How to use CrypAI

Everything you need to create, test, and deploy profitable trading strategies using AI.

Overview

CrypAI is an AI-powered strategy builder for crypto trading. You describe your trading idea in plain English, and AI converts it into a backtestable strategy with real market data, fees, and slippage.

The workflow

1. Describe — type your strategy idea or pick a template

2. Backtest — AI generates the strategy, you run it against historical data

3. Analyze — see monthly breakdown, AI diagnoses what works and what doesn't

4. Improve — refine your prompt, use AI improve, or edit conditions manually

5. Deploy — once Grade A or B, deploy to paper or live trading

Creating strategies

You can create strategies in three ways:

1. Natural language (Pro)

Just describe what you want. The AI understands trading concepts and converts them into precise conditions.

"Buy BTC when momentum is strong and volume is high, 
risk 2% per trade, stop at 3%"

"Mean reversion on ETH: buy when price is 2 standard 
deviations below the mean and RSI shows oversold"

"Ichimoku cloud breakout on SOL with volume confirmation"

2. Visual Builder (Free)

Use the 8-step visual strategy builder to configure indicators, conditions, exits, and risk management without writing any code or using AI.

3. Strategy discovery (Pro)

Click "Discover" and AI generates 5 completely different strategy approaches for your chosen pair. Pick the best one and refine it.

Refining strategies

After creating a strategy, use the "Refine current" tab to modify it without starting over:

"Make it long-only"
"Switch to 4h timeframe"
"Add a volume filter"
"Tighten the stop loss to 2%"
"Use Stochastic RSI instead of regular RSI"

Indicator reference

CrypAI supports 40+ indicators across multiple categories. Each indicator creates one or more columns you can use in entry conditions.

Quant tools

CrypAI includes statistical tools used by quantitative traders.

Writing conditions

Conditions use column names, operators, and values. Multiple conditions are joined with AND or OR.

Operators

>    greater than         ema_9 > ema_21
<    less than            rsi < 30
>=   greater or equal     adx_14 >= 25
<=   less or equal        close <= bb_lower
==   equals               supertrend_dir_10 == 1

Combining conditions

AND — all must be true:
  ema_9 > ema_21 AND rsi > 50 AND adx_14 > 25

OR — any group can trigger:
  (close < bb_lower AND rsi < 30) OR (is_hammer > 0 AND rsi < 40)

Math expressions:
  volume > volume_sma_20 * 1.5
  close > ema_21 + atr_14 * 0.5

Backtesting

Backtests run against real Binance historical data with realistic assumptions.

What's included

• Real data — actual OHLCV candles from Binance via CCXT

• Taker fees — 0.04% per side (matches Binance Futures)

• Slippage — 0.03% per side (conservative estimate)

• Funding rates — 0.01% per 8h for long positions

• Position sizing — risk-based (% of capital per trade)

Grading system

Grade A — PF ≥ 1.8, Sharpe ≥ 1.0, WR ≥ 45%, DD < 15%  → Deploy ready
Grade B — PF ≥ 1.3, Sharpe ≥ 0.5, WR ≥ 40%, Return > 1%  → Deploy or improve
Grade C — PF ≥ 1.0, Return ≥ 0%  → Marginal, improve first
Grade D — PF ≥ 0.7  → Unprofitable
Grade F — PF < 0.7  → Broken, try different approach

AI improvement

The AI analyzes your backtest results and suggests improvements targeting the weakest months. You get 3 AI improvement attempts per strategy.

Pro features include:

• 8-regime market detection — knows when your strategy works and when it doesn't

• AI analysis — detailed breakdown with specific fix recommendation

• Auto-improve — AI generates a surgically improved version

Risks & warnings

Backtesting limitations

• Overfitting — a strategy that works perfectly on historical data may fail live. Watch for: Sharpe > 3, win rate > 80%, fewer than 30 trades.

• Survivorship bias — only pairs that still exist are in the data.

• Slippage underestimate — real slippage during volatility can be much worse.

Risk management rules

• Never risk more than 2% of capital per trade

• Always use a stop loss

• Paper trade for at least 2 weeks before going live

• Start with small size on live

• Set a max drawdown limit of 15-20%

Strategy examples

Proven strategy patterns you can use as starting points.

1. Trend following

"BTC trend following: buy when Supertrend is bullish 
and MACD histogram is positive and ADX > 25. 
2% risk, 3% stop, 6% TP. 4h timeframe."

Long: supertrend_dir_10 > 0 AND macd_hist > 0 AND adx_14 > 25

2. Mean reversion

"ETH mean reversion: buy when z-score < -2, 
RSI < 30, and MFI shows accumulation. 1h."

Long: zscore_20 < -2 AND rsi < 30 AND mfi_14 > 30

3. Volume breakout

"SOL Donchian breakout with volume surge. 1h."

Long: close > donchian_upper_20 AND volume > volume_sma_20 * 1.5

4. Price action

"BTC: bullish engulfing above 200 EMA with divergence. 4h."

Long: is_bull_engulf > 0 AND close > ema_200 AND rsi_bull_div > 0

Pricing & limits

Backtest runs and AI Improve clicks are free and don't count toward your daily limit. Only strategy creation counts.