Sidd Motwani, Ian Anderson and Shivaditya Sinha spent years building the behavioral intelligence infrastructure behind Spotify’s recommendation engine. Their Vector AI system is designed to predict a user’s intent and next actions rather than relying solely on past behavior; according to the report, it powers about 90% of Spotify’s recommendations for roughly 800 million users.
New startup: Malachyte
The three have launched a startup called Malachyte to adapt this approach for online retail. The company announced on Thursday that it raised $10 million in seed funding to scale distribution and hire additional product and commercial leaders. The round was co-led by Bessemer Venture Partners and Gradient, with participation from Harpoon Ventures.
Malachyte was founded on the observation that most online stores treat shoppers uniformly: personalization typically depends on historical purchases, demographic segments, or logged-in profiles. That means first-time visitors often see the same generic storefront as everyone else, while returning shoppers receive recommendations mainly based on what they bought previously rather than what they need right now.
Real-time, intent-sensitive shopping
Malachyte’s platform — which the company describes as a “two-headed Vector AI” — aims to predict which product a shopper will want next, learn general taste, and continuously fine-tune recommendations based on real-time actions. Motwani, Malachyte’s CEO, told TechCrunch that the system begins forming a profile before the first click, using 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.”
Motwani gave an example: a search for “heavy-duty boot” followed by two clicks on steel-toed boots is enough to elevate work pants and gloves up the page and push dress shoes down — all without requiring an account or history. Each additional action sharpens the user profile, so the experience becomes more relevant the longer someone stays and on subsequent visits.
He argues retailers already hold their most valuable 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,” Motwani said.
He also notes that contextual signals are often underused: a phone visitor at 11 p.m. arriving from an email link is in a different state of mind than the same person on a laptop mid-morning, yet most systems treat them identically.
Development and deployment
Malachyte has been developing and testing its technology since 2024 and worked with more than 20 enterprise customers across travel, grocery and retail before 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 a larger opportunity in aligning merchandising and marketing around a unified understanding of customer behavior.
Why it matters
If successful, real-time, intent-based recommendation systems could improve relevance from the first visit, reduce irrelevant suggestions, and increase click-through and conversion rates without requiring immediate login or prior purchase history. The $10 million seed round and early live deployments indicate investor and early-customer interest in experimenting with intent-driven personalization in commerce.
