Onboarding and Capability Discovery Framework

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.

What is Onboarding & Capability: Core Principles?

What is Onboarding & Capability: Implementation Patterns?

What is Onboarding & Capability: Commerce Applications?

What is Onboarding & Capability: Guidance for Teams?

Key concepts in Onboarding & Capability Discovery Framework | AXD Practice

How do onboarding & capability discovery framework 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 the Onboarding and Capability Discovery framework?

The Onboarding and Capability Discovery framework is an AXD methodology for designing how humans and AI agents establish their initial relationship. It covers the critical first interactions where trust is formed, capabilities are demonstrated, authority is first delegated, and expectations are set for the ongoing relationship.

Why is agent onboarding different from traditional software onboarding?

Traditional onboarding teaches users how to use an interface. Agent onboarding establishes a trust relationship: the human must understand what the agent can do, what it cannot do, how it will communicate, and what authority it needs. This is closer to onboarding a new employee than learning a new app.

What are the key phases of agent onboarding?

Agent onboarding has four phases: introduction (the agent explains its capabilities and limitations), demonstration (the agent performs low-stakes tasks to build initial trust), calibration (the human adjusts authority and preferences based on demonstrated competence), and graduation (the agent transitions to its intended autonomy level with full delegation).

Key Takeaways

Framework 11 of 12 · Entry Phase · Mental model formation Onboarding & Capability Discovery Framework Teaching humans how to delegate, not how to navigate Commerce Application: Agent capability calibration Traditional product onboarding teaches users how to navigate. Agentic onboarding must teach something fundamentally different: how to delegate. Users must form accurate mental models of agent capability, understand what kinds of goals the agent can pursue, and calibrate expectations before experiencing disappointment or misplaced trust. Traditional onboarding teaches users how to use a product. Agentic onboarding teaches users how to trust a partner. The skills are fundamentally different: not clicking and navigating, but specifying, delegating, and evaluating. Onboarding & Capability: Implementation Patterns Onboarding & Capability: Commerce Applications The most expensive onboarding failure is not a user who churns. It is a user who stays but never delegates beyond the simplest tasks because their first experience set the wrong expectations. Onboarding & Capability: Guidance for Teams Onboarding & Capability: Lifecycle Connections Onboarding teaches humans how to delegate. The final framework - Ethical Constraint & Value Alignment Architecture Onboarding & Capability: 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

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)