Agentic Design Discipline: The New Design Practice for AI Agent Systems

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 Agentic Design Discipline

How do agentic design discipline 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 is the agentic design discipline?

The agentic design discipline - formally codified as Agentic Experience Design (AXD) - is the practice of designing trust-governed relationships between humans and autonomous AI systems. It addresses how humans delegate authority, calibrate trust, observe agent actions, interrupt autonomous behaviour, and recover from failures in systems where the AI agent acts independently. It was founded in September 2024 by Tony Wood at the AXD Institute in Manchester, United Kingdom.

How is the agentic design discipline different from UX design?

The agentic design discipline is not a specialisation or evolution of UX - it is a parallel discipline. UX was built for screen-based interactions where the user is present and navigating an interface. The agentic design discipline is built for systems where the user is absent and the agent acts autonomously. UX works in attention and affordance; the agentic design discipline works in trust and delegation. UX specifies interfaces; the agentic design discipline specifies outcomes.

What are the practice areas of the agentic design discipline?

The discipline encompasses five core practice areas: Trust Architecture (designing how trust is established, calibrated, and recovered), Delegation Design (designing how humans grant and constrain agent authority), Observability Design (making invisible agent actions legible), Interrupt Surface Design (designing when agents should re-engage humans), and Agentic Commerce Design (applying the discipline to commercial contexts like machine customers and zero-click commerce).

Who founded the agentic design discipline?

The agentic design discipline was founded by Tony Wood in September 2024. Tony Wood is an Emerging Technologies and Innovation Consultant and Agentic AI Product Specialist based in Manchester, United Kingdom. He established the AXD (Agentic Experience Design) Institute as the canonical institutional home of the discipline, publishing the founding manifesto, vocabulary, practice frameworks, and over 50 essays on the theoretical foundations.

Why is trust the primary material of the agentic design discipline?

Trust is the primary material because agentic systems operate when the human is absent. Without the human present to verify, correct, or approve agent actions, the entire experience depends on whether the human trusts the agent to act in their interest. Trust architecture - the structured design of how trust is established through competence, integrity, benevolence, and predictability - determines whether humans will delegate authority and whether that delegation will succeed. Every other aspect

Key Takeaways

None of these disciplines were designed for the defining characteristic of agentic systems: The agentic design discipline does not replace UX, interaction design, or service design. It operates in parallel, addressing a fundamentally different design context. Where UX works in The agentic design discipline is built on five principles that define its scope, methods, and materials. These principles were articulated in the Every agentic system begins with a designed act of delegation - a moment where a human grants authority to an agent. This act must be intentional, informed, and reversible. The quality of the delegation design determines the quality of the entire agentic experience. Where traditional design works in pixels, layouts, and interactions, the agentic design discipline works in trust. The most consequential agentic experiences happen when the human is not present. The discipline designs for Agentic experiences are not transactions; they are relationships that accumulate history over time. The discipline designs for Traditional designers specify what appears on screen - layouts, buttons, text, animations. Agentic designers specify what results - the outcomes, constraints, and conditions for human re-engagement. The agentic design discipline encompasses several distinct practice areas, each addressing a different aspect of the human-agent relationship: The structured design of how trust is established, measured, calibrated, and recovered in agentic systems. Trust architecture includes the The practice of designing how humans grant, constrain, and revoke authority in agentic systems. This includes The practice of making invisible agent actions legible to humans. This includes The practice of designing the boundaries at which an agent should pause and re-engage the human. The application of the discipline to commercial contexts - The agentic design discipline was formally codified as The Institute's work spans four interconnected domains: the The discipline is

References and Citations

Gartner: Machine Customers as Strategic Technology Trend Stanford HAI: Human-Centered AI Research NIST AI Risk Management Framework About the AXD Institute Contact Us Email the AXD Institute Tony Wood on LinkedIn Tony Wood on X (Twitter)