Per-Action Autonomy

Per-action autonomy is an AI agent UX pattern that sets independence per capability, not one global autopilot. Users might auto-draft email but require approval to send, or auto-commit to feature branches but never to main.

Share

Interactive demo

Tool permissions

Choose how each tool runs. Changes apply to this project only.


edit_file

Edit files in the workspace

run_terminal

Run terminal commands

git_push

Push to remote

delete_file

Delete files

Overview

The design problem

How might we design per-action autonomy so people can trust and act on AI output?

Use this pattern

When this pattern fits

  • Essential for AI coding agents, workflow automation, and productivity assistants where different actions carry different risk profiles and users need calibrated autonomy per capability, not per app.

Avoid this pattern

When to skip or lighten it

  • Single-capability agents where per-action settings duplicate a global toggle.
  • Audiences who will never open advanced settings; offer sensible defaults first.
  • When the platform cannot enforce different policies per tool call.

States

State model coming soon

Key UX elements

Key UX elements coming soon

Anti-patterns to avoid

  • One “Autopilot” switch that silently enables irreversible actions.

  • Per-action settings buried with no summary of current policy.

  • Defaults that auto-approve send/delete on first connect.

  • Policies that drift after model or connector updates without notice.

How products use it

ProductImplementation
Email agentsAuto-draft known threads; approve send to new recipients.
Cursor / coding agentsFreer edits in working trees; gated pushes to protected branches.
ChatGPT agent modeDifferentiated confirms for browsing vs messaging vs purchases.
Enterprise IT botsAuto-read; approve write to production systems.

Implementation

Copy this prompt to generate a production-ready implementation in Cursor, Claude Code, Lovable, or any AI coding agent.

Generate a production-ready implementation of the "Per-Action Autonomy" AI interface design pattern.

Pattern Definition:

Frequently asked questions

What is per-action autonomy in AI agents?

Per-action autonomy sets how independently each capability may run, so read, draft, and send can have different approval rules inside the same agent.

Why not a single autonomy slider?

Risk is not uniform. A global slider either blocks useful automation or over-authorizes dangerous actions. Per-action policies match real trust gradients.

How should defaults be set?

Default to ask-to-approve for irreversible or external actions, and allow freer autonomy for reversible local drafts. Make the policy matrix visible and editable.

Weekly AI UX in your inbox

Weekly AI interface UX notes and resources on Substack, no spam, unsubscribe anytime.

Subscribe on Substack