Trading,visualized.
Most quant tutorials are walls of text with one screenshot. Ours is the opposite: every concept on this page comes with a chart you can drag, a slider that morphs the market, or a bot you can run in real time. Read it like a book — but every page argues with you.
Trending.Random.Reverting.
A price wanders with no memory of where it's been. Its Hurst exponent is closest to…
Dataset.Bot.Workspace.
Real OHLCV from Yahoo Finance for AAPL, NVDA, BTC, NIFTY — anything Yahoo lists. Synthetic deterministic walks for symbols Yahoo doesn't have. Same input → same answer, every time.
Could be 70-year-old textbook math (Black-Scholes, RSI, SMA crossover) or a 2024 neural net trained on real markets. Either way the output is the same shape: BUY / SELL / HOLD / WARN with a confidence score.
They all see the same chart. The Output panel tallies who agreed. When 5 trend bots and 3 AI bots all flash BUY at the same time, that's a signal worth noticing.
One bot.One chart.Nothing fake.
The fast moving average crosses ABOVE the slow one. The textbook signal is…
Same bot.Wins one regime,loses the next.
Bot A returns +40%, Bot B returns +18%. Which is the better strategy?
One bot isa guess.Six agreeingis a signal.
One bot flashes BUY at 60% confidence. How much should you trust it?
Five numberstell you everythingabout an option.
You're long a call and the stock rips up fast. Which Greek just paid you most?
A 15%-OTM putcosts more thana 15%-OTM call.
A 15%-OTM put vs a 15%-OTM call — which one costs more?
Three models.One question.Three answers.
Three models price the same option's odds. They return…
27 bots,organized soyou don't drown.
12 bots that delegate to a Python ML service — neural option pricers + ensemble direction forecasters trained on real Yahoo data.
Follow momentum. Buy the breakout, exit the reversal. SMA Crossover, MACD, Donchian, Bollinger.
Measure what's normal. Z-score, Hurst exponent, Kalman filter, LinReg channel.
How much to bet. Kelly criterion, Monte Carlo VaR, Sharpe optimiser.
Pure math. Black-Scholes solver, IV crush detector, the wheel back-test.
Five knobs.Each inplain English.
You re-run the exact same seed twice. The chart comes back…
Toggle on.The mathreads like a story.
OPENAI_API_KEY is set; falls back to a hand-written mock if not.RSI is a 0-to-100 thermometer. Below 30 means everyone panicked and the price is probably going to bounce. The bot just spotted three of those bounces in your window — that's why it leans BUY with high confidence.
If you can writea JS function,you can write a bot.
candles + params and returns { verdict, summary, metrics }. It hot-loads into the workspace.// Example: a 10-line bot that buys 52-week breakouts.
export default {
id: "my-breakout",
name: "52w Breakout",
category: "trend",
glyph: "↑",
tagline: "Buy when price hits a new 252-day high.",
params: [{ key: "lookback", kind: "number", default: 252 }],
run: (ctx, p) => {
const px = ctx.candles.map(c => c.c);
const high = Math.max(...px.slice(-p.lookback));
const last = px[px.length - 1];
const breakout = last >= high;
return {
signals: [],
metrics: [{ key: "h", label: "52w high", value: high.toFixed(2) }],
summary: `Last ${last.toFixed(2)} vs ${p.lookback}d high ${high.toFixed(2)}.`,
verdict: { side: breakout ? "buy" : "hold", text: breakout ? "Fresh high." : "Below high.", confidence: breakout ? 0.7 : 0.2 },
};
},
};Two halves.One workbench.
ai quants/serve.py that runs trained neural networks. When the service is up, you see Source: Python NN on every card. When it's not, the bot falls back to a deterministic TS surrogate marked clearly Source: Mock.You click ▶ Run All in /quant. The bot's run() function builds a request body.
aiBot() wrapper hits the FastAPI service (NEXT_PUBLIC_QUANTAI_URL) with an 8s timeout.
serve.py loads the right surrogate, runs predict(), returns JSON. The card flips green.
cd "ai quants" && uvicorn serve:app --reload --port 8000