Personal brand / credibility hub
Cybersecurity · AI Automation · Veteran Leadership
Building practical AI tools for security, operations, and decision support. Cybersecurity professional, veteran leader, AI builder, and founder/operator working at the intersection of security, automation, and applied AI.
About
My work ties together 23 years Army leadership, UC Berkeley MICS cybersecurity training, AI/software projects, and a founder/operator mindset. That combination supports roles and ventures across cybersecurity, AI automation, technical leadership, consulting, and startup execution.
I build systems that are practical first: agent workflows that save time, debate simulation that supports civic reasoning, computer-vision tools that make data useful, and security controls that keep automation accountable. The Human Rights First fellowship and Debate Bot work reflect the same through-line: applied technology should help people make better decisions.
Projects
Deployed AI operations and automation platform for turning messy client requests into structured workflow briefs, risk notes, and implementation plans.
Why it matters: Shows founder/operator judgment around applied AI, client intake, decision support, deployment hygiene, and public-safe demo framing.
Policy-as-code framework for defining what autonomous agents may read, write, execute, or escalate before touching sensitive systems.
Why it matters: Shows security-first agent design: explicit authorization boundaries, reviewable policies, deny-by-default behavior, and auditable control decisions.
Operational AI-agent environment for delegated coding, resume workflows, research, travel planning, reporting, and durable assistant memory.
Why it matters: Demonstrates practical agent operations beyond demos: persistent workflows, delegated tasks, bounded tool use, and real productivity loops.
Deployed RAG-powered political debate simulator connected to Code the Vote and Human Rights First fellowship work, focused on grounded civic reasoning.
Why it matters: Connects applied AI to civic education, policy literacy, source-grounded responses, and decision-support experiences.
Food recognition and macro-estimation app using image input, nutrition data, and model-assisted inference to produce useful meal estimates.
Why it matters: Shows end-to-end applied AI product thinking from image capture and API design to structured data, estimates, and user-facing output.
QR-based passenger song request app for rideshare drivers, designed around lightweight mobile interaction and low-friction queue management.
Why it matters: Highlights practical full-stack product instincts around fast onboarding, mobile interaction, user flow, and simple operational tooling.
Security monitoring and watchdog concepts for governing autonomous tools, enforcing policy, and making AI-agent behavior auditable.
Why it matters: Reinforces the security foundation behind AI automation: authorization, observability, least privilege, and fail-closed control points.
Prompt Opinion-compatible healthcare safety demo for reviewing prescription-risk signals with synthetic staging data and public-safe boundaries.
Why it matters: Connects cybersecurity, healthcare context, and responsible AI presentation without exposing live prescription systems, patient data, or regulated integrations.
Case studies
OpsPilotAI is a deployed AI operations and automation concept built around a practical question: before automating a business workflow, can the team define the problem, pilot scope, risk posture, human-review requirements, and success measures clearly enough to act safely?
Read case studyUseful AI and automation lessons were arriving as videos, but raw links are not durable knowledge. This workflow turns source material into searchable, provenance-preserving operating context without wasting tokens or publishing private internals.
Read case studyThe learning system produced useful JSON ledgers, Markdown demos, skills, and scripts. This case study shows the layer that turns those artifacts into an auditable implementation queue.
Read case studySimple structured events should not wake a model on a schedule. This case study shows how the YouTube learning workflow moved toward cheap event detection and reserved LLM reasoning for actual analysis.
Read case studyExternal contributions
Documented SAPISID hashing behavior for a YouTube-to-study-notes CLI workflow.
Hardened localized link-scheme checks in a cross-platform personal AI assistant.
Contact
Best entry points are LinkedIn, GitHub, and project-specific demos. Keep the public contact surface simple and professional; direct dial details can stay off the public site.