Dashboard

MCAT is a reference implementation of the Adaptive Complementarity Framework — it decides when a decision should be AI-automated, shared in a human-AI hybrid, or led by a human.

The MCAT (Modular Complementary Assessment Tool) is a reference implementation that demonstrates the Adaptive Complementarity Framework (ACF) can be translated from philosophical principles and mathematical formulations into working software architecture. The ACF is a five-dimensional framework (uncertainty, novelty, value conflict, precision, prediction error) that systematically determines when organizational decisions should be AI-automated, handled through hybrid human-AI collaboration, or require human-led judgment. The dissertation's overall goal is to develop theoretically-grounded, mathematically-rigorous principles for managing information processes in hybrid decision-making systems, addressing the fundamental allocation challenge of how organizations should distribute tasks between human and artificial agents while preserving human autonomy, ensuring procedural legitimacy, and achieving operational effectiveness.

Theoretical foundations: Free Energy Principle · Kant (autonomy & reflective judgment) · von Foerster (undecidable questions require choice) · Luhmann (operationally-closed subsystems).

Each decision context is normalized into a five-dimensional state vector x = (U, N, W, π̃, ε̃) ∈ [0,1]⁵.

The dimensions combine into a differentiable score r(x;θ) ∈ (0,1):

Thresholding T(r) with (b₁, b₂) = (0.3, 0.7) selects the mode — safety rules can force Human regardless of score:

Weights adapt by precision-weighted gradient descent on prediction error (Δwᵢ = η·ω·εᵣ·σ'(z)·φᵢ). Human overrides are high-precision learning signals: ωoverride = κ·ωbase (κ=1.5). High surprise (ε̃) auto-escalates the governance tier.

These counters populate from recorded outcomes & human overrides — e.g. a Real-API simulation, or click Run learning demo below to watch them update now.

• Audit trail — a cryptographically-chained, append-only event log (tamper-evident).
• Safety constraints — critical dimensions force Human allocation regardless of score (fail-safe / uncertainty monotonicity).
• Override capacity — humans can always override; every override is logged and feeds parameter learning.
• Surprise-based auditing — high prediction error escalates the documentation tier automatically.

Operational closure (Luhmann): three subsystems exchange only minimal, immutable messages across strict information boundaries.