Sequen co-founder Zoe Weil tells Sam Charrington how her company uses in-session browsing signalsAI personalization adapts information, recommendations, interfaces, or agent behavior to an individual or group using permitted context and observed needs., such as scrolling and dwell time, to rank products with commercial outcomes in mind. Charrington asks how the approach differs from conventional upselling and raises privacy concerns.
Weil describes low-latency event processing, specialized models and evaluation harnessesEvaluation is the systematic assessment of a system's behaviour or results against explicit criteria.. She says the company uses live session data rather than sharing customer data across clientsData privacy governs how personal, confidential, or sensitive information is collected, used, shared, retained, and protected in AI systems., and discusses the tradeoffs involved in measuring relevance and sales.
The conversation covers complementary product recommendations, continuous model updatesAn AI feedback loop occurs when AI outputs or their consequences become inputs that influence later model or agent behavior. and future research in ranking. Weil’s performance and privacy claims are presented as her account of the company’s approach.
Watch on YouTube
