ISCIL: Inter-System Coherence & Integrity Layer

What is ISCIL?

The Inter-System Coherence & Integrity Layer (ISCIL) is a containment architecture that detects and dampens environment-level drift in AI-integrated enterprise systems. Introduced by Myriam Ayada (2026).

ISCIL operates at boundaries between systems. It does not inspect individual outputs, gate execution paths, or attempt to eliminate AI outputs' semantic openess.

Design Philosophy: Coherence, Not Correctness

A healthy immune system does not achieve sterility but maintains homeostasis despite foreign agents. ISCIL’s success metric is not absence of ABOs but the environment’s ability to absorb small deviations without amplification, prevent uncontrolled propagation, and restore alignment within acceptable timeframes.

This reframes AI risk from reactive fault handling to proactive coherence preservation.

ISCIL Overview

ISCIL functions as an immunity layer: monitoring aggregate boundary statistics, detecting abnormality patterns, tolerating normal variation, and applying proportional containment. The below figure illustrates an example of how ISCIL can be implemented for a credit scoring pipeline (see more about Interconnected System Environment).

ISCIL — INTER-SYSTEM COHERENCE & INTEGRITY LAYER Immunity, not sterility. Coherence, not correctness. ISCIL CONTAINMENT LAYER CRS MONITOR CRS = 0.4 (normal) 1.0 ALERT ZONE AI SCORER Semantically open score = 0.39 T CATEGORISER Rules engine 0.39 → MEDIUM T DECISION Approve / Deny MEDIUM → Review T CALIBRATION Portfolio metrics FEEDBACK (damped by ISCIL) ISCIL FOUR-STEP MECHANISM 1 Boundary Telemetry Monitors aggregate stats at each corridor 2 Coherence-Risk Score Rate-of-change detection via z-scores 3 Corridor Containment Guardrails + feedback damping in CRC only 4 Proportional Response Scales with severity. Relaxes when stable. SIMULATION RESULTS 39 excess defaults eliminated 100% drift recovery 6.5% operational overhead 40 timesteps faster detection T = ISCIL boundary telemetry sensor (non-intrusive, no output inspection) mind-xo.com/research

How ISCIL works

Operational Process

Step 1: Boundary Telemetry
Monitors aggregate behavioural statistics at corridor boundaries: approval rates, category proportions, escalation rates, feedback magnitudes. No individual output is inspected. Operates without proprietary model internals.

Step 2: Coherence-Risk Scoring
Uses rate-of-change z-scores relative to a rolling baseline. Detects acceleration above normal variability. Seasonal or market-driven level shifts do not trigger alerts (Ayada, 2026).

Step 3: Corridor-Level Containment
Discretisation guardrails:
Blind scalar offset before discretisation boundaries, steering outputs away from jump-susceptible thresholds.
Feedback damping: Asymmetric attenuation; corrective signals boosted, amplifying signals dampened.

Step 4: Proportional Response
Containment scales with severity. Applied only within detected CRC. Blast radius expanded only if risk persists. Relaxes autonomously once stability returns.

Design Constraints

1. Interface-level: No internal model inspection. Works with any system producing boundary outputs.

2. Non-intrusive: No synchronous gating except during active containment.

3. Graph-native: Acts on ISE corridor structure.

Simulation Results

In a simulation that replicates a realistic AI-integrated underwriting pipeline, e.g. four interconnected systems processing loan applications over 1,200 decision cycles, we measured what happens when a single AI output carries just enough ambiguity to pass local checks but shift downstream behaviour. Below the main results:

All excess defaults eliminated (100% recovery)
78 timesteps active intervention (6.5% overhead)
Detection at ~t=50~40 timesteps faster than outcome monitoring
Direction-agnostic: detectedboth ABO onset and cessation

Beyond Brittle Semantic Contracts

To prevent context clash and downstream errors, many MLOps teams attempt to write rigid “semantic contracts”or force strict JSON schemas. This approach attempts to achieve sterility by breaking the pipeline whenever ambiguity occurs.
ISCIL offers an alternative: instead of brittle semantic contracts that destroy the utility of Generative AI, ISCIL acts as a continuous immunity layer, dampening drift dynamically without requiring absolute determinism.

What ISCIL Complements

Approach What It Does ISCIL Relationship
MLOps monitoring Watches model performance ISCIL watches between models
Spec-closure Constrains output format ISCIL covers where spec-closure isn't feasible
Hardened boundaries Reduces jump susceptibility Doesn't address feedback persistence
Human review Semantic interpretation ISCIL enables selective, not blanket, review

Learn More

Check the key concepts

ABO Concept /research/ambiguity-bearing-outputs
ISE Framework →/research/interconnected-systems-environment
Glossary →/research/glossary

Source & Citation

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