AI UX PlaygroundNewsletterJoin 2K+ AI designers and PMs on Substack. New teardowns, patterns, and prompts as they drop.

Agentic UX

A decision framework for how much authority an AI agent should have, and what the product must guarantee at each level.

Assistants answer questions. Agents take actions. A wrong answer is awkward; a wrong action can delete a file, spend money, or email a customer. Choose the right autonomy before you ship.

How much should the agent do?

Confirm

Agent proposes. You say go.

YouAgent

Autonomy is a product decision, not a model capability.

An agent may be able to take an action without being ready to receive authority over it. Separate what the model can do from what the product should allow, then match authority to consequence.

Design principle

Grant the lowest level of autonomy that delivers the outcome. Raise authority only when evidence shows the system can stay safe, legible, and recoverable.

When signals conflict, choose the lower level, or split the workflow so low-risk steps proceed while high-impact steps stay under review.

The five levels

Higher is not better. Each level changes who decides, acts, and monitors. Each section includes what to build and patterns that put it into the product.

Suggest

Agent advises. You do the work.

Question
Can the agent help without taking any action?
Principle
The agent never takes the action. It only surfaces options you can ignore.
Breaks as
A single pushy recommendation with no alternatives, or a suggestion that looks like a completed action.
Use when
Ideas, rankings, or next steps where a wrong suggestion is cheap to ignore.
Build
  • Show why this was suggested
  • Offer alternatives, not one answer
  • Let people dismiss it with no penalty
Roles

Decides

You

Acts

You

Monitors

You

Suggest / Confirm / ExecuteMap suggest, confirm, and execute onto one product control so L1 stays advisory.Open pattern

Other related patterns

Draft

Agent starts. You finish.

Question
Can the agent prepare work that only ships when a person finishes it?
Principle
The agent prepares an artifact, but nothing ships until you edit and intentionally complete it.
Breaks as
A draft that auto-sends, edits durable records, or hides that side effects are still blocked.
Use when
Emails, docs, code, or plans that must not go out until a person finishes them.
Build
  • Mark it clearly as a draft
  • Make every part editable
  • Block side effects until publish
Roles

Decides

You

Acts

You finish

Monitors

You

Chat ArtifactsKeep drafts editable and side-effect free until a person intentionally publishes.Open pattern

Other related patterns

Confirm

Agent proposes. You say go.

Question
Is the agent ready to act, but still paused until a person approves?
Principle
The agent is ready to act, but stays paused until you approve the exact scope.
Breaks as
Approve without a preview of impact, no deny or edit path, or silent re-plans after the user said yes.
Use when
Send, spend, delete, or change access: actions with real consequences that need a yes first.
Build
  • Preview exact impact before approve
  • Allow edit, deny, or cancel
  • Re-ask if the plan changes
Roles

Decides

You approve

Acts

Agent after OK

Monitors

You

Human in the loopThe approval gate when the agent is ready to act but a person still decides.Open pattern

Other related patterns

Bounded

Agent acts inside your limits.

Question
Can the agent run alone inside hard limits and escalate on exceptions?
Principle
The agent runs on its own inside hard limits, and escalates when it hits an exception.
Breaks as
Soft limits the agent can ignore, no interrupt, or exceptions that fail silently without an owner.
Use when
Repeatable work where the agent can run alone inside budgets, allowlists, or timeboxes.
Build
  • Hard limits: budget, scope, stop rules
  • Escalate when uncertain
  • One-click interrupt and rollback
Roles

Decides

You set policy

Acts

Agent in bounds

Monitors

You on exceptions

Per-Action AutonomyDifferent actions in the same product can sit at different levels inside hard limits.Open pattern

Other related patterns

Monitor

Agent runs. You watch.

Question
Can the agent operate continuously while people govern policy and anomalies?
Principle
The agent operates continuously. People govern policy and anomalies, not every step.
Breaks as
An always-on agent with no visible status, no anomaly owner, or no safe shutdown path.
Use when
Stable, well-owned operations where people oversee the system more than each action.
Build
  • Always-on status that it is running
  • Anomaly alerts with a clear owner
  • Safe shutdown and reauthorization
Roles

Decides

You set policy

Acts

Agent

Monitors

You + systems

Autonomous Mode DisplayWhen the agent runs without asking, that state has to be unmistakable.Open pattern

Other related patterns

Match the risk of one action to an autonomy level.

Score impact, reversibility, reliability, sensitivity, and detection. The tool recommends a level from Suggest to Monitor, plus who should decide, act, and monitor.

01 · Impact

If this goes wrong, how bad is it?

02 · Reversibility

Can you undo it?

03 · Reliability

How proven is the agent at this task?

04 · Sensitivity

How sensitive is the context?

05 · Detection

Can someone catch a bad outcome?

Cheatsheet

Eight checks before raising autonomy.

  • Is this the lowest level that still delivers the outcome?
  • Can people see who decides, who acts, and who monitors?
  • Are side effects blocked until the level allows them?
  • If the plan changes, does the product re-ask or re-bound?
  • Is there a one-click interrupt, deny, or shutdown path?
  • Are hard limits real (budget, scope, allowlist), not soft preferences?
  • When autonomy rises, is status unmistakable and owned?
  • Can someone recover work after a bad autonomous action?

Other frameworks