Maple's feature set is organized around a single research workflow: observe markets, form a hypothesis, validate it, and keep a record of what you learn.
AI-assisted research
Maple can turn a plain-English trading idea into a structured, testable strategy, and its autonomous research mode can test dozens of strategy variations on an asset without needing any AI model — a deterministic search-and-score process that runs entirely in the browser.
Backtesting and strategy validation
Every strategy can be backtested against historical market data, with full trade-by-trade detail, equity curves, and drawdown analysis. Results are then checked by Maple's validators, which look for overfitting, regime-dependence, and small-sample unreliability (see Methodology).
Strategy Lab
A library for saving, comparing, and iterating on strategies over time, so testing an idea doesn't mean starting from a blank page every time — and so a trader can track how a strategy's robustness has changed as it's refined.
Paper trading
Strategies can be run forward against live market prices using simulated capital, so their real-time behavior can be observed without any real money at risk. Paper trading in Maple never places a real order and never touches real capital.
Market observation
A dashboard view of the assets a trader is tracking, alongside the status of their saved strategies and paper positions, so research stays organized instead of scattered across notes and spreadsheets.
Feedback and iteration
Because Maple is under active development, in-app feedback is a first-class feature — testers can flag issues or ideas directly from any screen, which is read and acted on by the team building the product.