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.
AI Engineer & Founder of TAVON.ai.
Matthias Lübken is an AI engineer and founder of TAVON.ai, where he helps organizations build software with agents. With more than 20 years building cloud-based systems, he works on agent architectures, developer tooling, and enterprise AI. His current work explores how secure, stateful, AI-built applications can give individuals more adaptable software while simultaneously improving governance, integration, or control at an enterprise scale.
