Results by cohort

Cohort A — live bot book. Closed positions executed by the trading engine. This is engine evidence, not customer outcomes: it is not what a subscriber receives, fills, or earns. The displayed PnL ratio is this window's qualifying closed-position realized USD PnL divided by verified bot balance at the window start. It is not total account return.

Cohort B — published signal-model outcomes. The product being purchased (delivered signals with a +1R target and 8-hour expiry, manual execution), settled by market-price observation. Each published signal counts once, no matter how many customers reveal it — purchasers are never counted as independent outcomes, and losing signals are never hidden.

Cohort C — historical simulations. Labeled models evaluated on historical data. Simulations are not live results and never substitute for delivered-signal evidence; every published model carries its label, fixed UTC date range, costs treatment, and sample size.

Cohort D — customer execution (future). Opted-in customer fills will appear as their own cohort. Nothing currently published is a customer return claim.

A separate, small summary of the bot's recent closed positions, shown on this page. It is engine evidence like Cohort A, but it uses a different basis, so its numbers are never comparable to the Cohort A ratio above.

Each closed position's realized PnL is expressed as a percentage of that position's own positive entry notional (not the bot balance, and not account return). The card shows the median, best and worst of those percentages, the sample size, and how many positions were positive, negative or flat. Positions are published at least 24 hours after they close.

Numbers appear only when at least 8 qualifying positions are available. Below that, this page says there is not enough evidence yet and shows no numbers. Samples under 30 positions are labeled a small sample: a snapshot, not a trend. The summary appears only here, because it is not the same measure as the figures defined elsewhere in this section; the home page carries no outcome figures. The product's own signals are measured in R (see part 4), not in percent of notional.

Every aggregate on this page names its window start, window end and as-of time, all in UTC. The as-of time is the latest qualifying close, not the end of the window. The signal-model cohort uses its own published window.

A transient endpoint failure never rewrites history: when evidence goes stale, pages fail closed to “not currently verified” instead of showing old numbers as current.

For the signal format, 1R = |entry − stop| and the delivered target is entry ± 1R. A billing WIN means the market touched the target inside the 8-hour window after entry activation (closed candles only) — a defined price-touch event, not proof that any customer filled at those prices or earned that amount.

When entry and either target or stop touch in the same closed 1-minute candle, or stop and target touch in one closed 1-minute candle after activation, the signal is AMBIGUOUS because that candle does not prove which boundary touched first. A Pro ambiguous outcome releases its four-credit hold and costs zero. Signals never activated expire CANCELLED and are refunded; activated-but-unclosed signals at expiry stay in economic analysis with an executable exit mark and never disappear as zero-return cancels.

Modeled average R is reported with its R-sample size and denominator, using the mapping WIN=+1R, LOSS=−1R, AMBIGUOUS=−1R (conservative market model, separate from the zero-credit Pro billing outcome); CANCELLED signals keep their own count and never enter R; unknown states are counted separately and excluded from the total. Rates always carry their denominators (total signals vs decided signals); a percentage without a denominator is not published.

The signal-model cohort is price-touch verification only: no trading costs are netted in it (no fees, spread, slippage, or funding subtracted at signal level). Trading costs apply to any customer execution and require a separate customer-economics analysis — they are never subtracted inside this cohort, and the cohort never implies inclusion by silence.

The $59/month subscription and credit spend are service fees, not trading costs — they are never netted into trading expectancy. A positive trading signal can still be uneconomic for a subscriber after the service fee; customer-economics analysis keeps subscription cash, credit consumption, and trading expectancy in separate lines. Current self-serve Pro terms hold four credits at reveal, consume four only on a provable TP-first win, and release the hold at zero cost on a provable SL-first loss, ambiguous first touch, or cancellation.

• Small samples carry low confidence. Bot-cohort Sharpe is unavailable until a defensible return series exists.
• Sparse and negative periods remain visible — charts show losing months with their labels rather than dropping them.
• Market-price observation cannot prove customer fills, slippage, missed entries, or capacity.
• Past performance, backtests, and shadow-mode simulations do not guarantee future results.
• Missing or stale evidence reads unavailable, never optimistic.