Human-Agent Interaction Models

By Tony Wood, Founder — AXD Institute, Manchester, United Kingdom

What is Agentic Experience Design?

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.

How does AXD differ from traditional UX?

Why is trust architecture important for agentic AI?

Key concepts in Human-Agent Interaction Models | HITL HOTL | AXD

How do human-agent interaction models relate to agentic commerce?

• human-agent interaction models
• what interaction models exist for human-agent relationships
• interaction models change as trust increases

• Trust Architecture
• Delegation Design
• How To
• Playbook
• Practice/Autonomy Gradient

1. Agency requires intentional delegation — every agentic system begins with a designed act of delegation
2. Trust is the primary material — AXD works in trust rather than attention
3. Absence is the primary use state — the most consequential experiences happen when no one is watching
4. Relationships have temporality — agentic experiences accumulate history over time
5. Outcomes replace outputs — AXD designers specify results, not interfaces

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

Frequently Asked Questions

What interaction models exist for human-agent relationships?

AXD defines several interaction models: Delegation (human assigns task to agent), Supervision (human monitors agent activity), Collaboration (human and agent work together), Interruption (agent requests human input), and Recovery (human intervenes after agent failure). Each model has distinct design requirements.

How do interaction models change as trust increases?

As trust increases, interaction models shift from high-oversight to high-autonomy: initial relationships use Supervision and Collaboration models, mature relationships use Delegation with minimal interruption, and highly trusted relationships use full Delegation with exception-only reporting. The Autonomy Gradient maps this progression.

Key Takeaways

Every agentic experience exists somewhere on a spectrum between full human control and full agent autonomy. AXD identifies three canonical interaction models that define this spectrum. Each model carries different requirements for

References and Citations

Gartner: Machine Customers Will Be a Multibillion-Dollar Opportunity Harvard Business Review: The Age of AI Agents McKinsey: The State of AI in 2024 About the AXD Institute Contact Us Email the AXD Institute Tony Wood on LinkedIn Tony Wood on X (Twitter)