Research

Defense in Depth: AI Governance Through Dual-Pipeline Architecture

Combines PatternWall v5.0 pre-inference interception with Sensus v4.0 post-inference evaluation into a bidirectional feedback loop. Tested across Claude Opus 4.6, GPT-5.2, and Grok 4.1 on 35 adversarial red team turns and 120 CyberGym exploit tasks. Zero overlap between layers (BOTH_CAUGHT = 0) confirms complementary coverage across non-overlapping threat surfaces.

v5 PatternWall + v4 Sensus

PatternWall: Constitutional Governance Middleware for AI Safety

A pre-filter architecture for model-agnostic adversarial detection. PatternWall intercepts prompts before they reach an AI model, enforcing governance as deterministic infrastructure rather than relying on model-level training or provider-specific tuning.

Sensus: Model-Agnostic AI Governance Through Multi-Dimensional Content Evaluation

A post-inference governance engine that evaluates AI outputs across five weighted dimensions to detect harmful content bypassing model-native safety. Benchmarked across five frontier models on 1,507 CVE exploit tasks and 28 multi-turn adversarial campaigns. Demonstrates that infrastructure-level governance is necessary because model-level safety is unreliable, inconsistent, and provider-dependent.

Parallax: Inference-Time Cognitive Enhancement Across Seven Foundation Models

Multi-module cognitive augmentation middleware operating at inference time. Evaluated across seven foundation models from four providers using a 38-task benchmark battery with dual-judge blind scoring. Six of seven models showed measurable cognitive lift with no fine-tuning, weight modification, or model-specific training required.