Progressive Delegation
Start with drafts the human always reviews; expand the agent's autonomy action-by-action as measured trust accrues — promotion and demotion are automatic, evidence-based.
Intent & Description
🎯 Intent
Stage the human-to-agent handoff over time — the agent starts producing drafts a human always reviews; its autonomy expands action-by-action as measured trust accrues.
📋 Context
An agent will eventually take over parts of a human workflow — drafting code review comments, triaging support tickets, scheduling meetings. The end state is full autonomy on routine cases; the starting state is human-supervised because trust hasn’t been built yet.
💡 Solution
Tag each action class with a current autonomy level (draft → assisted-send → autonomous). For each class, track a rolling success-rate window. Promotion fires automatically when the window clears a bar over enough samples; demotion fires when it drops below. The promotion mechanism is the policy of record — not a verbal decision in standup.
Real-world Use Case
- Multiple action classes have materially different risk profiles.
- Per-class success can be measured online with reasonable delay.
- Stakeholders want autonomy to be a measurement outcome, not a meeting decision.
Source
📌 TL;DR
Autonomy expands action-by-action as rolling success rates clear bars — promotion and demotion are automatic and evidence-based, not meeting decisions.
Advantages
- Autonomy decisions become a function of evidence rather than calendar or politics.
- Different action classes can sit at genuinely different autonomy levels simultaneously.
- Trust incidents demote only the affected action class, not the whole agent.
Disadvantages
- Promotion gates can be cheaply gamed if the success metric is weak or easily satisfied.
- Demotion thrashing on small windows can noisily yank capabilities away.
- Per-class bookkeeping is overhead that small teams consistently underinvest in.