⋯
Checking engine status

Today

Ctrl+K to jump anywhere

Build something no code — each opens a guided builder

1. Write an atoma condition on the candles, e.g. a volume spike on a red bar
2. Chain a sequenceatoms in order: this happens, then that, within N bars
3. Make it a strategywatch every market for your sequence
4. Deploy to a paper bookvirtual capital; see how it would have traded

System is it working?

Strategy readings confirmed, newest first

Top of the scanner composite rank

Pumped pairs open episodes

Paper books virtual capital

Alerts latest

Row click → chart 1
Symbol Base Quote Market Venue Symbol
Hybrid Pattern Universe
A map of what this platform can detect, not a claim that any of it works. Nothing here is validated. A library this size is a multiple-comparisons machine — at p<0.05 roughly one sequence in twenty looks excellent by chance, and this platform has already read +0.323R in sample and −0.048R out on a 900-config search (ADR-069). Each atom and each sequence carries what has actually been measured about it; an empty measurement means unmeasured. The candles on each card are synthetic — a generated picture of the sequence's own stages, drawn so sweep, then structure breaks, then the gap is retested is legible at a glance. Hover a numbered badge for that stage's role.
Atoms — the vocabulary
Atom Universe
Every observation the hybrid engine can extract, in every state. This describes the platform, not the market in the toolbar — it is the same list on every symbol and it does not reload when you inspect one. An atom is one stamped reading taken from a layer that already computed it; an ordered sequence of them is a pattern, and those live in the Patterns tab. Each row carries what has actually been measured about that reading, and an empty measurement means unmeasured, which is the default. Nothing here is a signal. Uses counts sequences that name the atom, not ones that need it: a stage naming three alternatives counts for all three, so choch_break reads 78 and no sequence depends on it. The candles beside each row are synthetic — the same generated picture the Patterns tab draws, for one atom instead of a whole sequence, because a sweep and a break differ only in whether price held beyond the level it took and that is a picture rather than a sentence. Direction is a drawing convention: atoms publish a direction per event and the registry declares none. Hover a diagram for what it does and does not claim.

Signals Python

Completed 15m candles, with a frozen stop, target and risk decision.

Market / sourceDirectionStateAvailable · ISTEntry referenceStopTargetNet RQuantityPlanned loss
Loading saved decisions…

Entry prices are references. Planned stop loss includes stated costs and can differ from a fill. Setup scores do not establish profitability.

Signal Lab

Choose a study, review both backtest years, check its evidence, then follow its forward paper trial.

1. Choose a research study

2. Review the saved backtests

Each year starts with its own 1,000 USDT. The continuous account carries its balance through both years. Fees, slippage and native funding are included.

Closed trade preview

3. Check the qualification evidence

A completed, audited two-year study is required before a new paper trial can start.

4. Follow the forward paper trial

New deployment stays blocked until all two-year checks pass.

Short experiments, saved accounts and candle replay

Use these tools for a teaching example or a short custom experiment. The saved two-year research and forward trial above remain separate.

Choose a saved run

The offline launcher and this page use the same Python workflow.

Paper equity

Recorded trade outcomes

Entry and exit prices use the market's native quote. Fees, funding, quote-currency P&L and net P&L use USDT.

MarketOutcomeQuantityEntry fillExit fillFeesFundingQuote-currency P&LNet P&LNet R
Chart workspace
Layout
Chart layout

↑ Rising: blue outline · ↓ Falling: orange fill

Candle replay

Replay the market, one close at a time

Replay setup Pairs, dates & selections
Additional timeframes & custom patterns

Sequences you saved in Patterns → Sequence builder… are already in the Patterns list above, marked ★ and listed first — no JSON needed. Paste JSON here only for a one-off draft.

Single-timeframe patterns follow the chart. Multi-timeframe patterns retain their ladder; remap each rung above. Strategies evaluate the chart timeframe.

Select event and reading atoms, patterns and strategies.
Load a replay to begin
Turn on to drag or pinch the chart. Turn off to scroll the page.
More controls Events, window & display
Load a replay to begin.
Wheel to zoom · Drag to pan · Click a line label for details
Green / red: direction · Gold: confirmed pivots · Dashed grey: rejected · Click an event for its evidence
Atom readings
Timeframe coverage & unavailable readings

Saved configurations & run history

Open a frozen run, or load its configuration and change pairs, timeframes or dates.

Scanner-stack backtests & comparisons
— —

Live readings the session's own stack, at this frame

Start a replay to watch the platform re-experience history.

Backtests click two to diff

Time Machine

Target and stop probabilities, projected prices and prior outcomes for a saved experiment.

Choose a saved experiment to see its Time Machine projection.
PRICE · FLOW · FOLLOW-THROUGH

Exhaustion OBSERVING

See when effort stops moving price, and what happens next.

Loading observations…

MARKETSChoose a coinChange

Status checks both directions. Event time uses the latest warning or confirmation candle; markets without one stay last.

Choose a market

Each reading keeps its native venue and contract.

Reading native price…

Native price15m · completed candles

Touch or move over the chart to inspect a candle and its evidence.

Flow and contextNative volume and positioning
Choose plotted metrics

Price stays in native quote units. Normalized values describe each metric's trailing range, not reversal probabilities.

Why this reading?
Native values and data coverage
Recorded history
How the assessment works

A warning needs a move of at least 2 ATR near a recent directional extreme, plus measured effort without progress, balanced absorption or price/CVD divergence. A strictly later close beyond the warning candle's opposite edge confirms the attempt. A new extreme invalidates first; the window expires after eight candles.

Funding, open interest, crowding, depth and reported liquidations provide context. The existing Pumped Pairs score is shown separately.

Recorded markers preserve actual save times. Calculated markers use completed native candles and evidence available at each close. Missing data and stale readings remain labeled. Normalized plots show each metric's trailing range from 0 to 100.

Warnings and confirmations describe observed price and flow. They do not establish a profitable trade or a reversal probability.

CRYPTO DERIVATIVES

Options Lab PAPER

Build a structure. Explore its payoff. Follow it in paper.

MODEL INPUTSEditable assumptions

Loading Options Lab…

ActionOptionStrike · USDPremium / unitIV %ContractsUnits / contract
Up to 8 legs · one expiry · premiums in USD per underlying unit
Costs & pricing assumptions

Expiry payoff reserves a fee on entry and exit. Paper fills also use the bid/ask spread and adverse slippage. These costs are editable assumptions.

Payoff at a glance

Net P&L · USD

Expiry payoffToday · modelWhat if · model

Greeks across price

Change in value for a $1 spot move.

Spot × volatility

Net model P&L at the selected elapsed time

Time decay

Model P&L if spot and IV stay unchanged

Leg exposures

Sized to your contracts
How these calculations work

    Books every portfolio, compared

    Virtual positions marked, never filled

    Performance the whole filtered set, as the API counted it

    Closed trades realized and booked once — virtual throughout; window set in Performance above

    Allocation decisions approvals and denials, with the gate that decided

    Every decision is recorded — a denial names the closed reason that produced it.

    Scenario results a shocked copy; this book is untouched

    Run a scenario to see which named limits a shock would breach.

    Report every number traces to a recorded output

    Pick a report above.

    Workflows trigger, approval, mode, and what each has done

    Pending approvals waiting on a human

    Nothing is waiting for a decision.

    Execution history every run, and why it ended where it did

    Audit timeline a run is reconstructable from these rows alone

    Pick a run above to see every stage it went through.

    Dry-run replay validate against recorded history

    Choose a workflow and a replay session, then run. Broker calls are simulated only.

    Answer deterministic unless a model is configured

    Ask about something the platform recorded — a narrative, a pattern, an analyst's change of mind, or the market right now.

    Retrieval evidence what the answer was built from

    Every answer cites document ids. Nothing here is generated from raw tables.

    Similar history vector search — no model involved

    Enter a symbol or click a document to find its closest historical analogues.