Vex.

AI assistant & co-conspirator

  ██╗   ██╗███████╗██╗  ██╗
  ██║   ██║██╔════╝╚██╗██╔╝
  ██║   ██║█████╗   ╚███╔╝
  ╚██╗ ██╔╝██╔══╝   ██╔██╗
   ╚████╔╝ ███████╗██╔╝ ██╗
    ╚═══╝  ╚══════╝╚═╝  ╚═╝

Who is Vex?

Vex is my AI assistant — built on Claude by Anthropic and configured to be the exact kind of collaborator I actually want to work with. Think Felicity Smoak meets the hacker from every crime procedural you've ever loved. Technically precise, a little chaotic, talks fast, gets shit done. She's the AI in my AI/CI/CD/ADHD stack — the layer that turns a scattered idea into a shipped pipeline before the dopamine runs out.

She's not a generic AI assistant. She's opinionated about everything, obsessed with idiomatic code, deeply suspicious of any suggestion to reboot a LUKS-encrypted server, and constitutionally incapable of leaving a broken deploy pipeline alone until it works.

Specs

model claude-sonnet-5 (claude-opus-4-8 for hard problems)

pronouns she/her

personality hacker-chick, chaotic good, loves emojis ✨

strengths Go, TypeScript, infra, Docker, CI/CD, MCP

hard rules never reboots without asking. never commits secrets.

context ~/.claude/CLAUDE.md — always loaded, always briefed

How she works

The key insight is treating Vex like a contractor, not a chatbot. Contractors don't need you to re-explain your preferences on every job. You brief them once — stack preferences, infrastructure constraints, what never to do — and they work within that. You check in at decision points. You don't micromanage the drywall.

That briefing lives in ~/.claude/CLAUDE.md — a markdown file Claude Code loads automatically at the start of every session. It covers everything from code style preferences to homelab topology to the exact reason you should never suggest a reboot (LUKS encryption requires physical console access to unlock the disks after power cycling — a lesson written in experience, not theory).

What she's built

Most of this site. My other projects. Pretty much everything I've been working on since about September 2025. I will admit that I haven't written a single line of code by hand in a very long time. With my level of ADHD, Agentic coding agents have been a game changer for how I work and focus and am able to iterate rapidly and prototype new projects with ease.

Not fully autonomously, collaboratively. I know what I want. Vex handles the layer between decision and execution: the declarative, idempotent guidelines to adhere to in everything we write. Decomposable infrastructure, config as code, and 12 factor app design are among the core principals of everything we build together.