Suggest / Confirm / Execute
Suggest / confirm / execute is an AI agent UX pattern that offers three autonomy modes: the agent only proposes (suggest) asks before acting (confirm) or runs with permission already granted (execute). Users pick the mode that matches risk so control scales with stakes instead of a single autopilot switch.
When to use
Essential for AI coding agents, workflow automation, and any interface where users need explicit control over how independently an AI acts on their behalf.
When not to use
- Single low-stakes draft tools where confirm always and execute never is enough.
- Fully attended interactive editors where every keystroke is already human-driven.
- Regulated flows that legally require confirm for every side effect, expose confirm only, not execute.
Anti-patterns
- A global Autopilot that silently includes irreversible execute actions.
- Mode labels without showing what will run (tools, targets, blast radius).
- Defaulting newcomers to execute on first session.
- Switching modes mid-run without pausing or re-disclosing side effects.
How products use it
| Product | Implementation |
|---|---|
| Cursor Agent | Plan and ask before apply vs freer edit modes with reviewable diffs. |
| GitHub Copilot Workspace | Proposal and plan stages before merging agent-authored changes. |
| Claude Code | Permission prompts for tool use vs trusted local edit sessions. |
| Devin | Staged plans and human gates before long autonomous coding runs. |
Use this pattern in your project
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 "Suggest / Confirm / Execute" AI interface design pattern.
Pattern Definition:Task · Send renewal
Send renewal email
Send renewal email
Ask firstPauses before each step and waits for your approval.
Frequently asked questions
What is suggest / confirm / execute in agent UX?
It is a three-mode autonomy model: suggest means propose only, confirm means act after approval, and execute means run with prior permission. Users choose the mode to match how much risk they accept.
How does it differ from human-in-the-loop?
Human-in-the-loop is the confirm gate on a specific action. Suggest / confirm / execute is the session-level policy that decides when that gate appears versus when the agent may proceed.
What mode should be the default?
Default to confirm for new users and irreversible or external actions. Offer execute only after users understand scope, or only for narrow reversible toolsets.
Can products mix modes per tool?
Yes, and they should. Suggest for planning, confirm for send/deploy/spend, and limited execute for local reversible edits is a common and safer mix than one blanket setting.