Public paper portfolio
The 10k Portfolio Lab Experiment.
Follow a live Binance paper portfolio across 10 coins. I calculate the indicators and rules first, then use AI to interpret the setup, suggest the call, and keep the reasoning visible in public.
No login required to follow the portfolio, inspect the reasoning, and watch the mistakes and recoveries in public.
Paper balance
$9,942.00
Updated 1 minute ago
-$0.42
0.00%
apr 27–may 3
Lab protocol
- Signals are allowed in, but they do not get to act alone.
- Cash level, open exposure, and recent mistakes stay in the room.
- The public feed shows hesitation as clearly as action.
From signals to decisions
Why the lab is changing.
Signals are still useful. They just stop being enough the moment real capital, open positions, and patience enter the picture.
Isolated calls
A signal could point at a chart, but it had no view of the bankroll around it.
Structured context first
Indicators, strategy conditions, portfolio limits, and risk rules are calculated before the AI sees the setup.
Decision layer, not autopilot
The AI reads that bounded context, suggests the action and risk, and the automation places the order under my portfolio rules.
Decision desk + 10-coin universe
Click the map. Read the call.
The chart shows where a decision was logged inside the 10-coin universe. Click any decision point to open the reasoning, what it meant for the portfolio, and what levels matter next.
ADA
ADA/USD decision map
Sunday reality checks
The wall of lessons.
The lessons deserve their own archive. Each week should end with a compact summary of what happened, what changed in the portfolio, and what I learned from the process.
The machine wasn't ready.
Week 1 had zero real trades. The entire week was spent building infrastructure: AI reasoning with structured prompts, market regime detection, strategy definitions, stuck-trade recovery, stale order sweeps, and fixing AI model timeouts. The lab UI was reorganized into an open and free-first platform, and BUY/SELL operations were still being debugged by Sunday. The honest lesson: you can't trade if the platform doesn't work yet.
About the lab
This is learning in public.
The point is to make the system inspectable. You should be able to watch the portfolio, see how and why decisions are made, learn from it, and understand when I got something wrong.
If you spot wrong data or want to suggest an improvement, send feedback here.
If having your own personal lab sounds useful, leave your email on the waitlist. If enough people are interested, it is worth building.