Platform · Train

Orchestrator

Every module has an opinion. This turns them into one call, with the reasoning attached — and it will only act on an edge that has actually proved out.

What you get
One decision

Not six dashboards to reconcile in your head. One call, and what it's based on.

It shows the conflict

When the modules disagree, it says so rather than papering over it.

It can't overreach

It cannot act on an edge that hasn't proved out — that limit is enforced server-side, not by the model's good behaviour.

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 what it reads, how it weighs it, or how the limit is enforced.

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.

Worth knowing

It advises. It never arms anything by itself.

How it works
  1. 01
    Many signals, one decision

    Where several strategies speak at once, the orchestrator resolves them into a single position rather than stacking correlated exposure that looks like diversification and behaves like leverage.

  2. 02
    One signal, one vote

    The same underlying signal arriving through two strategies counts once. Double-counting a single idea is the most common way a portfolio becomes accidentally concentrated.

  3. 03
    Advisory by construction

    The orchestrator proposes. It has no authority to arm live trading, and that boundary is enforced in the engine rather than left to configuration.

Worked example
The concentration that looks like diversification

Two strategies firing on the same underlying signal, with and without one-signal-one-vote.

Positions opened without it
same idea, same direction, double size2
Positions opened with it
1
Apparent diversification
unchanged
Actual risk
halved

Running two strategies is not the same as holding two positions. Where they agree, the account is concentrated exactly when it feels most diversified — which is why the collapse to one vote is enforced rather than offered.

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 arm live trading

Advisory only, enforced server-side rather than by a setting you might flip.

It won't stack the same idea twice

Correlated signals collapse to one vote.

Where orchestrator 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.

Under the claim
The Conscious training loopTHECONSCIOUSYour strategybuilt, imported, or drawnCondition lensessessions · regimes · structureEvidenceedge measured per conditionChallengeran improved copy, on paperYour callpromote it — or don'tIt narrows and tunes. It never deletes your work, and it never arms live money.

The same learning system that runs our own research desk, pointed at your strategies. You choose which folders it may learn from. Improved copies must beat the original on forward paper trades before promotion is even offered — and a promotion that stops holding up is demoted back to testing by the evidence, never quietly kept.

Questions people actually ask
Can the orchestrator place trades on its own?

No. It resolves competing signals into one recommended decision and stops there. Arming live execution is a separate, deliberate action that only you can take.

What happens when two of my strategies disagree?

The disagreement is surfaced rather than averaged. Netting a long against a short produces a position neither strategy asked for and that nothing was tested as — so the conflict is shown to you with both cases stated.

Does running more strategies make me safer?

Only if they are actually independent. Where several fire on the same underlying signal you hold one idea in multiple positions, which feels diversified and behaves like leverage. Collapsing those to a single vote is the orchestrator's main job.

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