SealCheck
A tool I’m building to assess sandbox security in preflight mode, before AI models are tested inside it.
A focus on sandbox security before model testing begins.
Personal project/01
The work / Built & being built
Built to solve
something real.
Production security platforms, sandbox preflight checks, and experiments in agent orchestration. The questions, the systems, and the decisions behind them.
04 projectsProfessional work & personal explorations
Multi-Agent Development Harness
A self-hosted coding system with builder and reviewer agents, human approval, and deliberately limited access to tools and credentials.
Isolated execution. Human approval. Credentials kept outside containers.
Personal project/02
VulTrack
A vulnerability management platform that turns scan results into clear priorities, remediation deadlines, and Board reporting.
Post-scan triage reduced from weeks to minutes.
Professional work/03
ThreatNet
A threat-intelligence service that connects public feeds with asset inventory to surface the threats that need attention.
700 daily records narrowed to 1–5 actionable items.
Professional work/04
More projects will join these pages as they take shape.