Explainability
The ability to understand how or why a model reached a conclusion and produced a given output.
Also called
- Explainable AI (XAI)
- Interpretability
Often confused with
- Observability The tracking and recording of what an AI system does on each run: inputs, outputs, steps, tool calls, cost and errors.
Related
- Bias A skew in how an AI system treats people or cases, or in what it produces, inherited from its data or built in by design.