AI observability

AI observability is the ability to see what an AI system did and why. It covers logging of who requested an inference, which model ran, what data was accessed, what was produced, and what action followed, in a record complete enough to reconstruct a decision after the fact.

The field most often missing is the last one. Systems log the request and the response but not the consequence, which is exactly what an auditor asks about, because it connects the output to something that happened in the world.

For agents, observability has to cover the plan as well as the actions. Understanding why an agent did something requires seeing what it intended, not only the steps it took.