The Interconnected Systems Environment (ISE) is a formal, graph-based framework for modelling how AI outputs propagate through enterprise systems.
Introduced by Myriam Ayada (2026), it represents an organisation’s AI-integrated infrastructure as a directed graph G = (V, E) where each node is a system and each edge is a corridor: a boundary where outputs transform into inputs for the next system.
Certain failure modes in AI-integrated environments arise not within systems, but at the boundaries between them.
ISE makes these boundary transformations explicit and analysable.
Current AI monitoring watches individual systems: modela ccuracy, data quality, component metrics. This is necessary but insufficient. When AI outputs cross system boundaries, meaning changes.
For example, let us consider a credit scoring pipeline (see figure below). An applicant with a risk score of 0.39 vs 0.37 may be indistinguishable to the AI. However to a categorisation engine with a threshold at 0.38, one produces MEDIUM and the other LOW. ISE shifts attention from “is the model right?” to “what happens to the output after it leaves the model?”
The fundamental driver of agentic AI integration complexity is an architectural impedance mismatch. Legacy databases and rules engines rely on deterministic, spec-closed interfaces. Meanwhile, Generative AI systems produce probabilistic, semantically open outputs.
The ISE framework formalises this mismatch at the corridor level, proving that integration failures, often resulting in downstream structural and format failures, occur precisely where semantic latitude is violently quantised by a legacy threshold.
Nodes: Systems, each a black box with defined input/output interfaces.
Edges (Corridors): Connections characterised by transformation operators capturing interface mechanisms: schema mapping, thresholding, formatting, truncation, routing logic.
Spec-closed: Exactly one valid output Y(x) per input x. Classical deterministic systems. For every input x,|Y(x)| = 1. (Ayada, 2026, Def. 3.1)
Semantically open: Multiple valid outputs per input. AI systems, especially NL or probabilistic, are theprimary source. ∃ input x where |Y(x)| > 1. (Ayada, 2026, Def. 3.2).
Discretisation corridors: Map continuous to categorical. Primary danger zone for ABO propagation.
Feedback corridors: Close loops, feeding outcomes back to upstream calibration. Enable drift persistence.
Critical Risk Cluster: A connected subgraph with (1) at least one AI-source node with a semantically open interface and (2) coherence-risk score exceeding threshold for sustained duration (Ayada, 2026, Def. 4.2). Identifies where ambiguity can and is accumulating.
Blast Radius: The h-hop neighbourhood of a CRC is the set of downstream systems affected if propagation continues (Ayada, 2026, Def. 4.3). Provides a controlvariable for containment scope.
ABO Concept →/research/ambiguity-bearing-outputs
ISCIL Architecture→ /research/iscil-containment-architecture
Glossary →/research/glossary
Ayada, M. (2026). Propagation of Ambiguity-Bearing Outputs Across Interconnected Systems Environment. TechRxiv (in review).
Code: github.com/Myr-Aya/ISE_simulator
Archive: Zenodo DOI 10.5281/zenodo.18719967