Where every number in our engine comes from.

Three external systems feed every decision the engine makes. None are proprietary; the same data is available to anyone with API access.

In V6, selection is now the BULLISH-only gate plus a delta edge-rank to the top ~50 bullish setups. The old moneyness, open-interest, volume, DTE, and V/OI filters were removed on 2026-06-04 — they choked real winners on stale scan-time data. The ~50 bullish setups that clear the enrichment bar below and the two safety rails go into the tournament; the engine does its discriminating there, not with a filter cascade. (Bid/ask spread is no longer shown or gated — this Polygon data tier serves no live options quotes, so there is no real spread to display.)

Once the enriched pool clears the two safety rails — on a busy day that's around 50 bullish candidates — one pick is chosen by a randomized bracket tournament. Not a scoring formula, not a human.

• Three independent brackets. Each one shuffles the ~50-name bullish pool into a fresh random order, then reduces it in batches of ≤10: an LLM (Gemini) reads each batch and advances the top 2, round after round, until one winner remains (≈50 → 10 → 1 per bracket).
• Consensus vote. The three bracket winners are compared. 3/3 agreement → high confidence, 2/3 → medium, 1/3 → low. The consensus ticker is the pick.
• Dead-simple prompt. Each batch call gets one instruction — make money buying a single option and sell it for a profit within three days — plus the daily report and a per-contract JSON. No memory, no rubric, no composite weights.
• Fail-closed. Any error — a timeout, a pick outside the eligible set, an all-leakage day — produces no email and a no-trade day. There is no fallback path; tournament uptime is the only SLO.

Every candidate is leakage-checked before it can enter a bracket: the judge never sees anything that wasn't known at scan time.

Every pick ships with the same execution rules, and they have not changed across strategy versions. The bracket isn't a guess — it came out of a sweep across thousands of historical signals where a −60/+80/3-day envelope was the highest-EV configuration tested.

The full pipeline is open-architecture. Every artifact is auditable.

• Forward paper-trading ledger — every entry, exit, and outcome lives in BigQuery. The same row is rendered into the public scorecard.
• Decision trail — every change to the strategy (V6 today, and its predecessors back to V3) ships with a dated decision document explaining the rationale and the evidence.
• Trace logging — enrichment, the tournament judge, and overnight-report-generator each write structured trace rows so a downstream auditor can reconstruct any specific morning's reasoning end-to-end, including every bracket round.