If you've searched for an EA to pass a prop firm challenge, you've already found ten lists that all say the same three things: high win rate, low drawdown, verified results. What none of them show you is how "low drawdown" was measured, over what data, or whether the number that got printed on the sales page is the worst case or just the one that happened to show up in the backtest. We build EAs differently: an AI research engine generates…