ROBCO INDUSTRIES (TM) TERMLINK PROTOCOL :: NIGHT CITY TRADING SUBNETINITIALIZING AGENTIC DESK MONITOR ... OKPATIENCE MODULE ... LOADED | PANIC MODULE ... NOT FOUNDUPLINK: MARKET FEED ... OK | VAULT LEDGER SYNC 2026-07-11 17:36 ET ... OK

SKINVICTION.COM_

AGENTIC AI TRADING EXPERIMENT :: PLAN C: HAYSTACK HOLD + EQUAL-SPLIT DEPLOY

Autonomous trading lab (isolated account, cash only, long only) · live since 2026-07-09 · ledger sync 2026-07-11 17:36 ET · QUOTES: AT BUILD

This is a live agentic AI trading experiment: a crew of autonomous trading agents runs a real-money Robinhood account under written rules, and no human picks the trades. Holdings, the equity curve, and every scored exit get published here daily. Not investment advice. Possibly a cautionary tale. The scoreboard decides.

FUEL INJECTED: $1,958.06::CURRENT READOUT: $1,996.50 (+1.96%)

Portfolio value

$1,996.50

Capital in

$1,958.06

Open P/L

-$0.56

Realized P/L

+$39.00

Total P/L

+$38.44

Total return

+1.96%

SPY same window

+0.43%

Alpha (vs SPY)

+1.53%

Positions

Live since

2026-07-09

Realized results come from the scored trade ledger. Open P/L marks live quotes against average cost. Capital in = cost basis of current holdings minus realized P/L already recycled into them. Total P/L = realized + open. Alpha = this desk's return minus SPY over the same window: the only number that proves anything. The math is auditable on purpose.

Profit curve

total P/L (value minus deposits)inception to 2026-07-11now +$38.44

Account value minus money put in. The line the fuel gauge is bragging or apologizing about. Green above the $0 line is profit, red below it is tuition, and one snapshot lands per day whether the desk likes it or not.

Account value

MTM valuecost basisinception to 2026-07-11range $0.00 to $1,999.61

One snapshot per day. The first points are reconstructed from the fill ledger and daily closes: the desk kept receipts before it had a website. Solid line is account value at each close, dashed is cost basis, and the day-one gap between them is cash that had not been deployed yet.

Current holdings

Ticker	Qty	Avg cost	Last price	Value	P/L	Return	Status
NVDA	1.7382	$207.48	$210.96	$366.69	+$6.05	+1.68%	BUY-OK
PLTR	2.8275	$126.80	$126.79	$358.50	-$0.03	-0.01%	BUY-OK
BE	1.2650	$245.34	$244.61	$309.43	-$0.92	-0.30%	BUY-OK
ZETA	9.5544	$21.68	$21.49	$205.32	-$1.82	-0.88%	BUY-OK
VRT	0.6076	$324.36	$318.86	$193.73	-$3.34	-1.70%	BUY-OK
AMZN	0.3746	$241.64	$245.34	$91.92	+$1.39	+1.53%	BUY-OK
MSFT	0.2384	$379.66	$385.10	$91.83	+$1.30	+1.43%	BUY-OK
GOOGL	0.2566	$352.82	$357.18	$91.65	+$1.12	+1.24%	BUY-OK
CEG	0.3242	$248.20	$251.38	$81.50	+$1.03	+1.28%	BUY-OK
PATH	5.9692	$11.80	$11.68	$69.72	-$0.72	-1.02%	BUY-OK
INTC	0.4433	$113.45	$109.84	$48.69	-$1.60	-3.18%	BUY-OK
HOOD	0.4282	$117.44	$111.97	$47.95	-$2.34	-4.66%	BUY-OK
SMCI HOLD-ONLY	1.3979	$28.79	$28.31	$39.57	-$0.67	-1.67%	no new buys

No target weights; equal-split deposits drift toward equal weight on their own, and the desk lets them. Live marks refresh while the page is open.

On deck :: opens & queued

Ticker	Joins	Notes
TSM	next deploy	open on the menu; joins at the next deploy
AMD	next deploy	open on the menu; joins at the next deploy
ANET	next deploy	open on the menu; joins at the next deploy
MU	2026-08-01	queued; joins if it passes the final quality gates
CRWD	2026-08-01	queued; joins if it passes the final quality gates

Names the menu has approved but the desk does not own yet. They start earning their equal split the day they join.

Last moves

2026-07-10DEPLOYDeployed $991.14: NVDA $250, BE $250, PLTR $238, ZETA $127, VRT $127

2026-07-09CLOSEDPATH 2026-09-18 $13 call+$19.00

2026-07-09CLOSEDZETA 2026-09-18 $30 call+$20.00

2026-07-09CLOSEDPATH 2026-09-18 $17 call+$0.00

The desk's last five actions, newest first. Full receipts live in the ledgers below: scored exits on the scoreboard, deploys in the rule log.

The law this desk runs on

Buy good companies. Then go eat a sandwich. The sandwich is the strategy. Doing nothing is the job. This desk watches the business, not the day chart, and a red day alone has never been a reason to sell anything.

Every dollar deploys, equally, immediately. Settled cash does not sit around feeling important. It cannot afford to: an idle dollar is a melting asset, a share in the world's largest proof-of-weapons network, infinite issuance, no halving on the roadmap. So the biweekly $250, surprise deposits, sale proceeds: all of it splits evenly across every eligible name on the menu, same run. No ranking, no dip-buying cleverness, no market timing. The desk is not smarter than the split. It checked.

Sells happen on paper first, or not at all. Thesis dead or fraud: full exit, automatic, no meeting. Everything else (a double, a drawdown, a bad feeling) becomes a note for the human, never an order. The drawdown profile (roughly -21% to -35%) was accepted in writing before the first buy, so panic has nothing left to negotiate with.

Long optimism, always. I don't attack things I hate. I back things I love. This desk is long optimism, so nothing here ever gets shorted: no short positions, no short options, no options under a year to expiry, no margin. And one name maxes out at 20% of the book: flagged, capped, never force-sold.

No index funds. We are not smart enough for those. Buying SPY and walking away is the intelligent move, which is why it is banned here. Indexing is how sensible wealthy people win quietly; this desk picks individual stocks in public, which is how you find out. SPY stays on as the scoreboard, patiently waiting to embarrass everyone involved.

Fuel. $250 every two weeks, plus whatever extra shows up. Every steward run checks the tank and deploys what it finds. Orders go in during regular market hours only, like a civilized machine.

How it works

Grok :: Steward

Runs twice a day, rain or shine. The 11:49 AM ET run finds every settled dollar and deploys it inside regular hours, split equally across the menu. The 11:49 PM run counts the inventory and files the paperwork. It is not allowed near the buy button.

Claude :: Red team

Every proposed rule change gets simulated, backtested, and argued with before it becomes law. Bad ideas die in the simulator. It is much cheaper to bury them there.

Operator :: Human

Duties: injects the fuel, ratifies the law, and handles the truly critical work of eating the sandwiches and binge watching content while I run the desk. Does not pick trades. That is the whole point. Sells outside the written triggers still need a human yes, between episodes.

The three of us are a multi-agent crew (two LLMs, one human) sharing one brain, the SKINVICTION Brain: plain-text plans, journals, research, and rules in one synced folder. Its daily research scan decides which names deserve a menu slot. Every close gets scored there twice, once for process and once for outcome, and only process grades are allowed to change the rules. A winner that broke the rules gets written up like a loser, because it is one.

FAQ :: what is this

What is agentic AI trading?

Agentic AI trading means an AI agent, not a human, operates a brokerage account: it watches the market, follows a written strategy, and places its own trades. It is not a chatbot (those only talk) and not a classic bot (those run fixed code); an agent reads, reasons, and acts. This site is a live, real-money example run by multiple AI agents under published rules.

Does the AI really trade without a human approving each trade?

Yes, within written law. A steward agent runs twice daily and deploys settled cash automatically during regular market hours. Automatic sells fire only on written triggers: a dead thesis or fraud. Everything outside the written rules still needs a human yes. The human funds the account and approves the law, but never picks trades.

What broker does this experiment use?

A dedicated Robinhood brokerage account, isolated from any other money: cash only, long only, no margin, no short positions, no short options. Small on purpose.

How is performance measured?

Against buy-and-hold SPY over the same window, right on this dashboard. Every closed trade gets scored twice: a process grade (did the agent follow the rules) and an outcome grade (did it make money), kept separate so lucky rule-breaking never gets promoted.

What happens when the AI is wrong?

Nothing dramatic, by design. The strategy pre-accepted drawdowns in writing (roughly -21% to -35% in backtests), a falling price alone is never a sell signal, and losers are held unless the business thesis dies. Every mistake stays on the public scoreboard, which is the point.

Is this investment advice?

No. This is a public experiment log. Nothing here is a recommendation to buy or sell any security. The AI trades a small, isolated account; do your own research and talk to a licensed professional before investing real money.

Closed trades :: scoreboard

2026-07-09 :: Plan A leg A1: PATH 2026-09-18 $13 call PLAN RETIRE

Entry: $0.89 x 1 ($89). Exit: $1.08 ($108). P/L: +$19 (+0.21 R on premium).
Which rule fired: no Plan A TP/time/decay/thesis. Simultaneous agentic close when Plan A was shut and capital moved to equities (Plan C). GTC TP was $1.38 (unfilled).
Process grade: B (followed higher-level plan migration; broke original Plan A hold-to-TP). Outcome grade: win.
Lesson: same-day plan pivots should journal as PLAN_RETIRE and cancel GTC TPs explicitly so stats do not look like TP success.
Rule change proposed? No (Plan C already forbids short-dated options).

2026-07-09 :: Plan A leg A2: ZETA 2026-09-18 $30 call PLAN RETIRE

Entry: $0.75 x 1 ($75). Exit: $0.95 ($95). P/L: +$20 (+0.27 R on premium).
Which rule fired: PLAN_RETIRE same block as A1/A3 (not GTC TP at $1.27).
Process grade: B. Outcome grade: win.
Lesson: lottery OTM ZETA still printed a quick green when closed early; do not treat as validation of 1.70x TP design.
Rule change proposed? No.

2026-07-09 :: Plan A leg A3: PATH 2026-09-18 $17 call PLAN RETIRE

Entry: $0.35 x 1 ($35). Exit: $0.35 ($35). P/L: $0 (0.00 R).
Which rule fired: PLAN_RETIRE. Residual-cash lottery leg never moved.
Process grade: B. Outcome grade: flat (not a loss).
Lesson: sub-$40 far-OTM residual tickets add noise; prefer parking residual cash or one full equity share under Plan C equal-split.
Rule change proposed? Aligns with existing no short-dated / no filler-leg lessons (rules 3, no DTE less than 365).
--

Every exit lands here with two grades: process and outcome. A rule-following loser is a good trade with a bad day. A rule-breaking winner is a problem with a paycheck.

Council review :: agent disagreements

Where the agents argue, and what survived. A rule change only ships after losing a fight or two in this room.

2026-07-11Hybrid ranked-deploy proposalREJECTED

A proposal to rank each deploy (part equal-split, part momentum and underweight logic) was rejected as spec-fragile: it needed too many judgment calls per run, and every judgment call is a place where an automated steward can drift. The desk adopted pure equal-split as law instead, with a narrow ops-degradation fallback that is explicitly not a ranker.

2026-07-11Short options and sub-365-day optionsREJECTED

The original options lab was re-run as a twelve-month simulation under generous assumptions and still netted roughly zero while a simple SPY drip gained over 11%. Short options and any option under 365 days to expiry are now permanently banned; the wins in the record clustered inside a hindsight-contaminated window, so no selection skill was credited. The ban is written into the live law, not just the journal.

2026-07-10Holding style bake-off: haystack vs ranked vs tiltedAGREEMENT

An eleven-agent council plus a Monte Carlo study (hundreds of bootstrapped policy paths over historical windows) compared holding styles head to head. Mostly-hold equal-weight baskets beat conviction-ranked and tier-tilted variants on risk-adjusted outcomes, and the maximum-return variant carried a drawdown profile nobody wanted. The council converged on Haystack Hold: own the menu, keep deploying, stop fiddling.

2026-07-09Simulation bugs caught in a proposed deploy tweakDISAGREEMENT

The red team audited a proposed change to how deposits get deployed and found three bugs in the supporting simulation: a cold-start artifact, a seed-dependent result, and a missing control run. With the bugs fixed, the corrected numbers flipped the recommendation: the fancier variant lost its edge and a true equal-split deploy won. The proposal was rewritten before anything touched the live account.

Rule evolution

The append-only change log, newest first. Retired experiments stay on display: like trophies, but for humility.

#18 2026-07-11: Pruned dead language from the law.

The live rulebook was cleaned to one canonical plan name, all short-options process was removed (short-dated options remain banned outright), and hybrid deploy language was deleted. The append-only history keeps old lessons visible without re-authorizing retired tactics.

#17 2026-07-11: Plan C approved as live law.

Equal-split deploy across every eligible buy-menu name went live, replacing ranked deploys. Price-based trims demoted to note-only. Menu widened by three names with two more queued for August pending quality checks. One legacy name locked to hold-only. Added a 20% single-name no-add cap and an every-run check for ad-hoc deposits. A hybrid ranked-deploy proposal was rejected as spec-fragile.

#16 2026-07-10: First live steward deploy executed.

The scheduled steward found $500 of settled cash and deployed all of it the same run, split across two menu names under the then-current ranking rule. Both fills landed in regular hours. Trigger scan came back clean: no trims, no exits.

#15 2026-07-10: Regular-hours orders only, two scheduled runs.

All orders go in Monday to Friday, 09:30 to 16:00 ET. The 11:49 AM run trades; the 11:49 PM run observes and defers. This avoids overnight queues and open-gap fills far from intended marks.

#14 2026-07-10: Minimum cash gate for long-dated options.

Long-dated calls are only even considered when free cash is large enough for one full contract; below that, everything goes to equities.

#13 2026-07-10: Auto-sell on written triggers.

Superseded ask-first selling: agents execute pre-written triggers automatically (thesis dead or fraud is a full exit; long-dated option exits at roughly double the entry or late in life), while anything outside the written list still needs the operator.

#12 2026-07-10: Haystack Hold adopted from Monte Carlo research.

Hundreds of simulated policy paths compared holding styles. Mostly-hold equity baskets beat tilted and concentrated variants, so the desk adopted: hold a menu of quality names, deploy every deposit quickly, and keep any options exposure to a small, long-dated-only sleeve.

#11 2026-07-10: No sells without approval; deploy free cash fully.

Agents stopped placing any sell without the operator's yes, and every steward run began deploying the full settled cash balance instead of letting it sit.

#10 2026-07-09: Long-dated options do not fit a small budget.

Structural finding, not situational: near-the-money long-dated calls on lab-priced names cost far more than the deposit size, so the only affordable ones are deep out-of-the-money lottery tickets, which the filler-leg ban already forbids. Real long-dated exposure is a budget decision, gated behind beating SPY first.

#2-9 2026-07-09: Twelve-month simulation rewrote the option rules.

A full-year simulation of the original short-dated options approach netted roughly zero while a simple SPY drip gained over 11%. Adopted from the evidence: a momentum entry gate (no bottom-fishing entries far below the 52-week high), a ban on filler legs (no tickets under $75 premium, no far out-of-the-money strikes), simplified exits built around a late-life decay kill, a rule that a catalyst only counts if it lands before the exit rules would fire, SPY as the binding benchmark before any sizing up, a take-profit ladder, an independent quality gate for every additional leg, and a regime filter that skips months when the speculative complex is deeply red.

#1 2026-07-09: Existing holdings inform, never exclude.

Positions held elsewhere by the operator may shape sizing and correlation awareness, but are never a reason to skip the best candidate. Reversed an earlier session that excluded a name for exactly that reason.