INJ/USDT1h
2026-06-03 · 41 candles
18WEAK
- Direction
- 1 of 3 right
- Inside 80% range
- 3 of 3
- Moved
- −7.04%
2 horizons called the wrong way.
We can't tell you
which way. We can tell
you how far.
Point your phone at any candlestick chart and get an 80% range for where price lands next — an interval built to contain four moves in five, which on the reserved test split contained81–85%.
Direction we measured at 50–51%, which is a coin flip, so we stopped selling it. Everything on this page is a number we published, including the ones that went against us.
Coming to theApp Store
See how it was measured, and what would prove it wrongNot submitted yet. The form below is the only way to hear about it, and it sends one message.
BTC/USDT · 1h · 61 candles read · last close $66,210Hover to see what it forecast42.2% likely up within 1 candle
Fig. 02 — the product, not a description of it
Three screens, in the order the app shows them.
Beat 01
Point it at any chart
A photo of a broker screen, a screenshot from a trading app, a chart on someone else’s monitor. If it has candles, it gets read — crypto or equities, any timeframe, no account linking and no API key.
Beat 02
It shows you what it read
The candles it digitised are drawn back over your image with a count. A forecast built on a misread chart is worse than no forecast, so the extraction is shown rather than assumed — you can see it got the bars right before you believe anything downstream of them.
Beat 03
And it refuses to oversell
The dial is a percentile of what this engine actually produces, stretched so the needle and the word underneath it agree. A typical forecast reads mid-dial and says so. Nothing here is tuned to look impressive.
Fig. 01 — the claim we can actually defend
Four moves in five land inside the range.
Built to contain 80%. Measured at 81–85% on a split nothing was tuned on.
So we sell the other number instead: when it says 70%, that happens about 70% of the time — and that one we can show you.
- 80% range, observed
- 84.9%
- At ten candles, on the reserved split. Supposed to contain the outcome 80% of the time. Does. This is the product.
- Held-out windows
- 729
- Non-overlapping, 26 symbols. Run once, as designed.
- Directional accuracy, measured
- 50–51%
- Against 47–51% drift. All three 95% intervals include 50%, so this is a coin flip and we do not sell it.
Fig. 02 — how far it reaches
Push it further out and it gets less sure.
One real scan, dragged through the three horizons it forecast. The next candle is the easy one. Ten candles out, the probability has slid 4.5 pointstoward the floor and the range is 3.1× wider. Nothing here is smoothed to make that look better.
Drag, or use the arrow keys
BTC/USDT · 1h · 61 candles read
Likely up
42.2% within 1 candle. With three outcomes the floor is 33.3%, so this call sits 8.9 points above guessing.
- 80% range
- −0.28% … +0.29%
- 0.57 points wide
- Median move
- +0.03%
- of similar setups
78/100STRONGsame at every horizon
Top 10% of what this engine produces, about one forecast in ten. These landed right 40.2% against a 34.2% base. A real edge, and still nowhere near a certainty.
Resolved+0.26%inside the 80% rangedirection right
One archived scan · BTC/USDT 1h · 2026-07-22 · resolved against what the market did next. Not a simulation.
Fig. 03 — stated against observed
This is the chart every competitor hides.
Each dot is a bucket of forecasts. Its position left to right is what the model claimed; up and down is what actually happened. A perfectly honest model sits on the diagonal.
Dots inside the corridor are sampling noise. Outside it is a miss, and two of these are.
| time | open | high | low | close |
|---|---|---|---|---|
| 07-21 22:00 | 66385.00 | 66388.35 | 66204.00 | 66304.02 |
| 07-21 23:00 | 66304.02 | 66576.00 | 66228.55 | 66556.16 |
| 07-22 00:00 | 66556.15 | 66739.89 | 66525.54 | 66620.97 |
| 07-22 01:00 | 66620.97 | 66661.79 | 66282.65 | 66433.30 |
| 07-22 02:00 | 66433.29 | 66532.26 | 66298.00 | 66314.12 |
| 07-22 03:00 | 66314.12 | 66371.27 | 66176.00 | 66210.00 |
Fig. 04 — the record, misses included
Eight scans, taken as they came.
8 scans sampled at even intervals through the 728 others in the final-gate run, sorted by confidence. Not curated; misses included.
ADA/USDT4h
2026-06-13 · 50 candles
49TYPICAL
- Direction
- 1 of 3 right
- Inside 80% range
- 3 of 3
- Moved
- +9.95%
2 horizons called the wrong way.
XAUT/USDT1h
2026-06-17 · 61 candles
66TYPICAL
- Direction
- 1 of 3 right
- Inside 80% range
- 3 of 3
- Moved
- +0.32%
2 horizons called the wrong way.
RUNE/USDT1h
2026-06-18 · 47 candles
10WEAK
- Direction
- 1 of 3 right
- Inside 80% range
- 2 of 3
- Moved
- −2.59%
2 horizons called the wrong way.
ATOM/USDT1h
2026-06-29 · 49 candles
32TYPICAL
- Direction
- 1 of 3 right
- Inside 80% range
- 3 of 3
- Moved
- −0.84%
2 horizons called the wrong way.
INJ/USDT1h
2026-07-16 · 61 candles
40TYPICAL
- Direction
- 2 of 2 right
- Inside 80% range
- 1 of 3
- Moved
- −2.10%
XAUT/USDT4h
2026-07-25 · 56 candles
98STRONG
- Direction
- not called
- Inside 80% range
- 3 of 3
- Moved
- +0.73%
RUNE/USDT1h
2026-07-29 · 58 candles
58TYPICAL
- Direction
- 3 of 3 right
- Inside 80% range
- 1 of 3
- Moved
- −1.35%
Across these 8 scans: 10 of 20 directional calls were right, and 19 of 24 outcomes landed inside the 80% range. Both sit where the measured averages say they should — which is the only claim being made here.
Fig. 05 — the states it can return
The weak reads get the same room as the strong ones.
Confidence is muted when it is low. The information never is. Hiding a weak read is the one thing that would make every strong read worthless.
AVAX/USDT1h
86/100STRONG
Forecasts in this band landed right 40.2% of the time, against a 34.2% base rate.
- 80% range, 10 candles
- 7.10 pts
- Resolved
- 1/1 right
XRP/USDT1h
48/100TYPICAL
Forecasts in this band landed right 34.5% of the time, against a 34.2% base rate.
- 80% range, 10 candles
- 2.01 pts
- Resolved
- 2/3 right
ETC/USDT1h
15/100WEAK
Forecasts in this band landed right 30.9% of the time, against a 34.2% base rate.
- 80% range, 10 candles
- 3.31 pts
- Resolved
- 2/3 right
Fig. 06 — the five inputs
A calibrated 70% and a 51% hit rate are not in tension.
One is a claim about how often the model is right overall. The other is a claim about whether its confidence means anything. A model can be barely better than chance and still tell you honestly which of its calls to trust — and that is exactly what the tiers do.
Signal strength
How far the models lean from a coin flip.
this scan: 0.164
Historical agreement
Whether the model and the historical analogs point the same way.
this scan: 0.600
Analog similarity
How closely past setups resemble this one.
this scan: 0.662
Chart readability
How cleanly the candles came off your image.
this scan: 1.000
Regime familiarity
How often the models have seen markets behaving like this.
this scan: 0.718
Fig. 07 — what it refuses to sell you
- 01
It does not tell you which way the price will go.
Direction measured 50–51% on the reserved split, against 47–51% for drift, with every interval containing a coin flip. We shipped that claim once. We measured it, it did not hold, and we took it down rather than round it up.
- 02
It never tells you to buy, sell, size or time anything.
It describes what a chart looks like and what similar charts did next. That is the whole job.
- 03
When the price axis is unreadable, it quotes no prices at all.
A designed refusal, not a blank field. You get the shape of the forecast and an explicit note that the numbers are missing.
- 04
A failed or unreadable scan never uses a credit.
Refunded on any non-200. Retry as many times as you need.
- 05
No countdown timers, no discount that disappears.
The price is the price. There is no urgency to manufacture, so none is manufactured.
Stocks and ETFs
No directional call on this market.
Three attempts at stock direction, none beating a coin flip, so we show none. How far it might move we can answer: the 80% range on daily equities held the outcome 80.7% of the time at ten days, with a mean width of 13.36%.
42 equities · daily · range only · ATR-scaled interval (the arm that shipped)
The largest of those refusals has its own write-up: eleven pattern detectors over 1.7 million bars, and every apparent edge dissolving once the control went deep enough. Candlestick patterns: a measured null
Calibration is the product. Direction is the coin flip we measure.
Price
3 scans free, then it costs what it costs.
Every camera scan runs AI vision over your image, then a quant engine over 230,000 historical windows. That is real compute each time, and this is what pays for it. Forecasts from the built-in market list don't use the camera, so you get 7 of those free every day.
Monthly
$9.99/mo
15 scans a month
Quarterly
$24.99/3mo
15 scans a month · $8.33/mo
Annual
$49.99/yr
14 scans a month · $4.17/mo
10 scans
One-time · never expires
$7.99
25 scans
One-time · never expires
$17.99
Packs cost more per scan than every subscription, and always will — a test fails the build if that inverts. No countdown timers, no vanishing discount. A failed or unreadable scan never uses a credit.
A small light, honest about how far it reaches.
Coming to theApp Store
Not submitted yet. The form below is the only way to hear about it, and it sends one message.