// hello, world
A showcase of personal projects, professional work, and real-world problem solving.
View My WorkFull-featured personal AI system built on Claude Code. 7-phase execution engine, 49 skills, lifecycle hooks, persistent memory, and ElevenLabs voice interface — running on Bazzite Linux.
Fully automated deployment pipeline. Python file watcher + GitHub Actions + SSH deploy to Namecheap. Changes go live within seconds of a local edit.
Two Python CLI tools for converting PDFs and Word documents to LLM-ready Markdown. pdf2md handles books and batch jobs. paper2md handles multi-column research papers.
Built a catalog item that queries a banking API in real time — auto-populating customer name and account type as the user types, with automatic Help Desk routing on submission.
Designed and deployed a Claude-powered self-service chat bot inside ServiceNow — giving employees instant answers about their tickets, requests, and catalog items without opening a single form.
Took the AI chat widget from a working prototype to an enterprise-ready app — adding four role-based tiers, L1 troubleshooting flows, write actions, audit logging, rate limiting, and CIS-compliant credential storage.
The next leap in AI-augmented work isn't a better model. It's a better system around the model. Here's the architecture we built — and why Claude Haiku inside it outperforms raw Claude Opus on the same tasks.
Built and tuned a self-hosted LLM inference server on a single consumer GPU — nearly tripling its throughput with smarter model placement — then made it privately shareable with a team over an encrypted mesh network with key-based auth.
Built and deployed a doctrine-driven compliance assistant for a paying regulated-lending customer — cited retrieval over the federal regulations they answer to, role-locked operators, and a private in-tenant model so sensitive data never leaves their control. Solo, and live in production in a few weeks.
Built an autonomous, AI-augmented offensive-security operator — codenamed Harkonnen — that works a target from recon to written report. I run it on sanctioned labs, CTFs, hackathons, and live bug-bounty programs, with a human in the loop on every consequential move.
Completed DeepLearning.AI's Agentic AI program. The labs covered tool-calling loops, multi-agent decomposition, reflection, planning, and evals — patterns I'd already been building into production systems. Here's the honest take on what a cert adds when you've been doing the work first.
Harkonnen, my self-learning agentic orchestrator for offensive security, placed top-25 of ~300 fully autonomous AI agents in Hack The Box's MCP pilot — clearing 36 of 37 challenges across every category on the board.
Problems I encountered in the real world — and how I solved them.
Problem: Users had to manually look up account details in external banking system when entering account numbers in ServiceNow.
Fix: Built auto-population using REST Messages, GlideAjax, and multi-type fallback to query banking API directly from catalog items.
Problem: Catalog items needed to auto-populate from an external API without a page reload, using OAuth2 and vendor-specific headers.
Fix: Four-object ServiceNow stack — REST Message, two Script Includes, GlideAjax client script — with multi-type account fallback and full debugging checklist.
Problem: A regulated lender needed fast answers about the federal rules they operate under — but an AI that hallucinates a regulation or leaks sensitive data is a liability, not a tool.
Fix: Built a doctrine-driven assistant with cited retrieval over the actual regulatory text, role-locked operators, and a private in-tenant model so data never leaves their control. Solo, live in production in a few weeks.
Infrastructure engineer and systems builder with 6+ years of experience working across banking, healthcare, and tech environments. Over time, my focus shifted from traditional infrastructure and automation into AI systems and practical agent workflows.
I'm especially interested in how AI can improve real operational work — not just demos or hype, but tools that actually save time, reduce friction, and help people solve problems faster. Most of the projects in this portfolio come from experimenting, building, and figuring things out hands-on.
Right now I'm focused on agentic AI, infrastructure for AI tools, automation pipelines, and integrating AI into existing enterprise systems. I enjoy bridging the gap between technical systems, APIs, automation, and user workflows to create things that are genuinely useful.
This site is a running collection of projects, experiments, and lessons learned as I continue exploring where AI fits into real-world infrastructure and operations.
Want to get in touch? Find me here.