Sidd Motwani, Ian Anderson, and Shivaditya Sinha, who spent years building the behavioral intelligence infrastructure behind Spotify’s recommendation engine, have raised $10 million in seed funding for their e-commerce startup Malachyte. The round was co-led by Bessemer Venture Partners and Gradient, with Harpoon Ventures participating. The company said the funding will be used to scale distribution and hire more product and commercial leaders.

At Spotify, their system, called Vector AI, is designed to predict a person’s intent and next actions instead of relying only on past behavior. It powers about 90% of Spotify’s recommendations to its 800 million users. Malachyte brings a similar approach to online shopping. The founders argue that most store personalization today is built on historical purchases, demographic segmentation, or logged-in profiles, so first-time visitors often see the same generic storefront, and returning shoppers get recommendations based primarily on what they bought previously rather than what they need now.

Malachyte’s platform uses what it calls a “two-headed Vector AI” to predict what product a shopper wants next, learn their general taste, and fine-tune continuously based on real-time activity. According to CEO Motwani, the system begins forming its model before the first click, using the context available the moment the page loads. Within a single session, it builds a read on both preferences and what someone is trying to accomplish right now. He gives 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 says retailers already possess their most valuable source of customer intelligence but rarely take advantage of it in real time. Every hover, click, scroll, search refinement, and add-to-cart is a signal; most systems either never act on it in the moment or aggregate it into a segment overnight. Malachyte reads those signals continuously, making the vector more confident about both preference and current intent. He also believes contextual signals remain 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.

The company has been developing and testing its technology since 2024, working with more than 20 enterprise customers across travel, grocery, and retail before ultimately focusing on e-commerce. Its platform first went live in fall 2025 with Fun.com. Since June 2026, it has been generally available to Shopify merchants through a native integration, while larger retailers can integrate the technology through its API. Looking ahead, Motwani sees the bigger opportunity in bringing merchandising and marketing together around the same understanding of customer behavior.