Autonomy is earned in shadow mode, where the machine's complete package is recorded against every human decision until six months of evidence settles the trust question.

Losing tests become coded constraints: two losing popular parlays tests turned into a 2.5x penalty weight and a hard floor in the next experiment's envelope.

One churn run cut 750 features to 20, lifted F1 by 6% and tested live across three arms of 47,000 users, worth roughly a million dollars over baseline.

The agent builds its own features (756 candidates to 20), never sees the validation set, and will reframe a problem when the scoring rules make a wrong guess cost more than a right one earns.

FanDuel's auto researcher reads an objective function, proposes a strategy, writes the model, scores it and repeats about 300 times in an hour for around $300, returning the winner as readable code.