Chart Reader
It reads the chart the way you do — structure, swings, ranges, compression, the shape of the candles — and it reads it as of that bar, never with hindsight.
Where price actually is: trending, ranging, coiled, at support, mid-pullback.
What it says about a bar is what it could have known at that bar. A read that improves with hindsight isn't a read.
Every read is scored against what happened next, so you can see whether it's any good.
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.
We don't publish how structure and patterns are detected, or how reads are scored and trained.
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.
- 01Structure, computed causally
Swings, ranges, support and resistance, sweeps and flips are derived only from bars that had already closed at the moment being described. A read that improves with hindsight is not a read.
- 02Geometry before opinion
The reader measures the things it can measure — where price sits in its range, how far the nearest opposing wall is, how fast the approach was — before any judgement is layered on.
- 03It reports what it cannot see
Thin data, a missing higher timeframe or an unformed level produce an explicit gap rather than a confident sentence built on nothing.
The same level, described two ways: using only prior closed bars, versus allowing the bars that came after.
- Causal read
- modest, sometimes uncertain
- Hindsight-assisted read
- confident and wrong-in-production
- Which one the engine uses
- causal, always
Every structural feature is stamped with what was knowable at that bar. This is why chart reads here look less impressive and survive better.
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.
The single most common way chart analysis flatters itself.
Missing context is reported as missing.
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.
Does the chart reader repaint?
No. What it says about a bar is only what could have been known at that bar. A read that changes once later candles arrive would be worthless for deciding anything.
Can it tell me what will happen next?
No, and it will not pretend to. It describes structure that exists and states its confidence and its gaps. Prediction dressed as description is the thing this engine is built to avoid.
What structure can it actually see?
Swings, ranges, support and resistance, liquidity sweeps, flipped levels, the distance to the nearest opposing wall and how fast price approached it — all computed from bars that had closed at the moment being described.
Why does it sometimes say it does not know?
Because sometimes it does not. Thin data, a missing higher timeframe or a level that has not finished forming all produce an explicit gap. A confident sentence built on absent data is the most expensive kind of wrong.
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.
Bring a strategy you already run. An MT5 expert or a Pine script comes in and gets held to the same standard as everything else here.
Most strategies aren't good or bad — they're good somewhere and bad somewhere else. This finds which conditions carry yours, and which quietly bleed it.
Every losing trade is evidence. This reads all of them, finds what they had in common, proposes a change to the rule — and proves the change before it ships.
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.
A backtest tells you what a strategy would have made. This tells you whether its decisions were actually any good — against history it was never shown.
It goes to paper the moment it earns it. Live stays off until you turn it on — and you're the only one who can.
A decade of minute-resolution history across thirty instruments — the thing that decides whether a backtest is evidence or an opinion with a chart attached.
Edges decay. A strategy exported six months ago is quietly rotting on someone's terminal, and nothing tells them. This does.
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