What The AI Trader Is
An AI Trader is an autonomous trader you attach to your desk — the signals you already scan with. It reads the same live signal data you see on the board, interprets it through a strategy you author in plain English, and for each setup that qualifies it writes a full trade plan: entry, stop, laddered targets, scale-outs, and an invalidation condition. It then manages the position turn by turn, logs its reasoning as it goes, and writes a journal entry when the trade closes. Everything runs on the simulated paper rail — no real orders, no custody of your funds.
Create A Trader
Traders live on the desk rail on the right side of the cockpit. Open it and choose Compose a trader.
- Signal: the composite signal the trader scores its board with — the same signal, settings, and interval you see.
- Persona: Tape Reader, Scalper, or Risk Officer — the temperament it reasons with.
- Mode: Analyst reads the board and narrates without taking positions; Paper opens and manages simulated positions.
- Cadence: how often it takes a turn — 1m, 5m, 15m, 1h, or 4h.
- Paper sizing: the per-order size in dollars, the maximum number of open positions, and the minimum conviction it needs before acting.
Write The Strategy In Plain English
The Strategy section of the composer is where you tell the trader how to trade. Describe the setups you would take, how to enter and manage them, and what to avoid — then choose Generate strategy. The AI drafts a structured strategy phrased in your desk's own signals: a one-line summary, the setups it will look for, and guidance for planning, management, sizing, and no-trade conditions. Type a refinement and regenerate to evolve it. A trader needs a strategy before it can run autonomously.
- Example: "Fade funding extremes on liquid majors only. Enter on a book flip, stop beyond the sweep, scale out in thirds. Stand down when spreads blow out."
- The strategy is yours — composed from your words and your signals, not a downloaded template.
- Setups reference the signals actually on your desk, so editing the desk changes what the trader can trade.
The Trader Loop
Once enabled with a strategy, the trader runs around the clock on VYX servers — no browser or open tab required. Every turn on its cadence it works like a discretionary trader:
- Perceive: score the board with your signal — the same rows and values your heatmap shows.
- Scan: read the board through the strategy. No qualifying setup means "nothing here" and the turn ends — no forced trades, no churn.
- Plan: for each fresh setup, author a trade plan — direction, entry, stop, target ladder, scale-outs, invalidation, and size within your caps.
- Manage: for each open position, re-evaluate against fresh data — hold, move the stop, take a partial, add, tighten to break-even, or exit if the thesis breaks.
- Record: append the turn's reasoning to the decision log and the trade's running thought-log.
- Reflect: when a trade closes, write a journal entry and update what it has learned.
Trade Plans
A plan is the unit of a trade — one open plan per symbol per trader, carried as living state from proposal to close.
- A thesis in the strategy's terms: why this setup, right now.
- An entry (market, limit, or trigger), a required stop, and a ladder of targets with per-level scale-out sizes.
- An invalidation condition that exits the trade early when the thesis breaks — before the stop is hit.
- The AI proposes; deterministic guardrails validate. Plans are checked against price sanity and your sizing caps, and anything out of bounds is clamped or rejected. The strategy's words can never override your limits.
- Stops, targets, and trailing are enforced mechanically each turn — the bookkeeping never depends on the AI.
The Logbook
Every trader is fully auditable. Open its Logbook from the book icon on the trader card to see what it is doing and why.
- The forward record: the simulated equity curve built only from what the trader actually did.
- The decision log: one entry per turn — what it saw, why, what it did, and the outcome — hash-chained so the history is tamper-evident.
- The thought-log: the server loop's per-turn reasoning while a trade is open, threaded to the trade.
- The journal: a reflection per closed trade — what the setup was, how it played out, the R outcome, and the lesson.
Learnings
The strategy keeps a short, curated list of one-line lessons the trader has drawn from its own closed trades — "thin books stopped me out; require a liquidity floor." After each journal entry the list is updated: repeated evidence reinforces an existing lesson instead of duplicating it, stale lessons are dropped, and the list is hard-capped so it stays sharp. The trader rereads its learnings every turn before it plans. Changes to the strategy core or your desk are never self-applied — those always wait for you.
Simulated By Design
- The autonomous trader trades the paper rail only — simulated fills, simulated PnL, never a real order.
- Running a trader 24/7 server-side requires a Pro or Elite plan; composing traders and strategies is available in the cockpit.
- Each account has a daily AI-turn budget, so a busy board cannot run up unbounded usage.
- Trader decisions are also readable programmatically via the API and MCP server.
- A simulated track record is a research instrument, not a promise of returns. Nothing here is financial advice.