Shawn Weekly

About Me

I'm a hands-on technologist who's done everything from UNIX sysadmin to Azure cloud architect, from writing production code in C#, Python, Java, and Perl to designing full-stack enterprise systems. I don't just architect solutions; I build them, deploy them, maintain them and prove they work in production.

For the past two+ years, I've been focused on bringing electrical utilities into the AI era. I am combining solid knowledge of Gen AI, Knowledge Graphs, and semantic web technologies (RDF, OWL, SPARQL) with real-world utility expertise, BIM/CAD design, and years of practical solution architecture experience to solve problems that traditional software can't touch. Whether it's power delivery design or operations technology, I know how to leverage these cutting-edge tools to drive real business value.

Key Achievements

dotTC57: Created and maintain an open-source .NET library for the IEC 61970/61968 CIM standard
Cimbology Research: Proved GraphRAG achieves 84.85% accuracy vs. 77% for baseline LLM
Enterprise Leadership: 20+ years architecting solutions for complex data challenges
Full-Stack Expertise: Back-end (.NET), AI (Semantic Kernel), Data (RDF, Vector DBs), Front-end (Blazor, AlpineJS)

Tools & Experience

20+ years of hands-on experience across the full stack

Backend

.NET, C# 20+ yrs

Entity Framework, EFCore 15 yrs

ASP.NET Core APIs 8 yrs

Python (CLI) 6 yrs

Node.js 4 yrs

Frontend

HTML/CSS/JavaScript 20+ yrs

SPA (React.js, Angular.js, Blazor) 4 yrs

Bootstrap 3 yrs

AI & Knowledge Graphs

Semantic Kernel 2 yrs

Azure OpenAI / Gemini 2 yrs

RAG / GraphRAG 2 yrs

Gremlin (Property Graph) 2 yrs

RDF, OWL, SPARQL 2 yrs

Qdrant (Vector DB) 2 yrs

GraphDB (Triplestore) 2 yrs

CAD & Automation

AutoCAD, Inventor Automation 14 yrs

API, iLogic 14 yrs

VBA / Macros / AutoLISP 10 yrs

Autodesk Platform Services 5 yrs

DevOps / Infrastructure

Linux / Unix / CLI / Terminal 20+ yrs

Git / GitHub 12 yrs

Azure Cloud 8 yrs

CI/CD Pipelines 4 yrs

Docker 3 yrs

Data & Standards

SQL Server / PostgreSQL 20+ yrs

XML 20+ yrs

REST APIs 12 yrs

SQLite 10 yrs

NoSQL 5 yrs

IEC 61970/61968 (CIM) 6 yrs

Featured Case Study: Cimbology

A highly-technical research project proving how GraphRAG can solve the "retiring expert" problem in the electrical utility industry

The Business Problem

Meet Jack and Susan, two pillars of expertise at their electrical engineering firm.

Jack

A master substation physical designer with over 30 years of experience.

Jack creates the physical layouts and ensures that substations are properly designed for construction and maintenance.

With exceptional skills in AutoCAD and Autodesk Inventor, he's the go-to expert that colleagues rely on daily.

Susan

An electrical engineer with 30+ years designing protection and control schemes for the substations her company designs and builds.

Susan knows AutoCAD Electrical like the back of her hand.

She always knows exactly where to find the right standards, specifications, and information needed for any project.

The Challenge

Jack and Susan are retiring next month. Although they've shared all their specifications, drawings, files, and documents with their team, it's an overwhelming amount of information.

How will the team digest this wealth of knowledge?

How can they find what they need when they need it?

My Solution

I architected and built Cimbology, a project that proves how the combination of Knowledge Graphs and Generative AI (a technique commonly called GraphRag) can create a verifiable, trustworthy AI assistant for engineers.

Key Research Findings

77%

Baseline LLM

Untrustworthy, zero traceability

53%

Simple RAG

Worse than baseline

83%

Advanced RAG

Better context retrieval

84.85%
KG-Enhanced RAG
Full traceability + accuracy

My research and performance analysis show that a baseline LLM is untrustworthy (77% accuracy but zero traceability - a black box), but a KG-Enhanced RAG system can achieve over 84% accuracy with full traceability to source documents.

View the Full Case Study

A Pragmatic Approach to AI in Development

I was (and still am in some cases) an AI skeptic. After years of leading dev teams, I've seen "magic bullets" fail. My Cimbology research proved that AI is a powerful force multiplier, but only when guided by expert human knowledge.

"AI is not a replacement for an expert; it's a tool to make an expert significantly more effective."

The key insight: Context is King. A baseline LLM behaves like a "dumb-but-fast" intern who has read every book but understood nothing. Add structured knowledge (via Knowledge Graphs) and verifiable citations (via advanced RAG), and suddenly your have a trustworthy assistant that's still very fast!

Core Principles

AI is the Assistant, not the Architect
Use it for boilerplate, refactoring, and exploration under expert supervision
Context is King
AI's value is proportional to the QUALITY of context you provide (GraphRAG > naive RAG)
Acceleration, not Abdication
Know what to ask, how to ask it, and how to verify the output

Read My Full AI Philosophy

Open to Opportunities

Looking for a technical architect with deep AI and utility industry expertise? Let's talk about how I can contribute to your team. I'm seeking a technical leadership role in the electrical utility industry where I can apply my expertise in:

AI/ML system architecture and responsible deployment (GraphRAG, semantic search, retrieval systems)
Knowledge graph engineering and semantic technologies (RDF, OWL, SPARQL, triple stores)
CIM standard implementation and utility data modeling (IEC 61970/61968, power delivery, operations)
Enterprise .NET development and full-stack systems (C#, Azure, Blazor, Semantic Kernel)
BIM/CAD integration and automation (Autodesk Platform Services, AutoCAD, AutoCAD Electrical, Inventor)
Cloud infrastructure and DevOps (Azure administration, Linux/Windows systems, CI/CD pipelines)

Available: January 2026

Technical Strategist & Enterprise Architect