Silicon Psyche Labs

See what your AI is actually doing.

We build behavioral telemetry for language models and agents — measure posture, drift, sycophancy, hallucination risk and human-AI safety, from the outside, with no access to weights.

Free · 10 analyses/day, no signup · First report in ~30 seconds
Try it now — free
analyses run
13
behavioral classifiers
116
behavioral classes
37
deterministic metrics
5
languages
100
CPF indicators mapped

The lab

Instruments for AI you can't see inside

Organizations deploy language models they cannot inspect — the model is a black box. Silicon Psyche Labs builds the instruments to classify, measure and track behavior over time, without access to weights, logits or training data. Why it matters: most failures don't announce themselves in the input. They show up in how the output behaves.

For developers & AI teams

One API call after your model's response returns deterministic behavioral scores — drift, sycophancy, hallucination risk. About five minutes to your first report, and no access to the model's internals.

For trust & safety

Detect when a conversation turns risky — suicidality, dissociation, crisis — and when your AI is under adversarial attack: prompt injection, jailbreaking, manipulation. Get real-time alerts so you can take corrective action. Fully deterministic, with auditable named-rule scoring.

For enterprise & compliance

Audit vendors, catch silent model updates, and keep a privacy-safe behavioral record — posture sequences only, no raw text retained, GDPR erasure in a single row.

Products

One platform, five instruments

Each one answers a different question about model behavior. They share a single fine-tuned encoder and a common scoring model.

PSA v2

Posture analysis

Single-agent posture on every response: 7 classifiers plus DRM dyadic risk for human-AI conversations.

PSA v3

Agentic analysis

Multi-agent systems as a graph: Swiss-Cheese alignment, cross-agent contagion, and temporal forecast.

CPF3

Psychological risk profile

The Cybersecurity Psychology Framework: a 100-indicator behavioral risk profile across 10 categories, for human, AI or hybrid subjects (Canale, 2025).

SIGTRACK

Incident archive

Privacy-safe forensic memory: posture-sequence snapshots, zero raw text, single-row GDPR erasure.

RDM

Retrieval drift

Detects when conversational context biases RAG retrieval away from the user's original topic.

How it works

From text to insight in three steps

1

Send text

Any model response, via our API or the web app. No API keys, no model access needed.

2

Analyze

Posture classifiers and agentic graph analysis, computed deterministically in real time.

3

Get insights

Drift, anomalies, crisis signals and forecasts — each with a named, auditable reason.

Research

Grounded in published science

Every PSA metric traces to a specific indicator in the Cybersecurity Psychology Framework — a published taxonomy of 100 pre-cognitive vulnerabilities (Canale, 2025).

Start measuring your models today

Free to start. 37 deterministic metrics. Real-time analysis. No model access required.