Grounded portfolio AI
Answers only from published artifacts, cites evidence IDs, and refuses unsupported claims.
John Kwan
AI Security / Agent Security. I build and audit AI systems, and I ship reproducible security demos.
This hub is designed for fast diligence: three flagship projects, stable evidence packs, grounded AI Q&A, and explicit limits on what is proven.
Live demos
LLM AppSecAgent SecurityGovernanceEvidenceSimulation
Reproducible project evidence
Each flagship links to stable snapshots, repo references, and explicit limitations.
Fit Check for recruiters
Paste a job description to generate an evidence-backed match and 30/60/90 plan.
Flagships
Three current projects, each with a case study and evidence pack
The site foregrounds stable proof artifacts rather than broad claims. Each project page combines context, architecture, limits, and cited evidence.
AI AssuranceGovernanceEvidenceRules Engine
AI Assurance Control Plane
An assurance layer over AI telemetry, evaluation, and review workflows, focused on evidence management rather than generic observability.
Agent SecuritySimulationSupabaseEducation
AI Security Navigator
Interactive periodic-table style navigator for AI security learning, design recommendations, and safe simulations with a constrained execution model.
LLM AppSecRegressionEvidenceHardening
LLM AppSec Harness
Deterministic regression harness for comparing baseline and hardened LLM application behavior with stable reports and explicit limits.