MissionSAFE / Design study

Model change evaluation: define the mission boundary

Radio telescopes at the Very Large Array in New Mexico at sunset.

The operational question

In this illustrative missionsafe scenario, a assurance reviewer uses AI to organize a model-change assessment. The workflow draws on MissionSAFE scenarios and recorded outputs. Its central risk is a previous benchmark being assumed to cover a new model version. The design question is how to submit the assessment for review for the deployment decision group while preserving the separation between evaluated behavior and release authority. This is a proposed evaluation scenario, not a report of an Archetypal customer deployment or a demonstrated operational outcome.

Define the mission boundary

The first governance decision is where the system’s authority begins and ends. Write the intended task as a bounded activity with an identifiable owner. Specify the information the workflow may use, the audience it serves, and the decisions it may support. Then identify the actions that remain outside that permission. A description of what a model can do is not an authorization to do it. A good boundary makes change visible. If the audience, information class, tool access, or intended use changes, the workflow should be able to recognize that it is operating under a new set of conditions. The owner can then decide whether an existing approval still applies or whether another review is required.

Put the control in the workflow

Place this review immediately before the team can submit the assessment for review. The assurance reviewer should see the proposed result beside the relevant parts of MissionSAFE scenarios and recorded outputs.

What a result would establish

Report the scope with the finding.

Authority.

Archetypal film

Documentary footage · No dialogue · Source credits