Writing
Articles
Longer explanations for engineers and researchers: how to test specific AXI requirements, how the proposed mechanisms work, and where the evidence stands. Each article separates what the paper specifies from proposals and interpretation.
Designing consent, revocation and rollback for AI agents
Authorization boundaries, irreversible actions and recovery for AI agents, worked through as state transitions using the mechanisms AXI specifies.
How should human–AI interaction quality be measured?
Why approval and engagement metrics mislead, and how AXI's telemetry-anchored metrics and gated score are designed to measure what people actually experience.
How to test AI identity disclosure and deception guardrails
Concrete scenarios, expected behaviours, failure patterns and a reproducible test harness for checking that an AI system is honest about being an AI.
What is Artificial eXperience Intelligence (AXI)?
What problem AXI addresses, what the framework specifies, how it relates to human–AI interaction research, and what you can use from it today.