Active Observability

We can come to an operational understanding of complex systems by watching how their parts work together and how they respond to our actions that either confirm our own model or demand its revision.

Here is the science behind the idea. springer

> Active inference is an approach to understanding behaviour that rests upon the idea that the brain uses an internal generative model to predict incoming sensory data. The fit between this model and data may be improved in two ways: perceptual inference or active inference.

We see the opportunity to bring a variety of mechanisms together to this end.

The Base Model provides an orienting surface description of the system suitable for annotation.

The Agent Probes collect and distribute observations and actions to the live system, real or imaginary.

With probes into the base we can confirm that the system works as expected or not. We are not yet able to ask the system what it might be doing that surprises us. For that we must watch what moves.

The Patterns of Movement allow us to see indirect action over distance and correlate likely causes and effects that could not be foreseen.