Methodology

SECTION 01

Principles

Every robot is a single documented strategy: fixed rules for entries, exits, and risk. If a claim about a robot can't be tested, we don't publish it. Where live data exists, it is shown next to the test, never instead of it.

SECTION 02

From library to featured portfolio

The research library currently holds 150+ strategies, each tested under the same reporting contract. Published strategies ship as deployable robots — currently 161 robots in the library — and curated, low-correlation baskets of them form the portfolios. The portfolio featured on the landing page is selected by the current catalogue resolver; it is not an owner-designated flagship until a canonical portfolio ID and constituent manifest are published.

SECTION 03

The backtest contract

Every backtest report follows a fixed 57-field contract: the same metrics, in the same order, for every robot — returns, drawdown, trade statistics, and test conditions. That makes results comparable across the whole catalog and makes cherry-picking visible.

SECTION 04

Spec sheets

Each robot ships with a public spec sheet you can read before you pay: the strategy logic (entries, exits, risk rules), the instrument and timeframe it trades, and the published requirements for running it — platform, account type, and setup instructions.

SECTION 05

Limitations we disclose

Backtest results are hypothetical. They are prepared with the benefit of hindsight and do not reflect actual trading or the impact of real market liquidity, slippage, requotes, or broker execution quality. No representation is made that any account will achieve results similar to those shown.

Past performance — live, backtested, or simulated — is not indicative of future results. The full disclosure is on the Risk Disclosure page and in Terms of Service §9.

SECTION 06

Questions