I build practical security infrastructure for the new AI software supply chain—tools that help teams test agents, inspect AI-written code, and ship with evidence instead of hope.
AI agents are becoming software collaborators. Their output needs the same rigor as any other production dependency.
I’m building a local-first security stack that helps developers move from generated code to verified software:
|
The independent security agent for AI-written software. It finds issues, investigates whether they are real, and shows the evidence. Why it matters: deterministic core, local-first operation, no API key required, and automation-ready JSON and SARIF output. |
Safely attack your AI agent before someone else does. A controlled security-testing CLI for adversarial tool responses. Why it matters: validates trust boundaries, reveals unsafe agent behavior, and makes security failures reproducible. |
| AI systems | Agent workflows · evaluation · safety boundaries · grounded generation |
| Product engineering | TypeScript · Next.js · React · Node.js · Python |
| Security tooling | Static analysis · adversarial testing · SARIF · CI automation |
| Infrastructure | PostgreSQL · Prisma · Docker · GitHub Actions · Vercel |
I’m interested in collaborating with founders, security engineers, AI infrastructure teams, and open-source maintainers working on the hard problems around agent trust and AI-generated code.
