Delegation Design: How Humans Authorise AI Agents

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 Delegation Design: How Humans Authorise AI Agents

How do delegation design: how humans authorise ai agents relate to agentic commerce?

  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
DimensionTraditional UXAgentic Experience Design (AXD)
Primary materialAttention and affordanceTrust and delegation
User statePresent, navigatingAbsent, delegating
Design outputScreens and interfacesOutcomes and constraints
Temporal modelSession-basedRelationship-based
Success metricTask completionTrust calibration

Frequently Asked Questions

What is delegation design?

Delegation design is the practice of structuring how a human grants authority to an autonomous AI agent. It defines scope (what the agent may do), constraints (what it must not do), permissions (what resources it may use), and recovery paths (what happens when things go wrong).

Why is delegation design important for agentic AI?

Every agentic AI system begins with an act of delegation. Without structured delegation design, organisations face over-delegation (granting too much authority, leading to failures) or under-delegation (constraining too tightly, leading to abandonment). Delegation design makes the transfer of authority safe, calibrated, and recoverable.

What are the four components of a delegation?

Every delegation has four structural components: scope (what the agent is authorised to do), constraints (hard boundaries it must never cross), permissions (resources and capabilities it may use), and recovery paths (what happens when errors occur).

How does delegation design relate to trust architecture?

Delegation design and trust architecture are the two foundational concepts of Agentic Experience Design. Trust architecture governs how trust is built and maintained. Delegation design governs how authority is transferred based on that trust. Together they form the structural foundation for safe human-agent relationships.

Key Takeaways

Every agentic AI system begins with an act of delegation - a human granting permission for autonomous action. This act is the most consequential design surface in the entire system. Get it wrong, and the agent operates outside its intended boundaries. Get it right, and the human can confidently step away, knowing the agent will act within the authority granted. Traditional software design assumes the user is present and in control. Delegation design assumes the user is Every delegation in an agentic system has four structural components: What is the agent authorised to do? Scope defines the boundaries of the agent's operational envelope - the tasks it may perform, the domains it may operate in, and the decisions it may make. A shopping agent's scope might include "find and purchase running shoes under £120" but exclude "negotiate payment terms with the retailer." What must the agent not do? Constraints are the hard boundaries that the agent must never cross, regardless of how it interprets its goals. Budget limits, time boundaries, ethical guardrails, and regulatory requirements are all constraints. Constraints are non-negotiable - they override the agent's optimisation logic. What resources may the agent use? Permissions define the tools, data, APIs, and capabilities available to the agent. A financial agent might have permission to access market data and execute trades but not to transfer funds between accounts. Permissions are the capability layer of delegation. What happens when things go wrong? Recovery paths define the agent's behaviour when it encounters errors, ambiguity, or situations outside its scope. Options include escalation to the human, graceful degradation, automatic rollback, and constraint tightening. Recovery paths are the safety net of delegation design. Delegation design recognises several recurring patterns in how humans transfer authority to agents: The most common pattern. The human defines clear scope, constraints, and permissions. The agen

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)