Borrowed from autonomous-systems literature. The label is not just rhetoric — each posture implies a different UI, a different staffing model, and a different liability story.
Co-pilot
The human approves each consequential action before it executes. The agent proposes; the human commits.
Use when
Zone 2–3 actions. Regulated outputs. Anything where “undo” is expensive or impossible.
Design rules
The failure mode
Approval fatigue. Reviewers click through hundreds of identical-looking proposals and miss the one that matters.
Supervisor
The agent acts autonomously within bounds; the human monitors a stream of outcomes and intervenes by exception.
Use when
Zone 1–2 actions at high volume. Steady-state operations. Observability is mature.
Design rules
The failure mode
Automation complacency. The dashboard is green for ten months and the human stops looking. Then it goes red and nobody is watching.
Owner-only
The agent acts without per-decision oversight. Humans review aggregate outcomes, set objectives, and tune policy.
Use when
Zone 0 actions only, at this stage of the industry. Read-only research, internal drafts, low-stakes summarization.
Design rules
The failure mode
Drift without detection. The agent's outputs slowly degrade, the cost slowly creeps, nobody notices because nobody is looking.
The honest truth: most enterprise agents in 2026 should be human-in-the-loop today, with a deliberate path to human-on-the-loop as evidence accumulates. Skipping a stage to look ambitious is how incidents get made.