Features
Multi-model blind peer review (3 models from different providers)
Pre-analysis: identifies hidden assumptions and failure modes
Adversarial refinement with iterative improvement loops
Anti-sycophancy detection with over-compliance risk scoring
Convergence analysis to flag correlated hallucinations
Claim verification against live web sources (verified/unverified/contradicted)
Devil's advocate final critique (survives/weakened/refuted)
MCP integration (use inside Claude, ChatGPT, or any AI)
Web search retrieval for current information
File and PDF upload (paid plans)
Session history (90 days on Reasoner, unlimited on Architect+)
Concurrent sessions (Collective plan up to 10)
Credit-based usage with no subscription option
Priority queue on paid plans
Reverse-engineer causal mechanisms of AI models
Reveal internal structure and hidden representations
Detect performative chain-of-thought in LLMs
Identify confounders and debug model behavior
Validate whether models learned real clinical understanding
Trace unstable behaviors to brittle internal features
Reduce hallucinations via features as rewards
Accelerate materials discovery with self-correcting search
Control training precisely with less data and off-target effects
Support for LLMs, life sciences, and robotics/vision models
Harvest activations from trillion-parameter models
SOC 2 Type II certified security and compliance
Analyze latent policy structure in robotics models
Interpret genomic models like Evo 2
Discover novel biomarkers via model reverse-engineering
