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 |
AI agents will plan and book travel by querying APIs, evaluating structured inventory data, and constructing optimal itineraries based on delegated preferences - optimising across price, schedule, comfort, loyalty value, and carbon footprint simultaneously, shifting competition from search marketing to API-first inventory access.
Yes - agents can monitor flight status, detect disruptions before travellers are aware, evaluate rebooking options across carriers, rebook within delegated constraints, arrange alternative accommodation, and file compensation claims - all without human intervention, representing a pure zero-click commerce application.
Hotels should publish room-level structured data (accessibility, amenities, specifications), build API-first booking and modification interfaces, publish verifiable quality signals (satisfaction scores, service metrics), and design for programmatic disruption management and compensation processing.
Guest satisfaction scores, repeat booking rates, service response times, on-time performance data, cancellation policy clarity, disruption handling quality, and verified review sentiment - all published in machine-queryable structured formats that agents can evaluate against traveller preferences.
AI travel agents will reduce dependence on OTA platforms by booking directly with providers that offer API-first inventory access. Travel providers with machine-readable inventory and programmatic booking capability can bypass OTA intermediation, while those without will become more dependent on aggregators.
Travel planning is one of the most time-consuming consumer tasks - researching destinations, comparing flights, evaluating hotels, coordinating schedules, and managing bookings across multiple providers. The average leisure trip involves dozens of micro-decisions spread across multiple platforms. This complexity is precisely what makes travel an ideal domain for An AI travel agent can optimise across dimensions that humans cannot process simultaneously This shifts the competitive battleground for airlines, hotels, and travel platforms from Travel disruption - flight cancellations, delays, overbookings, weather events - is where agentic commerce delivers its most compelling value. A human traveller stranded by a cancelled flight faces hours of phone queues, limited rebooking options, and stress-driven decision-making. An AI agent can respond in seconds. Autonomous disruption management requires real-time data access and pre-authorised action authority. The agent must monitor flight status, detect disruptions before the traveller is aware, evaluate rebooking options across all available carriers, rebook within the traveller's constraints (budget, schedule, preferences), arrange alternative accommodation if needed, and file compensation claims - all without human intervention. Hotels and hospitality providers face a specific challenge in agentic commerce: their product is experiential, and experiences are difficult to express in structured data. A hotel's "ambiance," "location feel," or "service quality" are subjective attributes that resist machine-readable encoding. Yet agents must evaluate and compare these properties to make booking decisions. Room-level structured data becomes essential. Agents booking on behalf of travellers with specific needs - accessibility requirements, noise sensitivity, view preferences, workspace needs - require room-level attribute data that goes far beyond standard room categories. Hotels that publish detailed, structured room specificat