Define the rules
Choose a universe, signals, position sizing and exits before examining any results.
Define signals, sizing and exits with visual rules, Vega or Python, then evaluate the strategy with walk-forward backtesting before paper trading.
Define the strategy before inspecting its results, then review the evidence each run returns.
Choose a universe, signals, position sizing and exits before examining any results.
Use visual rules, write sandboxed Python or ask Vega to draft the specification.
Inspect walk-forward folds, modeled costs, drawdown and the statistical gate verdicts.
Review the full run and required gates before trying the strategy in simulation.
Use the visual builder, the sandboxed Python SDK, or let Vega draft the rules.
Deflated Sharpe, universe warnings and the Probability of Backtest Overfitting flag a failing strategy.
Track a tested strategy's risk in Aegis, or paper-trade it with signals by email.
Use the visual builder, write Python or export the signals.
Whichever route you take, the backtest and the risk views read the same rules.
strategy: momentum-x-sectoruniverse: { region: US, top: 500 }signals: - momentum(126) - momentum(21) - filter: adx(14) > 20portfolio: { long: 50, weighting: risk_parity }exits: { trailing: 8%, invalidation: signal_flip }validate: { walk_forward: 5y, costs: realistic, gates: [DSR, PBO] }
Use visual rules or ask Vega to draft a specification, then inspect the universe, signals, sizing and exits. The Strategy Builder methods show the visual and Python routes.
Market-data coverage and strategy support differ. Check your selected strategy, universe and date coverage, including point-in-time support and survivorship limitations.
A preview uses a lighter universe for iteration. Paper trading requires a qualifying full walk-forward run, the required validation gates and available account capacity.
Review held-out folds, trading costs, the benchmark, drawdown and gate verdicts together. The walk-forward testing guide explains how the evaluation periods fit together.
The current pricing and access page explains preview limits, metered full runs and invite-only signup. Each metered run shows its estimate before it starts.
Backtested / walk-forward results are hypothetical, do not represent actual trading, and are not indicative of future results.