Things we have built.

Winsen One

Purpose-built AI for financial services, manufacturing, logistics, and healthcare.

Winsen One puts role-specific AI into operational work such as credit file review, reconciliation, and alert disposition. Each system owns a defined queue and works the full volume instead of a sample. Nothing it produces counts until a named person signs it, and every action is logged and replayable.

Walle

An AI assistant that lives on Slack.

Walle takes care of the work around your work: the follow-ups, the updates, the loose ends. Ask it like you would ask a person, in Slack, and it plans the work, does it across your tools, and checks with you before anything leaves your workspace. Free to start.

Platos

The runtime our production AI runs on.

We needed a runtime that survives production, not just the demo. Platos is model-agnostic, monitored by default, and self-hostable in one docker compose up. We run Winsen One on it, and you can run yours on it too.

Rocketman

Project management that lives in the repo.

When coding agents write most of the code, the plan needs to sit where the agents can read it. Rocketman keeps a project hub inside your codebase as a single offline file. It is how we ship everything else, including this site.