Platform · Build

Strategy Builder

Draw your rules on a canvas, or just describe them in plain English. Either way you end up with a strategy the platform can test, trade and grade like any other.

What you get
Your rules, not a preset

Entries, exits, stops, targets, filters, sizing — the things you already think in.

Plain English works

Describe the setup and the canvas fills in. Adjust anything it got wrong.

One shape, everywhere

What you build is what gets backtested, papered and deployed. No re-implementation between steps, so no drift.

Whatever you build here is tested against real market conditions and graded out-of-sample, so you always know whether it's working — on your own strategy, not a marketing figure. How the proof engine grades.

What we don't publish

We don't publish how a description becomes executable rules, or how the compiler keeps user-authored logic safe and honest.

We publish what a module does and what it's for. We don't publish how it works. The method is the product — and anyone holding the method holds the product.

Evaluating this for a desk? Talk to sales and we'll go as deep as an NDA allows.

How it works
  1. 01
    Your words become a graph, not a guess

    A description is parsed into an explicit rule graph — entries, exits, filters, sizing — that you can see and edit node by node. You are never left wondering what it thought you meant, because the interpretation is the document.

  2. 02
    One shape from build to live

    The graph the canvas produces is the same object the backtester runs, the paper book trades and the exporter writes. Most platforms re-implement a strategy between stages; every re-implementation is a chance for the tested thing and the traded thing to differ.

  3. 03
    Ambiguity is surfaced, not resolved silently

    "Buy the dip" has no single meaning. Where a description is under-specified the builder asks rather than picking a default and burying it — an invisible default is how a strategy ends up being tested as something you never wrote.

  4. 04
    Nothing runs that cannot be stated

    If a rule cannot be expressed in the engine's vocabulary it is refused at build time, loudly, instead of being approximated. An approximation that backtests well is worse than an error.

Worked example
One strategy object, checked at every station

The same strategy carried from canvas to backtest to paper to export, compared at each handover.

Stations the object passes through
5
Parity checks run between them
14 / 14 pass
Re-implementations along the way
the point of the whole design0

Most platforms rebuild a strategy between stages, and every rebuild is a chance for the tested thing and the traded thing to differ. Here there is one object, so there is nothing to drift.

What it refuses to do

Every one of these is a thing we could ship and choose not to. They are here because the limits are the part of a research tool you actually have to trust.

It won't invent the missing half of your idea

An under-specified description gets questions, not a confident filling-in.

It won't quietly substitute a similar rule

If the engine can't express what you asked for, it says so at build time.

Where strategy builder sits
Describe → Build → Prove → Train → Paper → You arm liveevery improvement re-proves before it counts1DescribePlain English, a pastedscript, or a chart photo2BuildA runnable strategy —one shape everywhere3ProveBacktested and gradedout-of-sample4TrainThe Conscious works it,condition by condition5PaperA real forward record,no money at risk6You arm liveOff by default. Only youcan turn it on

One pipeline, one strategy shape end to end. What you backtest is byte-for-byte what papers and what exports — there is no re-implementation step where drift can hide.

Questions people actually ask
Do I need to write code to build a strategy?

No. You can draw the rules on a canvas or describe them in plain English, and edit whatever the description got wrong. Code is an option, not a requirement.

Can I edit what the AI produced?

Yes — the output is an explicit rule graph, not a black box. Every node is visible and editable, and the edited version is what gets tested.

Is the strategy I build actually the one that gets traded?

Yes, and it matters. The graph the canvas produces is the same object the backtester, the paper book and the exporter all read. Nothing is re-implemented between stages.

Bring a strategy you already trade.

Test it yourself — or bring your desk's questions to us.

No card required · sales is for desks and teams