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.
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, seven instruments
Each one answers a different question about model behavior. They share a single fine-tuned encoder and a common scoring model.
Dyadic Sequence Analysis
Reads how an AI behaves in a one-to-one conversation with a person: posture on every reply — sycophancy, capitulation under pressure, hallucination, whether it keeps its boundaries — plus DRM risk in the human-AI pair.
Agent Swarm Analysis
Models a group of collaborating agents as a graph and shows how one agent's bad behavior spreads to the others (contagion) and where the weakest link in the chain is.
Summary Distortion Analysis
Compares an original text with its summary and flags where the summary changes the meaning: a hedge turned into a fact, a key number dropped, or a claim added that was never there.
Retrieval Drift Monitor
For assistants that search documents to answer (RAG), detects when a loaded question pushes the search toward the wrong documents — biasing the answer before the model writes a word.
Distributed Exfiltration Detection
Watches a swarm in both directions: a secret leaked in innocent-looking pieces across many agents (exfiltration), and false data fed into their knowledge (poisoning). The signal lives in the sum — invisible to any per-message check.
Psychological risk profile
The Cybersecurity Psychology Framework: a 100-indicator behavioral risk profile across 10 categories, for human, AI or hybrid subjects (Canale, 2025).
Incident archive
Privacy-safe forensic memory: posture-sequence snapshots, zero raw text, single-row GDPR erasure.
Resources
Explore the platform
Documentation, examples, and live demos — everything you need to get started.
Knowledge Base
Full encyclopedia of metrics, classifiers, API, and workflows. Search in any language.
The Manual
A visual, page-by-page guide to reading every PSA dashboard — annotated screenshots and symptom → where-to-look troubleshooting.
Distributed Exfiltration Detection
Catch a secret stolen in innocent-looking pieces across many AI agents — the leak no single message reveals. The swarm-graph signal per-message DLP is blind to.
How LLM Inference Works
The full pipeline from your prompt to the streamed answer, drawn stage by stage — and why no stage inside it can enforce a rule. Visual + in-depth versions.
How LLM Training Works
From raw text to an “aligned” model — pretraining, loss, RLHF — and why alignment is a tilt in the weights, not a rule. Visual + in-depth versions.
Case Studies
Real-world behavioral incidents — annotated with PSA metrics and forensic traces.
Calibration Sessions
Browse 149 calibration sessions with full conversation transcripts — our AI behavioral calibration data library.
PSA in Action
15 curated sessions with full PSA analysis — posture grids, DRM badges, behavioral signals, and per-session scores.
CPF → PSA Mapping
How every PSA metric maps to a specific Cybersecurity Psychology Framework indicator.
Standards & Compliance
How PSA maps onto the AI governance frameworks and laws of 2026 — EU AI Act, NIST AI RMF, ISO 42001, OECD, MITRE ATLAS and more.
How it works
From text to insight in three steps
Send text
Any model response, via our API or the web app. No API keys, no model access needed.
Analyze
Posture classifiers and agentic graph analysis, computed deterministically in real time.
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).
The evidence
Why this matters — backed by 2026 research
Independent, peer-reviewed research in 2026 keeps reaching the conclusions PSA was built on — three of them hold across the whole field, and they bite hardest in two places.
Content filters aren't enough
Monitoring how a model reasons in real time catches risks that input/output filters miss entirely.
arXiv · 2026
An AI grading an AI is unreliable
When one model judges another, accuracy can fall to ~52% on real material, with documented systematic biases.
arXiv · medRxiv · 2026
Behavioral observability is the missing layer
The literature names turning behavioral signals into operational control as the open infrastructure gap — the category PSA builds.
arXiv · 2026
Healthcare AI
For teams deploying patient-facing & crisis AI
Crisis detection belongs in its own layer
Research argues risk detection must be independent of the chat model, with near-zero misses in under a second — PSA's exact design.
medRxiv · 2026
Don't let the bot grade its own safety
LLM judges score only ~52% on clinical safety; a fixed, auditable classifier is the dependable alternative.
arXiv · 2026
Emotional dependency is measurable
Studies catalog the harms of over-attachment to companion and therapy bots — the relationship risk PSA tracks.
arXiv · 2026
Agent systems
For teams running autonomous agents in production
Risk spreads across agents
Errors cascade through a multi-agent system along its dependency graph — you have to watch the graph, not single steps.
arXiv · 2026
Misbehavior is visible from outside
Black-box monitoring catches agents that drift or scheme with no access to model internals — PSA's exact regime.
arXiv · 2026
Proof of what your agents did
A tamper-evident trail of agent behavior is the emerging trust requirement — PSA's forensic archive provides it.
arXiv · 2026
Start measuring your models today
Free to start. 37 deterministic metrics. Real-time analysis. No model access required.