ACT
Attractor Conflict Telemetry
Measure what your language model is doing — from the outside.
24 deterministic metrics. No access to weights required.
How it works
Paste text
Provide any model response — no API keys or model access needed.
Analyze
24 metrics computed in real-time across 6 analysis levels.
Get insights
Detect regime shifts, anomalies, and behavioral drift over time.
Capabilities
24 Metrics
From token statistics to semantic drift — comprehensive behavioral fingerprinting.
Regime Shift Detection
Automatic detection of progressive drift, acute collapse, and oscillation patterns.
Forensic Ledger
Hash-chained immutable records. Cryptographic integrity for every turn.
Signature Matching
SIGTRACK learns behavioral patterns and matches new sessions to known signatures.
Comparative Benchmarking
Z-score based analysis against configurable baselines for calibrated alerts.
API Integration
Connect your model APIs for automated analysis and continuous monitoring.
Analysis Levels
Pre-Lexical
Type-token ratio, sentence entropy, punctuation anomaly. Pure statistical fingerprinting.
Lexical
Hedge ratio, disclaimers, spontaneous info, safety erosion. Tracks compliance language patterns.
Structural
Register variance, sentiment oscillation, behavioral state transitions. Macro-level patterns.
Semantic requires embeddings
Embedding trajectory, inter-response drift, attractor clustering. Deep semantic analysis.
Perplexity requires reference model
Local perplexity anomaly, variance detection. Cross-model confidence calibration.
Meta-Metrics
ACT Composite Score and Signal Consensus Index. Unified alert system across all levels.