Black Swan Commerce
Problem — Purchase intent is trapped inside retailer-specific search boxes. Customers repeatedly restate the same requirements while every seller represents products, availability, pricing, and carts differently.
Product — Black Swan Commerce is an API-first commerce engine that turns a plain-text shopping list into reviewable product selections and pushes the confirmed picks into a real merchant cart, recording every decision along the way.
A purchase request should be written once, remain under the customer's control, and work across whichever seller or interface responds best.
Evidence
- Canonical, schema-validated request model shared across every interface— Implemented
- Command-line, MCP, and versioned REST interfaces on one engine, with REST as the sole product surface— Implemented
- Stateful commerce sessions (resolve, review, confirm, cart) on an asynchronous job queue and worker— Implemented
- Replaceable selection strategy (ranking heuristic or language model, with fallback) behind a provider-neutral inference interface— Implemented
- Recorded decision trail: verbatim supplier requests and responses plus per-candidate ranking scores— Implemented
- Kroger authentication, product search, and cart-add, verified by a real end-to-end grocery run into a live cart— Implemented
- Supplier-adapter architecture isolating retailer-specific logic from the core model— Implemented
- Self-hosted deployment (PostgreSQL, API, worker) on owner-controlled infrastructure— Implemented
- Selection-accuracy analysis over the recorded decision trail— Planned
- Second merchant integration— Planned
Next — Add a second merchant through the same supplier contract without retailer-specific assumptions leaking into the core model, and use the recorded decision trail to measure selection accuracy before tuning ranking.