A new computing paradigm is emerging where the agent is the runtime, natural language is the interface, and skills are starting to look a lot like apps.
Software 1.0 was hand-written code. We told the computer exactly what to do.
Software 2.0 was training models on data. Instead of writing every rule, we trained systems on examples and let them learn the behavior.
Now there is a new layer showing up on top of both. It doesn’t replace Software 1.0 or 2.0. It builds on them.
You still need code for the underlying systems: integrations, infrastructure, permissions, reliability, and all the deterministic parts that have to work. You still need models for reasoning, language, perception, and generation.
But the top layer is changing. The agent starts to look like a runtime. Natural language starts to look like a programming interface. And skills start to look a lot like apps, with directories to find them and package managers to install them.
