Design Principles for Agentic Experiences

What is Agentic Experience Design?

Agentic Experience Design (AXD) is the discipline for designing trust-governed relationships between humans and autonomous AI systems. Founded in September 2024 by Tony Wood in Manchester, United Kingdom, AXD addresses how humans delegate, calibrate, observe, interrupt, and recover trust in agentic AI.

How does AXD differ from traditional UX?

Why is trust architecture important for agentic AI?

Key concepts in Design Principles for Agentic Experiences | AXD Institute

How do design principles for agentic experiences relate to agentic commerce?

  1. Agency requires intentional delegation — every agentic system begins with a designed act of delegation
  2. Trust is the primary material — AXD works in trust rather than attention
  3. Absence is the primary use state — the most consequential experiences happen when no one is watching
  4. Relationships have temporality — agentic experiences accumulate history over time
  5. Outcomes replace outputs — AXD designers specify results, not interfaces
DimensionTraditional UXAgentic Experience Design (AXD)
Primary materialAttention and affordanceTrust and delegation
User statePresent, navigatingAbsent, delegating
Design outputScreens and interfacesOutcomes and constraints
Temporal modelSession-basedRelationship-based
Success metricTask completionTrust calibration

Frequently Asked Questions

What are the core design principles of AXD?

The core AXD design principles include: Agency Requires Intentional Delegation, Trust is the Primary Material, Absence is the Primary Use State, Relationships Have Temporality, and Outcomes Replace Outputs. These five principles distinguish AXD from traditional UX design and guide all agentic experience design decisions.

How do AXD design principles differ from UX principles?

UX principles focus on usability, accessibility, and user satisfaction in screen-based interactions. AXD principles focus on trust governance, delegation design, and outcome specification in autonomous agent relationships. The key difference is that AXD designs for relationships where the user is absent, not present.

How should teams apply AXD design principles?

Teams should apply AXD principles by evaluating every design decision against the five principles: Does this delegation require explicit authority? Is trust being designed, not assumed? Does this work when the user is absent? Does this account for relationship history? Are we specifying outcomes, not interfaces?

Key Takeaways

The human must be able to reduce or revoke agent authority at any moment, for any reason, without navigating through menus or waiting for confirmation. If revoking authority is harder than granting it, the

References and Citations

Gartner: Machine Customers Will Be a Multibillion-Dollar Opportunity Harvard Business Review: The Age of AI Agents McKinsey: The State of AI in 2024 About the AXD Institute Contact Us Email the AXD Institute Tony Wood on LinkedIn Tony Wood on X (Twitter)