This page explains the architecture behind the SKINVICTION live dashboard: an autonomous trading desk where AI agents run a real brokerage account under written rules, with no human picking trades. The design goal is boring on purpose. Every part of the system exists to remove improvisation, because improvisation is how AI traders quietly destroy themselves.
The crew: three roles, one account
The desk is a multi-agent system with a strict division of labor.
- The steward is the only agent that touches the brokerage account. It runs twice a day on a schedule. The midday run, during regular market hours, checks for settled cash and deploys all of it according to the rules. The late-night run marks positions to market, scouts for news on the holdings, and writes notes, but places no orders. Orders happen in regular trading hours only.
- The red team never trades. Its job is to attack proposals. Any suggested change to the rules gets simulated, backtested, and adversarially reviewed before it can become law. Ideas that survive get adopted; ideas that fail die in the sim instead of in the account. The dashboard's council review section shows these fights and their verdicts in public.
- The human operator approves the rules and adds deposits. That is the whole job. The operator does not select stocks, time entries, or override the plan on feelings. One safety valve runs the other way: any sell outside the written triggers requires an explicit human yes.
The shared memory: the SKINVICTION Brain
The agents do not share a database or an API. They share a folder of plain-text markdown files called the SKINVICTION Brain: the trading plan, a scored journal of every closed trade, research notes, and the rule book itself. Each agent reads the current state before acting and writes its results back for the next one. Plain text turns out to be the right substrate for a multi-agent system: it is diffable, auditable, and no agent can hide a decision inside a binary blob. The buy menu itself is curated from this layer's daily research scan, which decides which companies deserve a slot.
The law: how decisions are constrained
The strategy is deliberately simple, because simple rules are checkable rules.
- Equal-split deployment. Every deposit that settles (a biweekly contribution plus any ad-hoc additions) is deployed in full, split equally across all eligible names on the buy menu. No ranking, no dip-buying logic, no momentum scoring, no market timing. The desk converges toward equal weight over time instead of forcing it.
- Default is hold. Price falling is never, by itself, a reason to sell. The expected drawdown profile (roughly -21% to -35% in backtests) was accepted in writing before the first dollar deployed, so a drawdown arriving is the plan working, not the plan failing.
- Automatic exits on written triggers only. The steward can sell without asking a human in exactly two situations: the investment thesis is dead, or credible evidence of fraud appears. Profit milestones and drawdown flags generate notes for review, never automatic sells.
- Hard bans. No margin, no shorting, no short options, no options under a year to expiry, and no index funds inside the account (the S&P 500 is the scoreboard, not a holding). A single position that grows past 20% of the account gets flagged and stops receiving new buys, but is never force-sold.
The feedback loop: scoring every exit
When a position closes, it gets journaled with two separate grades. The process grade asks whether the rules were followed. The outcome grade asks whether the trade made money. Only process grades are allowed to change the rules. A rule-following loser is a good trade with a bad outcome; a rule-breaking winner just got lucky, and rewarding it would train the system toward improvisation. This separation is the desk's core defense against the drift that erodes most AI trading experiments.
Why publish all of it?
Because unaudited AI trading results are worthless. The dashboard shows the live holdings, cost basis, profit and loss per position, the equity curve against SPY over the same window, every closed trade, and every rule change with the argument that produced it. If the experiment underperforms, that stays public too. The value of the project is the data, not the bragging rights.
Nothing on this page or this site is investment advice. This is a public experiment log for a small, isolated account. Do your own research and consult a licensed professional before making investment decisions.