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 |
Honest uncertainty disclosure. When an agent acknowledges what it does not know - 'I found three options but could not verify the fourth supplier' - it signals a level of honesty that builds deeper trust than any performance metric. Humans trust agents that acknowledge their limitations more than agents that claim omniscience.
Traditional UX trust indicators are visual cues on an interface - security badges, brand logos, professional design. Trust signals in AXD are behavioural properties of the agent's actions and communication. They operate when the human is absent and must be verified through audit trails rather than visual inspection. The shift is from interface-based trust to relationship-based trust.
The signal system must be designed, but individual signals can and should be automated. The AXD designer specifies what signals the agent should emit, under what conditions, and at what frequency. The agent then generates those signals automatically based on its actual behaviour. The key requirement is that automated signals must be verifiable - the human must be able to confirm that the signal reflects reality.
In traditional software, trust is communicated through interface cues: security badges, brand recognition, professional design, social proof. These signals work because the human is This is a fundamental shift. Trust signals move from being visual properties of an interface to being behavioural properties of a relationship. The AXD designer must design agents that signal trustworthiness through what they do, not just how they look. Trust signals in agentic systems fall into four categories, each operating at a different layer of the human-agent relationship: A critical challenge in trust signal design is Performative trust signals are worse than no signals at all. They create a false sense of security that leads to over-delegation, which leads to larger failures, which leads to deeper trust collapse. The AXD designer must ensure that trust signals are This requires three design principles. First, Trust signals must be frequent enough to maintain trust but infrequent enough to avoid attention fatigue. This is the Too few signals, and the human loses visibility into the agent's behaviour. Trust erodes through opacity accumulation. Too many signals, and the human becomes overwhelmed, stops reading them, and the signals become meaningless noise. Trust erodes through relationship fatigue. The optimal signal frequency is not fixed - it varies with the maturity of the relationship, the consequence level of the agent's actions, and the human's individual attention capacity. Early in the relationship, more frequent signals are appropriate - the human is still calibrating their trust and needs more evidence. As the relationship matures, signal frequency can decrease - the human has accumulated enough evidence to trust with less frequent confirmation. Designing adaptive signal frequency - systems that automatically calibrate the volume and detail of trust signals to the relationship's current state - is one of the most sophisticated challenges in AXD. It requires the system to