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 |
The Orchestration Visibility framework is an AXD methodology for designing transparency in multi-agent systems where multiple AI agents collaborate to achieve outcomes. It addresses the unique challenge of making complex agent-to-agent interactions understandable to human principals who need to maintain oversight.
In multi-agent systems, the complexity of agent interactions can quickly exceed human comprehension. Without designed visibility, humans cannot understand how their request was decomposed, which agents are involved, what each agent is doing, and how the overall outcome is being assembled. This opacity undermines trust and accountability.
The framework provides three visibility layers: task decomposition view (how the request was broken into sub-tasks), agent activity view (what each agent is doing and why), and outcome assembly view (how individual agent outputs are being combined into the final result). Each layer can be viewed at different levels of detail.
Framework 06 of 12 · Active operation Phase · Ecosystem legibility Multi-Agent Orchestration Visibility Model Making the invisible choreography of multi-agent systems legible Commerce Application: Supply chain coordination Domains: Enterprise · Banking · Government The architectural reality of enterprise agentic deployment: multiple agents collaborate, hand off tasks, and coordinate toward shared goals. This framework addresses the human experience of agent ecosystems - making the invisible choreography of multi-agent systems legible without overwhelming the user. Multi-Agent Orchestration Visibility: Core Principles The enterprise future is not one agent doing everything. It is many agents, each specialised, collaborating toward shared goals. The design challenge is not the agents - it is making their choreography legible to the humans they serve. Multi-Agent Orchestration Visibility: Implementation Patterns Multi-Agent Orchestration Visibility: Commerce Applications In a multi-agent system, the most dangerous failure is not an agent making a wrong decision. It is two agents making contradictory decisions that neither reports, because each assumed the other was responsible. Multi-Agent Orchestration Visibility: Guidance for Teams Multi-Agent Orchestration Visibility: Lifecycle Connections Multi-Agent Orchestration Visibility: What Comes Next Orchestration Visibility addresses how agents coordinate in the present. The next framework - Agent Memory & Context Continuity Framework Multi-Agent Orchestration Visibility: The Framework Ecosystem Navigate the complete lifecycle of Agentic Experience Design. Each framework addresses a distinct phase of the human-agent relationship. Multi-Agent Orchestration Visibility Model Agent Memory & Context Continuity Framework Explainability & Observability Design Standard Onboarding & Capability Discovery Framework Ethical Constraint & Value Alignment Architecture