← All work

Builds

AI-First Interface Strategy

Active

The platform as an intelligent backend

Merchandising decisions in natural language

AIPlatformMCP

Exposing the merchandising platform as an intelligent backend — an MCP + skills layer — so enterprise AI assistants can drive merchandising decisions in natural language instead of clicking through screens.

Problem

Powerful platforms still bottleneck on the UI. Every workflow means training users on screens, and the value is gated behind knowing where to click.

Approach

Treat the platform as a set of well-described tools (MCP servers + a skills layer) that an AI assistant can call. The interface becomes conversational; the platform’s algorithms stay the source of truth.

Outcome

Clients can ask for merchandising decisions in plain language, and the AI orchestrates the underlying platform — turning a deep feature set into something you can just talk to.