Can it make the thing?
A chart renders. A dashboard runs. A prompt produces an analysis or interactive artifact.
Evidence: execution, task completion, feature contractThe central gap
A generated chart can be possible without becoming finished work—or useful communication.
Most demos answer the first question below. Practitioners live in the second. Readers determine the third.
Can someone finish and maintain the job?
The data and semantics are right. Decisions are inspectable. Precise edits, delivery, and reuse are possible.
Evidence: accepted artifact, total time, errors, repair, maintenanceDo creators retain control and readers understand?
The creator can explain the process. The reader grasps the claim, limits, and appropriate next action.
Evidence: observed behavior, reader tasks, decisions, confidence calibrationCapability → human consequence
Ten cases · three controlled bridges · zero accepted-delivery bridges.
HAIChart connects recommendation performance to controlled analyst use, interactive task decomposition connects system error to analyst correction, and ChartAttack connects generated attacks to reader harm. None freezes an exact accepted artifact and follows it through real delivery; none completes the reader, later-maintenance, and whole-cost episode. These are three partial paths—not one synthetic lifecycle.