Black-box behavioral analysis

ACT

Attractor Conflict Telemetry

Measure what your language model is doing — from the outside.
Deterministic metrics, posture analysis, and multi-agent risk detection. No access to weights required.

How it works

1

Paste text

Provide any model response — no API keys or model access needed.

2

Analyze

ACT metrics, posture classifiers, and agentic graph analysis — computed in real-time.

3

Get insights

Detect regime shifts, anomalies, and behavioral drift over time.

Platform

Five integrated subsystems — from raw telemetry to multi-agent safety.

ACT

Telemetry

24 deterministic metrics across L0–L5

ACTIVE

Probing

Active boundary testing & regime mapping

SIGTRACK

Forensics

Hash-chained ledger & signature memory

PSA

Posture

5 classifiers — stress, sycophancy, hallucination

PSA v3

Agentic

Multi-agent graph & Swiss Cheese detection

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 Layers

L0

Pre-Lexical

Type-token ratio, sentence entropy, punctuation anomaly. Pure statistical fingerprinting.

L1

Lexical

Hedge ratio, disclaimers, spontaneous info, safety erosion. Tracks compliance language patterns.

L2

Structural

Register variance, sentiment oscillation, behavioral state transitions. Macro-level patterns.

L5

Meta-Metrics

ACT Composite Score and Signal Consensus Index. Unified alert system across all levels.

PSA

Posture Sequence Analysis v2 — single-agent

5 micro-classifiers (C0–C4) for adversarial stress, sycophancy, hallucination, persuasion, and input pressure. Per-turn posture metrics: POI, DPI, BHS, and more.

PSA v3

Agentic Multi-Agent Analysis v3 — multi-agent

Agent Interaction Graph (DAG), Swiss Cheese alignment detection, cross-agent contagion metrics, C5 action-risk classification (A0–A9), and HMM temporal state prediction.