Home Mandate Engine Method Falsification Track Record About SSS Contact

Five stages.
One continuous loop.

From a thesis the engine formed itself to a strategy that has survived 21 days of paper trading — running without pause and without instruction.

Stage 01
Generate
Signal logic against an active thesis
Stage 02
Backtest
Harness-controlled, costs and slippage applied
Stage 03
Evaluate
Mandatory gates, 252-day holdout
Stage 04
Deploy
Paper book, reconciled daily
Stage 05
Validate
Live drift against backtest
GEN — 01
Strategy Generator

Runs on Claude Haiku 4.5. It writes signal logic only — entries and exits — and never its own backtest, so no strategy can grade its own homework. 30% of each batch explores new ground rather than refining what already worked.

HRN — 02
The Harness

The engine owns the simulation: the data window, transaction costs, liquidity-aware slippage, next-bar-open fills, position sizing, and every metric computed. A strategy plugs signals in and gets a verdict back. It cannot reclaim execution.

MEM — 03
Memory

Each cycle is informed by what came before, but the record of proven edges is recomputed from results rather than rewritten as narrative — so a strategy that has been demoted cannot survive in memory as one that works.

OPT — 04
A second harness

Defined-risk options run on a separate harness rather than an extension of this one, because an options Sharpe and an equity Sharpe are not comparable numbers — which is what makes per-asset-class gating load-bearing rather than decorative. Structures are checked for bounded loss from their own payoff, so an unbounded position is rejected structurally rather than by remembering to add a rule. It produces no live positions. Generation is manual, nothing from it reaches the paper book, and its thresholds were set by measuring what noise scores — a test the first attempt did not pass.

What it has produced.

Every strategy the engine has written, grouped by the thesis behind it and the family it belongs to. Almost all of it is rejected — that is the mechanism working, not failing.

Strategy lineage across the corpus 20,612 strategies grouped by the thesis that produced them and the strategy family they belong to. 18 cleared every gate. Breakout Untagged Other Mean Reversion Thesis I Thesis II Thesis VII Thesis VI Pairs Relative Thesis VIII Thesis IX Thesis X Thesis III Volatility Regime Volatility Regime Gated… Thesis XVI Thesis XIV Thesis XI Thesis XIII Thesis XV Thesis XII Simultaneous Breakout Duality… Volume Anomaly Volatility Regime Gated… Compression Volatility Breakout… Thesis IV Thesis V
Rejected or marginal Branch with survivors 20,612 strategies · 141 paths

The gates themselves — every threshold, and why each one exists — are set out in full on the method page.