Playbook

What this system does, the process a trade flows through, the hard rules that govern it, and the honest read on whether the edge is real. This is the one-pager — start here.

The process ↓Is the edge real? ↓$10K live sleeve ↓Discipline rules ↓Out-of-paper flaws ↓

The process — one idea, six steps

Every trade idea walks through the same six steps before it reaches your phone: find it, test it, size it, send it, score it, learn from it.

1
Hunt for setups
Every few minutes, automated scanners watch ~50 AI-related stocks for unusual options buying, momentum, and pressure points.
Why it matters: You don't have to stare at screens — the system surfaces the handful worth a look.
2
Stress-test the idea
Before anything is recommended, specialist views (big-picture, company health, and the chart) argue bull-vs-bear and reach a verdict.
Why it matters: No single hot take gets through. Weak ideas die in the debate.
3
Right-size the bet
Rules cap how much money can go into any one trade, so a single bad call can't blow a hole in the account.
Why it matters: Position size is decided by math, not excitement.
4
Send a clean play card
The idea is stripped down to a simple card — what to buy, the stop, the target — and sent to your phone.
Why it matters: A 10-second decision. No jargon wall, no essay.
5
Track every call (on paper first)
Each suggestion is logged and scored as if it were real money, then reviewed after about a week.
Why it matters: We build an honest track record before risking cash — no cherry-picking the winners.
6
Keep what works, cut what doesn't
Signals that lose money over time get retired; the rest get fine-tuned from what actually happened.
Why it matters: The system sharpens itself — and nothing changes without your sign-off.

Is the edge real? (SPY baseline)

We have no formal backtest engine — we can't replay signals we never logged historically. What we cando honestly: benchmark every closed trade against whether SPY rose over its actual holding window. If our win rate beats the tape, the edge is real. If not, we're riding AI beta.· refreshed 14h 11m ago

Mostly beta, not yet proven alpha
2026-05-03 → 2026-05-29 · n=86
Our win rate
70.9%
SPY up-rate (same windows)
79.1%
Win-rate alpha
-8.2pp
Wins while SPY flat/down
10 (16.4%)

In this window SPY was up in 79.1% of our holding periods — more often than we won (70.9%). On hit-rate, our directional picking did not beat simply being long. The dollar expectancy stays positive (options leverage), but leverage amplifies both ways. The real test is a flat/down tape, and we only have 10 wins there. Treat the paper win rate as cheap until proven in a non-bull window.

Active-book expectancy (for context): +$1011.87/trade · PF 3.81 · win 69.4% (n=98). Dollar edge ≠ hit-rate edge.

$10K live sleeve

A ring-fenced $10K real-money sleeve, separate from the main $223K account, to pressure-test the system with real stakes. Real money only follows signals that clear the deploy gate.· refreshed 14h 11m ago

Status
Live · funded 2026-05-29
Funded and live. Awaiting first reported entry. Real capital may only follow signals in 'cleared for real capital' below — today that is GEX_FLIP only.
Deployed $0 · available $10,000
Hard limits
  • Max risk / trade: $1000
  • Max concurrent: 5
  • Daily loss limit: $1000
  • Pause trading if it drops to: $7500
Cleared for real capital (1)
GEX_FLIPn=65 · win 67.7% · exp $729.02 · PF 2.52 · WLB 55.6%
Blocked from real capital (12) — click to expand
UW_FLOWn=7sample n=7 < 30 (not established)
IV_RANKn=6sample n=6 < 30 (not established)
intraday_scann=3sample n=3 < 30 (not established)
MANUALn=3sample n=3 < 30 (not established)
CC_INCOMEn=3sample n=3 < 30 (not established)
earnings_5_7_AMCn=1sample n=1 < 30 (not established)
NVDA_corning_optical_halon=1sample n=1 < 30 (not established)
theta_decay_12dten=1sample n=1 < 30 (not established)
post_earnings_winner_lockn=1sample n=1 < 30 (not established)
decision_zone_loss_capn=1sample n=1 < 30 (not established)
no_recovery_signaln=1sample n=1 < 30 (not established)
CSP_INCOMEn=1sample n=1 < 30 (not established)

Discipline rules

The hard rules the system enforces — the part that matters more than any single trade.

The AI reasons, plain code executes
The AI decides which trade and why. Simple code does the math, cleans the message, and sends it. A made-up ticker physically can't reach a real order — there's a checkpoint in between.
Real money has to earn its spot
Before the $10K touches a signal, that signal must prove itself: enough trades to mean something (30+), it makes money on average, and even the cautious statistical floor still clears our bar. Paper money can try anything; real money can't.
Cut losers, bank winners — at set lines
Options you buy: sell if it's down 50%, take profit when it's up 50%. Income trades (selling options): buy them back at 50% profit — don't get greedy holding to the last day (the AAOI lesson).
A cap on fast-expiring bets
Total money in options that expire within a month is capped at $10K, kept separate from the longer-term options budget. Fast-expiring bets are the riskiest, so they get a hard ceiling.
Retire losers, but keep the receipts
A signal proven to lose money is hidden from the live views — but its past trades stay in the all-time record, so the honest scoreboard still shows what ignoring the rule would have cost.
Stale data gets flagged, never hidden
Every table shows when it last refreshed and turns amber if it's old. A frozen scanner can't quietly pretend to be a live signal.

What changes when we leave paper

The flaws that only bite with real money. Read before funding the sleeve.

Slippage is real now
Paper assumes bid/ask + commission fills. Real single-name option fills in size are worse. The 68.6% paper win rate will compress — plan for it.
We may be selling beta as skill
Over May, SPY was up in 79% of our holding windows; our win rate (71%) did NOT beat the tape on hit-rate. In a bull run, winning is cheap. The real test is a flat/down tape — we have only 10 such trades.
One thesis, one correlated bet
Everything is AI-infra. A semis/AI-capex drawdown hits every position at once. The HHI monitor exists because this is the top risk.
Thin samples on the 'best' signals
UW_FLOW/IV_RANK look spectacular at n=6–7 — too small to stake real money. Only GEX_FLIP (n=65) has earned the gate. Don't let a hot small sample pull real capital early.
Psychology isn't modeled
A paper loss costs nothing. A real −50% leg tempts you to abandon the rules. The whole point of the $10K sleeve is to feel that at survivable stakes.
One vendor, one machine
If UW's API changes or the Mac sleeps through a session, the desk goes dark. No redundancy yet.