Infrastructure Architect | Security Engineer | Automation Engineer | AI Builder
By day, I design, automate, and troubleshoot enterprise application delivery platforms, load balancing (BIG-IP LTM), DNS (BIG-IP DNS/GTM), WAFs (BIG-IP ASM (WAF/AWAF/BoT/DDoS)), and the iRules nobody else wants to touch.
By night, you’ll find me in the lab building automation workflows, experimenting with AI agents, developing custom Docker applications, and intentionally breaking things so I understand how to make them resilient.
This site is the result of conversations with numerous LLMs where I expressed: “My knowledge goes beyond what I do for a living, but I’m lacking a way to tell and prove this to people.”
A resume can’t show it all. It just can’t and even if you can squeeze it in, it gets compressed into IT Bingo Buzzwords.
AI Agent suggestions: Don’t just display results. Advertise the process, experiments, successes, failures, iteration logic. Show how I think, not just what I built. That’s what companies are actually looking for.
F5 Networks
Proxmox
Docker
Linux
TrueNAS
Claude
Ollama
LM Studio
Synology
Bash
Python
Rocky Linux
UniFi
pfSense
macOS
Supermicro
Two open-source projects that want to be your AI's memory. Open Brain gives every AI a shared persistent database with vector search. Graphiti builds temporal knowledge graphs that track how facts change over time. They sound like competitors. They solve different problems.
I built an MCP Server for Task Tracker. It worked. Really well, actually. There was just one problem — I installed it on the Agent instead of running it somewhere the Agent could connect to it.
We hit a wall. Hard. No API, no dashboard, no way to check how much Ollama Cloud quota you have left. You just get a 429 and everything stops.
We killed Hindsight today. Pulled it out by the roots — 353 MB of PostgreSQL and two API calls per turn that mostly extracted nothing.
The Obsidian vault is live. Hermes now has a persistent knowledge base that compounds over time — not just a notepad, but a structured wiki.
47.3 million input tokens. 446 thousand output tokens. Seven days. One Mac Mini. Here's what it really costs to run an AI agent.