AI harnesses
What is the autonomy ladder for AI harnesses?
The autonomy ladder compares harnesses by how much they do on their own, from autocomplete, to approving each step, to plan-then-execute, to fire-and-forget background agents. Higher rungs trade oversight for throughput.
A useful way to compare harnesses is how much they do on their own, from least to most autonomous:
- Autocomplete — it suggests, you accept.
- Approve each step — it proposes an action and waits for your yes.
- Plan then execute — it drafts a plan, then carries it out.
- Fire and forget — a background agent runs to completion and reports back.
Higher rungs trade oversight for throughput. The right rung depends on the stakes of the task, which is exactly where rules and guardrails come in.