Strategy Lab

start_optimization_run

Start an AI optimization run on one of your own strategies — repeatedly mutates the code, backtests each variant, and keeps only the improvements, validated on data no experiment trained on. Charges your Strategy Lab wallet per experiment.

Parameters

NameTypeDescription
strategyIdstringID of your own strategy to optimize
exchangeIdstringAn exchange you own, used to source historical candle data
symbolstringTrading pair to optimize against(default: BTC/USDT)
timeframestringCandle timeframe, e.g. 1h, 4h, 1d(default: 1h)
maxExperimentsnumberHow many mutate-and-backtest experiments to run (1-30)(default: 20)
scoringProfilestringbalanced, conservative, aggressive, or consistency(default: balanced)
trainSplitnumberFraction of the window used for training vs. out-of-sample validation(default: 0.7)
userGuidancestringFree-text steering for the AI mutations
autoPromotebooleanAuto-promote the result to stable if it clears a strict validation bar(default: false)
acknowledgeCostbooleanConfirm the wallet charge to actually start the run(default: false)

Example Prompts

Try asking your AI assistant any of these:

Optimize my ETH strategy to reduce drawdown
Run 15 experiments on my GhostRider strategy for a better Sharpe ratio
Improve my strategy's win rate using AI

Start Using start_optimization_run

Set up the TradeStaq MCP server in under a minute.