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 Ethical Constraints framework is an AXD methodology for embedding ethical boundaries into autonomous AI agent behaviour. It defines three layers of constraints: inviolable rules (hard-coded ethical limits), contextual guidelines (situation-dependent ethical considerations), and preference-based ethics (alignment with the principal\'s values).
Ethical constraints are enforced through layered mechanisms: hard constraints are coded as immutable rules that override all other instructions, contextual constraints use situation assessment to determine appropriate behaviour, and preference constraints are learned from the principal\'s demonstrated values. The framework ensures ethical behaviour even in novel situations.
Traditional AI ethics focuses on training data bias and output fairness. Agentic systems face additional ethical challenges: they make autonomous decisions, handle real resources, and affect real people without human oversight. The Ethical Constraints framework addresses these unique challenges by designing ethics into the agent\'s decision architecture.
Framework 12 of 12 · Constitutional Phase · Moral character Ethical Constraint & Value Alignment Architecture The encoding of moral character into autonomous systems Commerce Application: Fair trading and value alignment Domains: All Domains · Regulated Industries The design of what the system should never do even when functioning perfectly - the encoding of organisational values, regulatory obligations, and ethical commitments into agentic behaviour as first-class design artefacts. Unlike failure architecture, which is reactive, this framework is constitutive. It defines the moral character of the agent system from the ground up. The most important design decision in any agentic system is not what the agent can do. It is what the agent must never do - even when asked, even when it would be profitable, even when no one is watching. Ethical Constraint &: Implementation Patterns Ethical Constraint &: Commerce Applications Ethics in agentic systems cannot be an afterthought bolted onto a working system. They must be constitutive - woven into the fabric of every decision the agent makes, from the first line of code to the last. Ethical Constraint &: Lifecycle Connections Ethical Constraint & Value Alignment is the constitutional framework that governs all others. Return to the beginning of the lifecycle with Ethical Constraint &: 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