Skip to content
Trader Console

Opening 1 December 2026 · paper accounts first

The model proposes.Your rules decide.

Trader Console researches markets, screens for setups and backtests strategies in one conversation. Every order it wants to place is checked against limits you set — and it has no way to raise them.

SOL/USDTLong
decision · draft

Proposed Open 1.4% of equity, stop 3.1% below entry

  • Position size1.4% of equity · limit 2%
  • Loss today−0.8% · halts at −3%
  • Open positions4 · limit 5
  • Leverage3× requested · limit 2×

Refused before the venue saw it

The order was never sent. The model was told which check failed, and may propose again inside the limit.

A proposed long in SOL/USDT, refused by 1 of 4 risk checks before reaching the venue.
  • MEXCSpot and futures, live orders
  • BinanceMarket data and derivatives
  • Freedom24Equities
  • PaperThe same engine, no money

Every account starts in paper. Live keys are added by you, and the console can trade only the accounts you connect.

One conversation, the whole workflow

The parts a retail trader normally runs across five tabs and a spreadsheet, joined by a system that remembers what it decided and why.

Ask, and it researches

Candles, indicators, order flow, funding and open interest — pulled live and read back as an argument you can disagree with, not a verdict.

Screeners that run without you

Set the conditions once; they run on a schedule and tell you when something crosses. Every firing is kept, so you can see what the screen actually caught.

Backtest before you believe

Walk-forward runs with a leakage check, because a strategy that has read the future backtests beautifully and loses money.

Strategies earn promotion

Nothing goes live on a good backtest alone. A strategy trades on paper first, and the promotion to real money is a decision you sign.

paper → live

A risk engine above the model

Position size, daily loss, exposure and leverage are evaluated by code the model cannot call, edit or talk around.

every order

Execution you can audit

Every fill traces back to the decision that caused it — the question you asked, the proposal, the checks that ran, the order id at the venue.

Where the model stops and the code starts

Four steps, and the boundary sits in the middle of them. This is the whole security argument of the product, so it is on the front page rather than in a whitepaper.

  1. 01

    You ask

    In plain language: find me a setup, size this position, tell me what changed in my book overnight.

  2. 02

    The model proposes

    It reads market data and your positions, and produces a proposal with its reasoning attached. A proposal is text. It moves nothing.

  3. 03

    The gate checks

    A separate service evaluates the proposal against your limits and signs the result. It runs on rules, not on judgement, and the model has no route to it other than being checked by it.

  4. 04

    You confirm, then it executes

    Live orders wait for your confirmation. Once you allow automatic execution for a strategy, the gate still runs on every single order — that permission widens what may pass, never what is checked.

What it cannot do

A capability list is easy to write. This is the other one — the things the architecture makes impossible, which is what actually protects an account.

  • Raise its own limits. Limits live in a service the model can only be judged by.
  • Withdraw funds or move money between accounts. There is no such call to make.
  • Trade an account you have not connected, or a venue you have not enabled.
  • Hide a refusal. Every blocked order is written down with the check that stopped it.
  • Promise a return. There is no number on this site we would not show you the trades behind.

The questions worth asking first

Does the AI trade my account by itself?

Only if you turn that on, per strategy, after it has traded on paper. By default it proposes and waits. Either way every order is checked by the risk gate first — automation changes who confirms, not whether the check runs.

Where do my exchange keys live?

In a secrets store keyed to your account, and they are used by the execution service alone. They are never handed to the model, never printed into a chat, and never shared with another customer’s process.

What happens on a losing day?

You set a daily loss limit. When the account reaches it, the gate stops approving new entries for the rest of the day — including the model’s. Reducing or closing a position stays allowed, because blocking an exit is how a bad day becomes a bad month.

Can I see why it did something?

Yes, and this is the part most tools skip. Each order carries the decision that produced it: what you asked, what the model proposed, which checks ran, what the venue answered.

Is this a signal service?

No. There is no basket of tips and no copy trading. It is your account, your limits and your confirmations — the model is research and drafting, not a manager.

Start on paper. Nothing to lose by looking.

A paper account runs the whole system — the same research, the same screeners, the same risk gate — against live market data and no money.