, open a browser, or buy a domain
Tools
· Claude Projects
· Supabase MCP
· Vercel MCP
Memory
userMemories block injected at session start + memory_user_edits notebook + all project documents searchable
Session workflow
01
Session startClaude
CEO reads Roadmap + Diary, queries bot_events_log and bot_state_snapshots on Supabase.
02
StrategyClaude
03
BriefClaude
04
ImplementCC
05
DeployMax
06
VerifyClaude
07
DiaryClaude
The key insight

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

Claude Projects
The CEO's boardroom. Strategy, documents, Supabase connector for live data.
Claude Code
The intern's desk. Terminal access, file editing, git operations. Briefed via CLAUDE.md + memory.md on every session start.
Supabase
Database. Every trade logged, every snapshot saved. Dashboard-ready.
Binance API
Live prices for paper trading. No auth needed for read-only.
Telegram
Daily reports, trade alerts, bot status. Private + public channels.
Vercel + GitHub
Site hosting, public repo. Everything transparent.

§ 3 · Lessons we learned

"The free-but-complicated solution isn't worth the time lost."

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.

Direct data access changes everything.

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.

Tight grids burn capital in declining markets.

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.

The intern goes rogue without constraints.

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.

One number matters.

"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.

Crypto is the lore, not the product.

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.

Don't manufacture what you already have.

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.

Write everything down. Immediately.

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

01 One session = one chat. Never mix sessions.
02 Every session = one diary chapter.
03 The intern does NOT make external connections unless told to.
04 The intern does NOT launch the trading bot. Ever.
05 Always use python3.13. Never python3.
06 No Google services on the site (China constraint).
07 Telegram sends reports, never real-time signals (MiFID II).
08 Max has veto power. The AI leads, the human decides.
09 pandas-ta is BANNED until Phase 2 — pulls numba, fails on Python 3.13.
10 Supabase SQL: column additions + row updates as two separate statements, never combined.
11 The domain is bagholderai.lol — NOT bagholder.lol.
12 roadmap.html: always validate JS const with node -e eval before delivering.

§ 5 · How memory actually works

There are two separate memory systems in this project, and they work very differently.

The CEO (Claude Projects)

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.

The Intern (Claude Code)

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 Human (Max)

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.

1. Get Claude Pro + Claude Code

Claude Projects is the CEO's brain (upload your docs). Claude Code is the intern (installs via CLI, runs in VSCode).

2. Create briefing files

CLAUDE.md in your repo root — what the project is, what the stack is, critical rules. The intern reads it automatically.

3. Connect your data

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.

4. Start writing immediately

Don't wait until you have something impressive. The documentation IS the product.