Ex-Spotify Engineers Raise $10M to Bring Intent-Aware AI to E-Commerce

Three former Spotify engineers are applying the technology behind the streaming giant's recommendation engine to e-commerce. Sidd Motwani, Ian Anderson, and Shivaditya Sinha, who built the behavioral intelligence infrastructure powering roughly 90% of Spotify's recommendations for its 800 million users, have launched Malachyte, a startup aiming to transform how online retailers personalize shopping experiences. The company announced Thursday it had raised $10 million in seed funding, which will be used to scale distribution and expand its product and commercial teams. Malachyte is built on the premise that most online stores treat shoppers the same way. Personalization, the founders argue, is often limited to historical purchases, demographic segmentation, or logged-in user profiles. As a result, first-time visitors see generic storefronts, and returning customers receive suggestions based on what they have bought before, not what they might need now. To address this, Malachyte has developed what it calls a "two-headed Vector AI" platform that predicts a shopper's immediate intent and general taste in real time, refining recommendations as the user interacts with the page. "Our system starts forming before the first click, using the context available the moment the page loads. Within a single session, we build a real read on both preferences and what someone is trying to accomplish right now," said Motwani, Malachyte's CEO. He gave an example: "A search for 'heavy-duty boot' followed by two clicks on steel-toed boots is enough to move work pants and gloves up the page and push dress shoes down, with no account or history required. Every additional action sharpens the profile, so the experience gets more relevant the longer someone stays, and again on their next visit." Motwani believes retailers already hold the most valuable source of customer intelligence, but rarely act on it in real time. "Every hover, click, scroll, search refinement and add-to-cart is a signal, and most systems either never act on it in the moment or aggregate it into a segment overnight. We read it continuously, so each action makes the user's vector more confident about both preference and current intent," he explained. Contextual signals, he noted, are also significantly underutilized. "A phone visitor at 11 p.m. from an email link is in a different state of mind than the same person on a laptop mid-morning, and most systems treat them identically," Motwani said. Malachyte has been developing and testing its technology since 2024, working with over 20 enterprise customers across travel, grocery, and retail before focusing exclusively on e-commerce. The platform launched in fall 2025 with Fun.com, and since June 2026, it has been generally available to Shopify merchants through a native integration, with larger retailers able to access the technology via API. Looking ahead, Motwani sees a larger opportunity in unifying merchandising and marketing around a shared understanding of customer behavior, which could redefine how online retailers engage with shoppers in the years to come.

via TechCrunch