Shawn Skelly

Systems Architect

I build AI-powered tools and full-stack systems from architecture to deployment, and I build them to last. I spent years in quality engineering before I started building products, and that background shows in everything I ship: real test coverage, clean interfaces, and error handling that accounts for the ways things actually break. Every project started with a real problem I wanted to solve.

How I Work

My Approach

Tests as architecture. Design patterns aren't optional. Data is hostile until proven otherwise. AI-augmented development.

Under the Hood

The engineering patterns that repeat across every project, mapped in one place.

Featured Projects

๐ŸŒ TALON

Land acquisition intelligence platform. Conversational AI search, 3D LiDAR visualization, ML owner classification, and deep parcel analytics across western North Carolina.

PostGISOpenAIAstro/PreactLiDAR

๐Ÿ” SF-Assistant

Conversational codebase assistant for Salesforce projects. Ask questions in plain English, get grounded answers with call graph context. Zero external dependencies.

Java 11RAGZero-DepsSalesforce

๐Ÿ”ฌ RepoAudit

Deterministic-first codebase analysis across six dimensions: architecture, security, AI maturity, docs, portfolio, diagrams. Works without API keys; LLM validation is opt-in.

Tree-sitterAnthropicSecurityCLI

๐Ÿ”Ž Salesforce Vector Knowledge

A Lightning Web Component that runs hybrid semantic + keyword search over Salesforce Knowledge with LLM-synthesized cited answers, at $0.0004-$0.0009 per search instead of Agentforce's $0.10/action floor.

ApexLWCVector SearchSalesforce
View all projects →

Writing

Some of this goes back to where the instincts came from, before any of it was code. Some works out how I earn the right to trust what a dataset or a model is telling me. The rest is field notes from the work itself. Different starting points, one throughline: learning to read a system well enough to know when to trust it. Some ideas run long enough to need more than one part.

The Model Doesn't Get to Decide

Jul 5, 2026 ยท 4-part series

This is one argument in four parts, built to be read in order, though each part stands on its own. The running question, every part, is the same: on this axis, does the model get to be the auditor, or the judge? The diagram at the foot of each part grows by one box, because the shape earns itself as you go.

AI EngineeringLLM SystemsDeterminismEssay
All writing →

Let's talk

Building something, hiring, or just want to compare notes on a problem? I read every message and reply to the ones worth replying to.

Get in touch hello@shawnskelly.com