TWIML Podcast Ep. 780: Zoe Weil on Using Live Behavioral Signals to Optimize Retail Rankings
TWIML AI Podcast Episode 780 features Zoe Weil, co-founder and CEO of Sequen, discussing how ranking systems can use live behavioral signals like scroll speed and hover duration to optimize for purchases rather than clicks or search relevance alone. The episode covers why social platform approaches don't necessarily translate to retailers, Sequen's large event models and specialized architecture for transforming streaming events into features, millisecond dynamic ranking infrastructure using Rust, evaluation harnesses connecting model improvements to business outcomes, tradeoffs between advertising and organic revenue, continuous model improvement, and the boundary between useful personalization and surveillance.
ImportanceLocalEvidenceE2 unreplicatedWrite-upQuick
TWIML AI Podcast Episode 780, published October 15, 2026, features Zoe Weil, co-founder and CEO of Sequen, discussing how ranking systems can use live behavioral signals to optimize for purchases rather than clicks or search relevance alone. The episode addresses why approaches developed at data-rich social platforms don't necessarily translate to retailers and how Sequen uses scroll speed, hover duration, and other in-session interactions to infer shopper intent without relying on user identity.
The conversation explores Sequen's large event models and its architecture of specialized models that transform streaming events into features for downstream rankers. Zoe describes the infrastructure required to serve dynamic rankings within milliseconds, why the team chose Rust for its backend, and how evaluation harnesses connect model improvements to business outcomes. Additional topics include the tradeoffs between advertising and organic revenue, continuous model improvement, and the boundary between useful personalization and surveillance.