Why we started testing Argos in a house, not in a factory

When you tell people you are developing an agent that makes autonomous decisions, the most frequent question is for what industry. People expect to hear manufacturing, energy, logistics, something big, something that justifies investment in advanced AI.

When you answer a house, they laugh. Then they listen why, and they stop laughing.

Reason 1, errors are recoverable

An autonomous agent will, by definition, make mistakes. It will observe wrong, infer wrong, plan wrong. That is part of learning, not a bug to eliminate.

In a factory, an agent that decides badly can stop a production line, damage equipment, compromise safety. Costs are immediate and large. In a house, an agent that decides badly turns on the light when it should not, or adjusts temperature wrong for a while. Annoying. Recoverable. Without serious consequences.

Reason 2, real sensory richness

A house has changing light, changing temperature, sounds, intermittent human presence, habits that change day by day, frequent anomalies. All of that is real signal, not simulated.

For an agent that has to learn to model the world, this is perfect. Complex enough that the problem is interesting. Bounded enough that everything relevant can be observed with a handful of sensors.

Reason 3, continuous human verifier

The person living in the house is the natural oracle. If the agent does something weird, they notice immediately and react. If it does something right, also. That continuous feedback is exactly what a system learning to infer intentions, anticipate needs and propose actions needs.

Intelligence is trained where errors teach the most. A house teaches more than a factory if what we are building is something we do not yet know completely.