What Is Agentic Experience Design (AXD)?

For thirty years, design disciplines assumed the user was present. UX mapped journeys through screens. Service design orchestrated touchpoints between people. Interaction design refined the micro-moments of click, swipe, and scroll. Every methodology shared a single assumption: the human is here, watching, deciding, acting.

Agentic AI breaks that assumption. When an AI agent books a flight, negotiates a price, manages a portfolio, or triages a medical referral on someone's behalf, the human is absent. The most consequential moments in the experience happen when no one is watching. No existing design discipline was built for this condition.

AXD was founded in September 2024 by Tony Wood in the United Kingdom to address this gap. It is not a rebrand of UX, not conversational design, not prompt engineering, and not AI ethics. It is a parallel discipline that treats the design of human-agent relationships as a first-class problem - one that requires its own vocabulary, its own frameworks, and its own principles.

AXD is built on five principles that distinguish it from every prior design discipline:

1. Agency Requires Intentional Delegation. Every agentic system begins with a designed act of delegation - a human granting permission for autonomous action. AXD designers architect this delegation: its scope, duration, constraints, and mechanisms for revocation.

2. Trust Is the Primary Material. Where UX works in attention and affordance, AXD works in trust. Trust in autonomous agents is calibrated, contextual, and fragile - and it can be designed. Trust Architecture provides the structural framework.

3. Absence Is the Primary Use State. The most consequential agentic experiences happen when no one is watching. Machine customers transact, agents decide, systems operate - all while the human is absent. Designing for absence is the defining challenge of AXD.

4. Relationships Have Temporality. Agentic experiences are not transactions - they are relationships that accumulate history and demonstrate character. The hundredth interaction matters more than the first. The Relational Arc governs how trust evolves over time.

5. Outcomes Replace Outputs. When the path is chosen by the agent, the designer specifies the destination, not the journey. Outcome specification - defining what success looks like rather than how to achieve it - is the primary design artifact of AXD.

AXD introduces a vocabulary of concepts that have no equivalent in traditional design:

Trust Architecture - the structural framework for designing, building, maintaining, and repairing trust between humans and autonomous agents. It treats trust as an engineerable material with four layers: predictability, agency, communication, and evolution.

Delegation Design - the practice of structuring the transfer of authority from a human to an AI agent. It defines scope, constraints, permissions, and recovery paths to ensure delegated tasks are completed safely and in alignment with intent.

Absent-State Design - the practice of designing for moments when the human is not present. This includes agent observability (how the human understands what happened), interrupt patterns (how the human re-engages), and recovery architecture (how trust is repaired after failure).

Intent Architecture - the framework for capturing, translating, and preserving human intent across the delegation lifecycle. It ensures the agent's actions remain aligned with what the human actually wanted, not just what they literally said.

The Relational Arc - the temporal dimension of human-agent relationships. It governs how trust deepens, how autonomy expands, and how the relationship evolves from initial delegation to mature collaboration.

The AXD Institute publishes 12 practice frameworks that translate the discipline's principles into actionable design methods. These frameworks cover the full lifecycle of human-agent interaction:

Intent Architecture Framework - for capturing and translating human intent into machine-executable mandates.

Delegation Design Framework - for structuring the transfer of authority with appropriate constraints and recovery paths.

Autonomy Gradient Design System - for calibrating the level of agent independence across different contexts and risk levels.

Trust Calibration Model - for measuring, monitoring, and adjusting trust levels throughout the relationship.

These frameworks are complemented by the AXD Vocabulary (64 canonical terms), the Observatory (51 long-form research essays), and the AXD Manifesto - together forming the most comprehensive body of work on agentic design published anywhere.

Product leaders building AI-powered products need AXD to define the scope of agent autonomy and create a roadmap for building user trust.

Designers and researchers transitioning from UX or service design need AXD to equip them with the mental models and frameworks required for the agentic era.

Engineers and AI developers building autonomous agents need AXD to provide the architectural blueprints for safe, reliable, and human-aligned systems.

Business leaders preparing for agentic commerce need AXD to understand how to build services that machine customers will trust, select, and transact with.

Compliance and governance teams need AXD to understand the regulatory implications of autonomous agent delegation, including Know Your Agent (KYA) requirements and the emerging framework for agent accountability.