GlossaryAgents and workflows

Agentic UX

Agentic UX is the design of interfaces for software that plans and acts on a user's behalf, tools, files, APIs, and multi-step workflows, not only text replies.

The core questions are permission, reversibility, autonomy, cost, handoffs, and trust in what the agent actually did.

What it means

UX patterns for agents: scope disclosure, action previews, approval gates, activity feeds, undo, and audit trails when AI touches external systems.

Why designers should care

A wrong chat answer is embarrassing; a wrong agent action can delete data or send email. Agentic UX makes oversight legible before and after execution.

Example

Before archiving 14 contacts, the agent shows a plain-language plan, lets the user edit scope, and writes each completed action to a readable log with undo.

Common mistakes

  • Chat-only UI for workflows that need task boards or timelines.
  • Executing destructive steps without a preview or confirmation gate.
  • No way to see which tools or accounts the agent used.

Explore more

Frequently asked questions

What is Agentic UX?

Agentic UX is the design of interfaces for software that plans and acts on a user's behalf, tools, files, APIs, and multi-step workflows, not only text replies.

Why should designers care about Agentic UX?

A wrong chat answer is embarrassing; a wrong agent action can delete data or send email. Agentic UX makes oversight legible before and after execution.

What are common mistakes with Agentic UX?

Chat-only UI for workflows that need task boards or timelines; Executing destructive steps without a preview or confirmation gate; No way to see which tools or accounts the agent used.

Weekly AI UX notes

Patterns, prompts, and glossary updates for designers building AI products on Substack. No spam.

Subscribe on Substack