Recommend has a new setting in the Frequently Bought Together (FBT) model! Previously, the FBT model inferred connections between products based on collaborative filtering, recommending items even if they hadn't been purchased together before. While sophisticated, this approach may not suit all use cases. To address this, we are introducing the "Strict" variant in public beta, which only recommends items that have been strictly bought together. This new option allows users to choose between the existing "Relaxed" model, which increases catalog discovery through inferred relationships, and the new "Strict" model, ensuring recommendations are based solely on past purchases. This update provides greater clarity and flexibility, enhancing the precision of product recommendations for different business needs. This feature is now available to all customers.