reason=

Projects

Four things in active development. Three more in the lab. If you want to talk about any of them — ryan.walsh1988@gmail.com.

featured

Reasonable UX

  • production
  • advisor pattern

AI-powered UX audit tool. A Playwright agent crawls a site and scores pages with Sonnet and Haiku executors; an Opus advisor gets consulted on ambiguous judgment calls.

QA Agent

  • shipped
  • 84% token reduction

Automated UX quality audit agent built on Playwright + multi-model scoring. Cut running cost 84% by stripping images from conversation history and shipping screenshots at JPEG-40.

Personal OS Dashboard

  • production
  • modular · Svelte 5

Private SvelteKit dashboard on Fly.io, reading a SQLite mirror of an Obsidian vault via Litestream. Modules for projects, daily notes, biometrics, and system health.

LLMOps Curriculum

  • tracker shipped
  • writeups in flight

Self-paced curriculum on the operational side of LLM systems — telemetry, evals, cost routing, model gateways. Tracker reads phases, tasks, and progress live from the same SQLite mirror as everything else; the long-form writeups land through summer 2026.

also building

  • Vault Search
    • in progress
    • Voyage AI · ChromaDB

    Built to understand what retrieval quality actually costs — chunking strategy, embedding model choice, and retrieval window size are the variables that matter. Voyage AI embeddings with H2-aware chunking over Obsidian markdown; ChromaDB for retrieval with SQLite mirror for query logs.

  • System Health
    • revamping
    • self-discovering

    Built because sustained attention to maintenance is exactly what ADHD is worst at — so the checker had to be the thing that pays attention. Self-discovers every automation: launchd jobs, git hooks, OAuth tokens, vault integrity. Reports what to run when something breaks.

  • Agent Panel
    • personal-os
    • 10+ specialists
    • eval harness

    Specialist Claude agents for vault queries, hiring analysis, curriculum review, and automation design — each with typed inputs and narrow scope. An eval harness runs periodic trajectory checks to surface drift before it compounds. The architecture is LLMOps patterns made operational.