An example portfolio
A demonstration account started at 10,000 USD on 5 January 2026 and followed the site's proposals, week after week, with dealing fees deducted. Nothing was bought on anyone's behalf : the account is declarative, like every account on this site.
Where it ended up
Read the second figure before the first. A return on its own says nothing : in a market that falls, any decision to step aside looks brilliant. The benchmark is what turns a number into a measurement — and the drawdown says what it cost along the way.
What was decided, and when
Each proposal is shown by what it did. The reasoning behind it — how the timeframes lined up, what the flow and the positioning said — is part of the product and is available with an account.
| Date | What the proposal did |
|---|---|
| 2026-08-31 | closed LLY, MSFT |
| 2026-08-24 | closed AVGO |
| 2026-08-17 | closed GOOGL |
| 2026-08-10 | closed TRX, ADA |
| 2026-08-03 | closed AAPL, NVDA, BTC |
| 2026-07-27 | closed META, ETH |
| 2026-07-20 | closed MU, TSM, TRX |
| 2026-07-13 | |
| 2026-07-06 | closed AMD |
| 2026-06-29 | closed LLY, AAPL |
| 2026-06-22 | |
| 2026-06-15 | closed NVDA |
What this example is not
It is not a track record. These decisions were replayed on past data with a strict cut-off — each one saw only what was known at the time. But the model behind them may have been trained on that period, and no amount of care in the replay removes that. The figure shows how the mechanism behaves ; it does not demonstrate judgement.
It is one trajectory, not a sample. Thirty-five decisions that inherit from one another over a single stretch of market are one story, not thirty-five measurements. A different eight months could tell another.
Nothing here was traded. No order was ever placed, no account exists anywhere but in this database. The disclaimer at the bottom of every page applies to this one too.
