Matthias Luebken

Today’s software factories are designed for distribution: a team of humans and agents builds an application, then many people use it. AI changes that economic model. When an employee can create a useful application for themselves, we can no longer afford to treat every application as a bespoke artifact requiring centralized design, approval, and long-term maintenance. The next software factory should be able to produce and operate a long tail of small, task-specific applications: software for one person, one workflow, or one decision. This does not mean abandoning engineering standards or enterprise governance. It means building them into the factory itself: identity, shared data, guardrails, secure capabilities, and a sandbox.

In this talk, we explore the architecture behind software of one: lightweight isolated compute, durable state, capability-based access to shared systems, and clear paths for sharing, reuse, promotion, and retirement. Including throwing code away and rebuilding from scratch. The goal is not to replace shared applications. It is to evolve how we build software so that everyone can safely become a builder.

When people use OpenClaw, they're amazed. It auto-discovers new capabilities, explores available data sources, stitches components together, and dynamically builds new solutions. It feels like the system is learning. It feels magical.

At its core, OpenClaw is powered by pi.dev: a deliberately simple coding agent built on a small set of powerful primitives. PI's "radical extensibility" turns out to be a strong architectural fit for the kinds of composable, evolving use cases OpenClaw is designed to support.

In this talk, we'll take a closer look at what's actually happening under the hood. We will look at the different components and how builders can reuse them in their products.