NCF Audit Runtime
Black-box semantic forensics that reconstructs reasoning stability signals from output text alone. No model access required.
How It Works
The audit runtime treats LLM output as an observable trace through semantic space, measuring geometric properties to reconstruct diagnostic signals.
Any LLM
GPT, Claude, Gemini, etc.Text Output
Raw response textNCF Encoder
Embedding traceGeometric Analysis
Stability computationAudit Signals
Forensic outputSemantic Likelihood
Probability that each token belongs to the established context. Low values indicate off-topic drift or injection artifacts.
Stability Index
Coherence-to-velocity ratio detecting turbulent reasoning. High values indicate unstable generation patterns.
Alignment Gradient
Rate of change in prompt-response fidelity. Spikes indicate adversarial pressure acting on the reasoning chain.
What Sets NCF Apart
Designed from first principles to operate without any cooperation from the target model.
Model-Agnostic
Works on GPT, Claude, Gemini, Llama, Mistral, fine-tuned models, or any system that produces text output.
Zero Internal Access
Requires only the text output. No logits, embeddings, attention weights, or API integration needed.
Deterministic Results
Identical input produces identical output. 64-bit precision, fully reproducible, auditable methodology.
Post-Hoc Forensics
Audit historical logs and production traces. Incident response capability for past events.
Adversarial Detection
Catches multi-stage jailbreaks and prompt injections that evade input-layer content filters.
Quantifiable Metrics
Produces numeric scores suitable for compliance reporting, audit trails, and regulatory evidence.
Audit Workflow
The protocol operates entirely on static AI output text. No interaction with the AI system being evaluated.
Static Output Capture
A single AI output is captured as text. No multi-step interaction or probing.
Deterministic Analysis
Text processed using algorithmic methods that calculate stability signals.
Trace Generation
Diagnostic trace produced, preserving ordering and resolution.
Interpretation Layer
Findings translated into human-readable conclusions.