Intentionality is a Design Decision: Measuring Functional Intentionality for Accountable AI Systems

2026-05-06

AI Summary

Current AI systems increasingly exhibit intention-like behaviors, yet the absence of standardized metrics to quantify their functional intentionality hinders effective governance and accountability. This work conceptualizes intentionality as a designable and measurable system property, offering an observable definition grounded in purposiveness, foresight, volition, temporal commitment, and behavioral consistency. It introduces the Functional Intentionality Test (FIT) and its accompanying evaluation protocol, FIT-Eval. By integrating architectural indicators—such as memory persistence, planning depth, and tool autonomy—the study establishes a multidimensional, interpretable framework for quantifying and tiering intentionality. This enables proportionate, intentionality-aware regulation of AI systems and provides theoretical and methodological foundations for calibrating autonomy.

Abstract

As AI systems increasingly exhibit autonomous, goal-directed, and long-horizon behavior, users lack a standardized way to detect the degree to which a system functions like an intentional actor for governance and accountability purposes. This position paper defines intentionality not as consciousness, but as a behavioral profile characterized by purpose, foresight, volition, temporal commitment, and coherence - criteria long used in legal and philosophical contexts to infer intent. These properties are design-contingent: architectural choices such as memory persistence, planning depth, and tool autonomy shape the degree to which systems exhibit organized goal pursuit. If intentionality is design-contingent, it is in principle controllable. Yet control requires measurement. We introduce the Functional Intentionality Test (FIT), a multidimensional framework that quantifies intentional-like behavior across five observable dimensions, and propose FIT-Eval, a structured evaluation protocol for eliciting and scoring them. While reduced human agency can increase efficiency, rising intentional capacity heightens accountability risks. By translating intentionality into interpretable levels, FIT enables proportionate oversight and deliberate autonomy calibration in increasingly agentic systems.

Problem

• intentionality
• accountability
• AI governance
• autonomous systems
• behavioral measurement

Innovation

• Functional Intentionality
• Accountable AI
• Autonomy Calibration
• Behavioral Measurement
• Intentionality Test