Borrow the SAE driving-autonomy framework. Five levels, each with a clean answer to one question: who decides, and what is the human's role?
Suggestion
What the AI decides
Nothing. Generates text or completions a human reads.
Illustrative example
Inline code completion. Draft email suggestions.
Single-Step Tool Use
What the AI decides
Which one tool to call, with which arguments, in response to a prompt.
Illustrative example
“Look up this customer's order status.” One API call, one answer.
Multi-Step Workflow
What the AI decides
A planned sequence of tool calls within a bounded scope, with human approval at the end.
Illustrative example
“Draft a refund. Show me the proposal.” Plans, gathers data, waits for sign-off.
Bounded Autonomy
What the AI decides
When to act, which steps to take, when to retry — within a guardrailed budget. Human is on-the-loop.
Illustrative example
An incident-response agent that triages alerts and opens tickets, escalating when confidence drops.
Goal-Directed Autonomy
What the AI decides
Goal, plan, sub-goals, and self-correction. Human reviews outcomes, not steps.
Illustrative example
A research agent given a topic and a budget. Returns a deliverable hours later.