Agents AI UX patterns

Agent patterns cover tool use, autonomy budgets, approvals, checkpoints, and orchestration. Where users need to see what the system did and revoke or roll back.

Essential

Make tools, approval, budgets, and rollback visible before agents act.

More in Agents

Agents

Per-Action Autonomy

Autonomy scoped per capability, not per app

Agents

Checkpoints and Restore

Named snapshots with one-click restore

Agents

Workflow Builder

Visual drag-and-drop workflows

Agents

Memory Management

Viewing what AI remembers

Agents

Human Handoff

Escalating to humans

Agents

Escalation Thresholds

Auto-demote autonomy when risk crosses a line

Agents

Error Recovery Strategies

Configurable retry/fallback patterns

Agents

Self-Correction

Agents fixing errors

Agents

Conditional Logic & Branching

Branch workflows by conditions

Agents

Scheduled Tasks & Recurring Actions

Time-based automation triggers

Agents

Multi-step Forms with AI

Adaptive progressive forms

Agents

Agent Orchestration

Visual flow for multiple agents

Agents

Agent Performance Metrics

Dashboard showing agent success rates

Agents

Agent Versioning

A/B test different agent configurations

Agents

Agent Marketplace

Browse and install pre-built agents

Agents

Blast Radius Visualization

Preview scope before agent executes

Agents

Reversibility Marking

Label actions by how easily undone

Agents

Time-Delayed Execution

Cancelable countdown before high-impact actions

Agents

Pre-Task Cost Estimate

Forecast tokens, dollars, and time before run

Agents

Autonomous Mode Display

Persistent signal when agent runs unattended

Agents

Context Portability

Legible payloads across app boundaries

Agents

Ambient Presence Displays

Low-attention signals for agent state

Agents

Sandbox Preview

Dry-run plan with explicit side effects before execute

Frequently asked questions

How are agent patterns different from chatbot patterns?

Chat patterns focus on conversation contract and turns. Agent patterns focus on side effects, tool calls, permissions, checkpoints, and durable control across sessions.

What should users always see before an agent acts?

Intent, scope, and reversibility: which tools will run, what data they touch, and how to stop or undo. Approval workflows and autonomy budgets make that contract explicit.

When do I need a task queue versus suggest / confirm / execute?

Use suggest / confirm / execute for the session-level autonomy contract. Expose a task queue only when several agent jobs run in parallel over time and users need status per job—not as a separate catalog pattern from tool use.

How do I design rollback and checkpoints?

Expose checkpoints before destructive steps, label what state will be restored, and keep rollback one gesture away. Users forgive agent mistakes when recovery is obvious.

Which products exemplify agent UX in this catalog?

Pattern examples reference Cursor, Devin-style agents, workflow builders, and assistants with tool pickers. Open any card’s examples list for specific references.

Where is the Agentic UX framework?

Use the linked framework for territories (permission, rollback, autonomy) and anti-patterns. Category patterns here are the implementation catalog mapped to those territories.