Active
Shadow strategy experiments.
Every trading decision runs a second AI pass using an alternate strategy. The shadow decision is logged but never executed. This page compares what the shadow would have done against the primary.
Experiment overview.
11 pending
Shadow agrees with primary
Running since Mar 18, 2026. Latest shadow decision: 22 minutes ago.
Per-strategy results.
How each shadow strategy performed compared to the primary.
Mean Reversion
806 decisions
Agreement
83.5%
Shadow wins
4.5%
Primary wins
5.2%
Avg score
+0.0
Symbols
3
Evaluated
803
Trend Following
538 decisions
Agreement
93.1%
Shadow wins
0.7%
Primary wins
3.2%
Avg score
+-0.0
Symbols
2
Evaluated
536
Breakout
538 decisions
Agreement
94.8%
Shadow wins
0.2%
Primary wins
1.9%
Avg score
-0.01
Symbols
2
Evaluated
536
Support/Resistance Flip
536 decisions
Agreement
91.6%
Shadow wins
0.0%
Primary wins
4.9%
Avg score
+-0.0
Symbols
2
Evaluated
534
ADX Trend Strength
269 decisions
Agreement
89.6%
Shadow wins
2.2%
Primary wins
6.0%
Avg score
-0.01
Symbols
1
Evaluated
267
Per-symbol breakdown.
Shadow experiment results for each coin in the universe.
| Symbol | Decisions | Evaluated | Agreement | Shadow Win Rate |
|---|---|---|---|---|
| SOL | 270 | 269 | 94.1% | 0.0% |
| TRX | 269 | 268 | 70.3% | 9.3% |
| ETH | 269 | 268 | 92.6% | 0.7% |
| DOGE | 269 | 267 | 89.6% | 2.2% |
| BTC | 269 | 268 | 93.7% | 0.7% |
| XRP | 269 | 268 | 84.4% | 2.6% |
| LTC | 268 | 267 | 95.5% | 0.0% |
| ADA | 268 | 267 | 87.7% | 0.0% |
| BCH | 268 | 267 | 95.9% | 1.5% |
| BNB | 268 | 267 | 95.5% | 0.4% |
Recent shadow decisions.
The latest shadow decisions and how they compare to the primary call.
DOGE
22 minutes ago
HOLD
vs
HOLD
Agree
ETH
24 minutes ago
HOLD
vs
HOLD
Agree
XRP
43 minutes ago
HOLD
vs
HOLD
Agree
BTC
about 1 hour ago
HOLD
vs
HOLD
Agree
TRX
about 1 hour ago
HOLD
vs
HOLD
Agree
LTC
about 1 hour ago
HOLD
vs
HOLD
Agree
SOL
about 1 hour ago
HOLD
vs
HOLD
Agree
ADA
about 2 hours ago
HOLD
vs
HOLD
Agree
BCH
about 2 hours ago
HOLD
vs
HOLD
Agree
BNB
about 3 hours ago
HOLD
vs
HOLD
Agree
DOGE
about 4 hours ago
HOLD
vs
HOLD
Agree
ETH
about 4 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
XRP
about 5 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
BTC
about 5 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
TRX
about 5 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
LTC
about 5 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
SOL
about 5 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
ADA
about 6 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
BCH
about 6 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
BNB
about 7 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
DOGE
about 8 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
ETH
about 8 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
XRP
about 9 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
BTC
about 9 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
TRX
about 9 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
LTC
about 9 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
SOL
about 9 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
ADA
about 10 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
BCH
about 10 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
BNB
about 11 hours ago
HOLD
vs
HOLD
Agree
Score: 0.0
How shadow testing works.
Every trade decision runs the AI twice: once with the primary strategy, and once with a shadow strategy. Only the primary is executed. The shadow is scored against actual price movement.
Two decisions, one trade.
The shadow strategy runs in a background thread at the same time as the primary. It sees the same market data, indicators, and risk parameters — only the strategy lens is different.
Shadow never trades.
The shadow decision is stored alongside the primary but never submitted to the broker. It exists purely for comparison and learning.
Evaluated against price.
After 4 hours, the shadow decision is scored against actual price movement. A BUY that preceded a price increase scores positively. The evaluation is automatic and objective.
Keep following the experiment
The point is to make the lab 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.
This is a public paper portfolio. Past performance does not guarantee future results. Hugo's Trading Lab publishes rules-based analysis with AI-assisted decision summaries for informational purposes only, not financial advice.