How do you build an interface for a platform that makes a billion decisions a day — and make it feel effortless?

01 — Problem

Synerise is a behavioral AI company whose platform processes over 12 billion automated decisions per month for enterprise retail clients including BNP Paribas. BaseModel is their flagship AI/ML product — a behavioral foundation model that turns raw data into real-time personalization at scale. The frontend challenge is not the data volume: it is building a product platform that three separate teams can develop in parallel, that enforces design consistency without a style-guide-nobody-reads, and that makes an extraordinarily complex ML system feel navigable to a data scientist.

02 — Constraints

• Three product teams, one shared codebase — any architecture that serialised team work was a failure
• The ML pipeline is continuous and event-driven; the UI had to stay responsive as event volumes spiked unpredictably
• Design consistency across three products had to be structural — enforced by the system, not by convention

03 — Architecture

An NX monorepo gives each team a fully isolated workspace while sharing a single version of Colloid — the Storybook-first component library built to encode design decisions structurally. TanStack Query owns all server state: streaming ML outputs, polling prediction endpoints, syncing campaign data across the platform with consistent caching semantics. Teams ship features independently; Colloid makes them look like one product. Playwright E2E tests cover critical paths across all three products without duplicating setup.

04 — Solution

Contributed to the platform architecture from early-stage design through advanced beta. Co-developed Colloid — building reusable components integrated into the open-source design system and maintaining the shared NX infrastructure. Introduced TanStack Query as the standard data layer, replacing inconsistent ad-hoc fetching patterns with a typed, cacheable interface to the ML pipeline. Worked directly with architects, ML teams, backend engineers and UX designers to ensure the frontend kept pace with a rapidly evolving AI product.

• Senior Frontend Engineer — platform architecture
• Co-designer and contributor to Colloid open-source design system
• Frontend infrastructure across NX monorepo

05 — Outcome