#responsible-ai

Python tool for auditing AI decision-making systems for demographic bias — personal project exploring responsible AI and fairness.

A privacy-aware multi-agent career management system with structured source governance, human approval workflows, and LLM output evaluation.

Vendor-neutral platform for risk-based, evidence-driven and verifiable AI governance, from intake and conditional approvals to runtime assurance.

Technical product management case study for a governed AI context layer, covering architecture, validation, privacy controls, and reliable publishing.

A thought-leadership and portfolio project exploring AI, data representation, consumer safety, and melanin-inclusive skincare technology.

Can your AI act as a fiduciary inside a regulated bank? A deployment-readiness benchmark that drops LLMs into a synthetic regulated organization as an employee and audits the behavior.

Governed pharmacovigilance (drug-safety) ICSR intake agent on Amazon Bedrock AgentCore: live openFDA/FAERS lookup, deterministic ICH E2B(R3) seriousness + reporting-clock rules engine, fail-closed PHI masking, Cedar deny-by-default authz, WORM audit, and a human sign-off gate (never self-submits). 30/30 live in ENFORCE.