Learning Path
Navigate the AXO curriculum
Websites
Applications
AXD Fundamentals
Agentic Experience Design
Designing usable, explainable, and trustworthy interactions for human-agent collaboration.
What is Agentic Experience Design?
Agentic Experience Design (AXD) is the discipline of creating usable, explainable, and trustworthy interactions between humans, AI agents, and the systems they act on.
Where traditional UX focuses on direct manipulation interfaces, AXD focuses on delegated autonomy: helping users supervise, direct, and correct agents that act on their behalf while maintaining trust and control.
AXD sits alongside UX, conversation design, and service design, connecting interaction models, design principles, and implementation patterns for agentic systems.
What is AXD?
The design discipline for delegated autonomy, and how it differs from UX, conversation design, and AXO.
Human-Agent Interaction Models
In-the-loop, on-the-loop, and out-of-the-loop oversight — and how systems escalate between them.
Entry Points & Orchestration
Why one agent surface beats a widget per page, and what the orchestrating agent owes the user when it delegates.
Design Principles
User autonomy, honest communication, accountable safety, data alignment, and consent.
Generative UI & Context
Interfaces assembled by a model at runtime: the constraint spectrum, predictability, and provenance.
Interaction Patterns
Building blocks: expectation setting, error recovery, transparent permissions, progressive automation.
The Designer Role
What an agentic experience designer actually does, the skills it demands, and how it differs from product and conversation design.
The Future of AXD
WebMCP, the agentic browser shakeout, agent payments, and prompt injection as a design constraint.
Research behind agentic experience design
What the benchmarks and the human-factors literature say about designing for agents, with the papers cited and the numbers checked.
October 11, 2026
10 Agentic UX Patterns and Real-Life Scenarios
Ten patterns from our agentic interaction patterns reference, from the entry point to progressive automation, each with a shipping product that does it today and a scenario where you would need it.
October 6, 2026
Designing the Agent Handoff
Agentic experience design has no pattern for the moment an agent gives up. The research on what a handoff is worth, why knowing when to stop is its own failure class, and why the oversight literature disagrees with itself.
October 2, 2026
Why an Agent That Works 80% of the Time Finishes a Third of the Job
Reliability is quoted per action and experienced per task, and the gap is where agent integrations fail. What compounding does to a five-step flow, and what it changes about agentic experience design.
See the journey on your own site
The Agent Visualizer walks one of your pages and shows where an agent arrives, where it reads, where it stops, and everything after that it never reaches.
Stay Updated
Analysis of AI search, crawler policy and agent standards — sent when there is something worth reading, roughly twice a month. Unsubscribe anytime.