Sidd Motwani, Ian Anderson, and Shivaditya Sinha spent years developing the behavioral intelligence infrastructure that powers Spotify's recommendation engine. Known as Vector AI, this system is designed to anticipate a person's intent and next moves rather than simply relying on their past actions. It drives roughly 90% of Spotify's recommendations for its 800 million users. Now, the trio is applying a similar approach to e-commerce through their new venture, Malachyte. On Thursday, the company announced it had secured $10 million in seed funding to expand its distribution and bring on additional product and commercial talent.

Malachyte was built on the premise that most online retailers treat all shoppers the same way: Personalization tends to be shaped by past purchases, demographic groupings, or logged-in customer profiles. As a result, first-time visitors often encounter the same generic storefront as everyone else, while returning shoppers get suggestions based mostly on what they've bought before, not what they actually need at the moment. The startup aims to change that by delivering real-time, intent-aware shopping experiences. Its platform relies on what it calls "two-headed Vector AI" to predict which product a shopper is likely to want next, understand their overall preferences, and refine itself continuously based on live behavior.

"Our system starts forming before the first click, using the context available the moment the page loads," the team explained. "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 argues that retailers already have their most valuable source of customer insight at their fingertips, but rarely tap into 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 added. He also believes contextual signals are significantly underused. "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.

The company has been developing and testing its technology since 2024, collaborating with more than 20 enterprise clients across travel, grocery, and retail before narrowing its focus to e-commerce. Its platform first launched in the fall of 2025 with Fun.com. Since June 2026, it has been available to Shopify merchants through a native integration, while larger retailers can access the technology via its API. Looking ahead, Motwani sees a bigger opportunity in aligning merchandising and marketing around a shared understanding of customer behavior. The funding round was co-led by Bessemer Venture Partners and Gradient, with participation from Harpoon Ventures.