Definition
The practice of finding out what an assembled decision system can actually do, including reachable tools, side effects, and action classes nobody intended to expose. Discovery is testing and cataloguing, and its output is a capability catalog rather than a permission.
It matters because capability that has not been discovered can be neither authorized nor refused. Keeping discovery separate from authorization is how a new capability stays outside the authority grant until someone decides it belongs there.
Scale: Organizational · Phases: Design, Audit · Measurability: Semi-quantitative · Maturity: Active research
Adjacent terms
References
- Laws for engineering delegated intelligence · Doctrine