Open-source tools, AI security research, publications, and talks.

A curated index of public-safe work across developer-first security tooling, AI security research, AWS and CSA publications, and conference sessions.

Production AI Security Systems

Public work across agent development, adversarial evaluation, and security-agent measurement.

Incident response agent

AWS Security Incident Response

Led development of AWS’s first customer-facing AI security agent, including evaluation methodology and synthetic incident environments for evidence-driven investigations.

Adversarial evaluation

AWS Continuum for code vulnerabilities

Built red-team agents and led end-to-end evaluation using synthetic, production-like applications across vulnerability discovery, exploit validation, remediation quality, safety, and regressions.

Field leadership

Application Security at AWS

Co-lead AWS’s global Application Security field community, connecting customer needs, field specialists, service teams, and security leadership through technical guidance and enablement.

Open source