Designing for AI Autonomy

What is AXD Framework: Agentic Design Principles?

The practice of creating systems, frameworks, and experiences that enable autonomous agents to operate effectively within designed boundaries..

What is Sections?

What is The Absent State: When No One is Watching?

What is Operational Envelopes: Boundaries as Enablers?

What is Trust Architecture for Autonomous Systems?

Key concepts in AXD Framework: Agentic Design Principles

How do axd framework: agentic design principles 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

How should AI autonomy be designed in agentic systems?

AI autonomy should be designed as a graduated spectrum, not a binary switch. The Autonomy Gradient Design System in AXD provides five levels from fully supervised to fully autonomous, with clear criteria for when an agent should operate at each level. The design challenge is calibrating the right level of autonomy for each task, context, and trust relationship.

What is the relationship between autonomy and trust in AI?

Autonomy and trust are reciprocal in agentic systems. Greater trust enables greater autonomy, and demonstrated competence at lower autonomy levels builds the trust needed for higher levels. This creates a virtuous cycle where agents earn autonomy through reliable performance, and humans grant it through accumulated confidence - a process AXD calls trust calibration.

What risks arise from poorly designed AI autonomy?

Poorly designed autonomy creates two failure modes: under-autonomy (the agent interrupts too frequently, defeating the purpose of delegation) and over-autonomy (the agent acts beyond its competence or authority, causing harm). Both erode trust. AXD addresses this through the Autonomy Gradient, which provides structured criteria for matching autonomy levels to demonstrated capability.

How should AI autonomy be designed in agentic systems?

AI autonomy should be designed as a graduated spectrum, not a binary switch. The Autonomy Gradient Design System in AXD provides five levels from fully supervised to fully autonomous, with clear criteria for when an agent should operate at each level. The design challenge is calibrating the right level of autonomy for each task, context, and trust relationship.

What is the relationship between autonomy and trust in AI?

Autonomy and trust are reciprocal in agentic systems. Greater trust enables greater autonomy, and demonstrated competence at lower autonomy levels builds the trust needed for higher levels. This creates a virtuous cycle where agents earn autonomy through reliable performance, and humans grant it through accumulated confidence - a process AXD calls trust calibration.

Key Takeaways

There is a paradox at the heart of designing for AI autonomy. The more effectively we design systems that act without us, the more carefully we must design the conditions under which they are permitted to do so. Autonomy, in the context of agentic AI, is not the absence of design - it is the highest expression of it. Every boundary, every operational envelope, every trust calibration mechanism is a design decision that shapes what an autonomous agent can become. The practice of designing for AI autonomy is, therefore, the practice of creating freedom through constraint. This essay explores the emerging discipline of designing for AI autonomy - a practice that sits at the intersection of The stakes are considerable. As agentic AI systems move from experimental prototypes to production deployments, the quality of their autonomous operation will determine whether they create value or destroy trust. An agent that operates brilliantly within its designed boundaries earns the right to expanded authority. An agent that transgresses those boundaries - even once, even slightly - may never recover the trust it has lost. Designing for AI autonomy is designing for this asymmetry: the slow accumulation of trust and the rapid possibility of its destruction. The Absent State: When No One is Watching The dominant operating condition of an autonomous agent is the absent state - the period during which the agent acts without any human observation, guidance, or intervention. This is not an edge case or a failure mode. It is the intended condition. The entire value proposition of agentic AI rests on the premise that agents can create value in the absence of human attention. Absent-state design requires a fundamental shift in the designer's orientation. In traditional user experience design, the designer shapes what appears on screen while the user is present. In agentic experience design, the designer shapes what happens in the world while the user is absent. The design artifact is not

References and Citations

Gartner: Machine Customers as Strategic Technology Trend Stanford HAI: Human-Centered AI Research NIST AI Risk Management Framework About the AXD Institute Contact Us Email the AXD Institute Tony Wood on LinkedIn Tony Wood on X (Twitter)