Give an AI Agent Write Access One Verb at a Time

Описание и применение

При добавлении к агенту ИИ возможности записи необходимо классифицировать действия по стоимости отката, логировать каждое решение и поэтапно вводить автономию, начиная с безопасных действий.

Задача

When an AI agent has write access, a single wrong action can cause irreversible damage, yet many teams lack a systematic way to decide which actions the agent can perform and how to monitor them.

Результат

By classifying verbs, logging decisions, and staging rollout, the team achieved safe write access for AI agents, reducing accidental changes and enabling autonomous operations for low‑risk actions.

Рабочий процесс

• 1. List all verbs the agent can perform against named systems.
• 2. Sort verbs into free, awkward, and one‑way buckets based on undo cost.
• 3. Assign each verb a mode: dry_run, needs_approval, or autonomous.
• 4. Implement logging for every decision point, including declined actions.
• 5. Deploy in stages: start with dry_run to collect real traffic logs.
• 6. Move verbs to draft‑and‑approve, reviewing queued actions.
• 7. Graduate verbs to autonomous one at a time, applying caps and kill switches.
• 8. Monitor for silent skips and other failures, alerting on absence of action.

Доказательства

The point is not the type. The point is that nobody can add a tool without answering "what does undo look like for this?" in the same pull request.

Источник

Once the list is sorted, the approval gate goes at the line between awkward and one‑way.

Источник

The rollout sequence below costs a couple of extra weeks, and it removes most of the argument about whether the agent is trustworthy, because it replaces opinions with a log.

Источник