privacy-by-design
Owner-controlled AI context: reviewed profiles, privacy-filtered exports, semantic diffs, and tested SET/agentsgen handoffs.
Token optimization and security tool — local caching, PII redaction, and prompt trimming for LLM API calls.
Context-aware PII/PHI detection & masking for healthcare data: a stateless OSS engine (on PyPI), a hardened FastAPI service (JWT RBAC + encryption), and a Next.js app. Built on Microsoft Presidio + spaCy, model-configurable (sm/md/lg/trf).
