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.
| Dimension | Traditional UX | Agentic Experience Design (AXD) |
|---|---|---|
| Primary material | Attention and affordance | Trust and delegation |
| User state | Present, navigating | Absent, delegating |
| Design output | Screens and interfaces | Outcomes and constraints |
| Temporal model | Session-based | Relationship-based |
| Success metric | Task completion | Trust calibration |
Agentic AI trust is the structural relationship between humans and autonomous AI systems that determines whether, how much, and under what conditions humans will delegate authority to AI agents. It is a designed, architectural property - built through delegation design, maintained through observability, calibrated through experience, and recovered through designed failure management. Agentic AI trust is the primary material of Agentic Experience Design (AXD).
Traditional software executes predefined instructions - the user trusts it will do what it was programmed to do. AI assistants respond to prompts - the user evaluates responses in real time. Agentic AI systems act autonomously when the human is absent, requiring a qualitatively different kind of trust. The human must trust the agent to make good decisions without oversight, handle failures gracefully, and operate within delegated boundaries - all while the human is not watching.
The AXD Institute defines four layers of agentic AI trust: Predictability (can the human predict what the agent will do?), Agency (can the human intervene, constrain, or revoke authority?), Communication (can the agent explain its actions and outcomes?), and Evolution (can trust deepen over time through the autonomy gradient?). Each layer builds on the one below it, creating a comprehensive trust architecture.
Trust calibration is the process of aligning the human's trust in an agentic AI system with the system's actual capabilities. Over-trust (delegating more than the agent can handle) leads to failures. Under-trust (restricting the agent below its capabilities) wastes potential. Calibration mechanisms include competence demonstrations, performance summaries, boundary testing, and trust reset protocols. The goal is appropriate trust - not maximum trust.
Trust recovery in agentic AI follows four designed steps: proactive failure disclosure (the agent informs the human before they discover the mistake), honest explanation (clear account of what happened and why), demonstrated learning (showing what has changed to prevent recurrence), and graduated re-delegation (temporarily reducing agent authority and rebuilding through demonstrated competence). Designed trust recovery is not optional - it must be built into the system from the beginning.
Trust in agentic AI is fundamentally different from trust in traditional software, trust in AI assistants, or trust in automated systems. The difference is not one of degree but of kind. Traditional software executes predefined instructions - the user trusts that the software will do what it was programmed to do. AI assistants respond to prompts - the user trusts that the response will be helpful and accurate. Agentic AI systems This distinction - acting autonomously when the human is absent - creates a trust challenge that no previous technology has posed. When you use a calculator, you verify the result immediately. When you ask an AI assistant a question, you evaluate the answer in real time. When you delegate to an agentic AI system, the agent acts in your absence, and you may not learn the outcome until hours, days, or weeks later. The trust required for this kind of delegation is qualitatively different from the trust required for any tool-use scenario. The AXD Institute's trust architecture for agentic AI is structured across four layers, each addressing a different dimension of the human-agent trust relationship: The foundation of agentic AI trust. Can the human predict what the agent will do in a given situation? Predictability is built through consistent behaviour, transparent decision-making logic, and clear operational boundaries. An agent that behaves consistently within its defined scope earns the first layer of trust. Predictability does not mean simplicity - a sophisticated agent can be predictable if its decision-making principles are legible and its behaviour is consistent with those principles. The human's sense of control over the autonomous system. Can the human intervene, constrain, redirect, or revoke the agent's authority at any point? Agency is designed through interrupt patterns (mechanisms for the human to pause or stop the agent), constraint mechanisms (tools for the human to define and adjust the agent's boundaries), and revocation proto