AI Systems Analyst
LLM Evaluation Analyst
Model Behavior & Reliability Analysis

20+ years translating structure and flow into order. LLM reliability, multi-turn behavior analysis, structural stability testing, failure-mode detection, and AI-assisted workflow design. Irvine, CA — Open to remote, hybrid, and relocation.

AI systems analyst with 20+ years of experience translating ambiguous requirements, complex workflows, and inconsistent system behavior into structured, usable outputs.

Current work focuses on LLM reliability, multi-turn behavior analysis, structural stability testing, failure-mode detection, and AI-assisted workflow design.

Built and operates a self-directed AI knowledge system combining a typed knowledge graph, PostgreSQL/Supabase infrastructure, custom API surfaces, scheduled agents, and portfolio-grade web interfaces.

Strong at identifying hidden gaps, clarifying decision logic, documenting system behavior, and turning messy inputs into repeatable analysis.

Independent AI Systems Analyst & Platform Builder

FireStrike Productions / HoloSystem — Irvine, CA

2025 — Present

Self-directed AI systems research and platform development focused on LLM reliability, structured knowledge systems, and AI-assisted workflow analysis.

Converted long-running AI conversations, documents, and system outputs into a personal AI knowledge system containing 4,000+ typed knowledge nodes, 13,000+ typed relationships, and a large archived conversation corpus.

Built PostgreSQL/Supabase-backed infrastructure for capturing, structuring, retrieving, and updating system knowledge through structured tables, stored procedures, JSONB payloads, typed relationships, and custom API surfaces.

Developed repeatable methods for evaluating LLM behavior across multi-turn interactions, including consistency loss, hallucination risk, boundary drift, constraint failure, and unreliable synthesis.

Designed workflows for turning unstructured inputs into structured findings, source anchors, reusable knowledge objects, and practical analysis outputs.

LLM Evaluation Knowledge Graphs PostgreSQL Workflow Automation AI Systems Analysis

Founder-Led Product Concept & Systems R&D

HoloShape LLC — Austin, TX

2020 — 2024

Self-directed product and systems research developing HoloShape: a mixed-reality movement platform designed to make body mechanics measurable, repeatable, and improvable through VR, depth-sensing, guided feedback, and gamified progression.

Developed the original HoloShape concept as an embodied measurement-and-feedback system, later extended into AI/system analysis through the current HoloSystem platform.

Designed a model combining VR, depth-sensing movement capture, an 8'x8' physical workout space, virtual guides, skeleton mapping, comparative progress tracking, and gamified exercise loops.

Broke complex movement patterns into measurable micro-movements using joint isolation, range-of-motion mapping, cumulative progress records, and repeatable activity modes.

Explored product architecture, user experience, game mechanics, business models, physical equipment requirements, and potential retail/home deployment paths.

System Architecture R&D VR / Depth-Sensing Movement Analysis Product Design

Front-End Systems Consultant

Independent Client Work — New York, NY / San Diego, CA

2005 — 2020

Delivered production web systems for healthcare, consumer, and agency clients across a long-term independent consulting practice.

Translated client requirements into usable web interfaces, content structures, and production-ready front-end solutions.

Worked across HTML, CSS, JavaScript, CMS platforms, visual implementation, stakeholder communication, and project delivery.

Managed requirements, revisions, implementation details, and client communication from early scoping through launch.

HTML / CSS / JS Requirements Analysis CMS Platforms Healthcare Agency

AI Systems Analysis

LLM reliability analysis · Multi-turn consistency testing · Failure-mode detection · Hallucination risk analysis · Model behavior analysis

Evaluation & Quality

Structural stability analysis · Coherence testing · Gap and affordance analysis · Validation gates · Output drift detection · QA / quality validation

Systems & Workflow

Systems analysis · Requirements analysis · Workflow mapping · Process documentation · Knowledge system design · Data structuring

Technical Literacy

PostgreSQL / Supabase · SQL · REST / RPC APIs · TypeScript / Deno · JavaScript · HTML / CSS · Python · GitHub · Netlify

Case 01

HoloSystem — AI Knowledge System & Operator Platform

AI Systems Analysis // Knowledge Infrastructure

Self-directed AI knowledge platform built to capture, structure, analyze, and retrieve complex system knowledge over time.

Highlights: 4,000+ typed knowledge nodes · 13,000+ typed relationships · 62-table PostgreSQL/Supabase schema · 200+ stored procedures / RPC functions · Custom TypeScript/Deno API surface · Large archived AI conversation corpus · Scheduled background agents · Interactive operator surfaces for search, inspection, and plan navigation.

Demonstrates AI systems analysis, knowledge graph design, data structuring, workflow automation, and long-horizon independent system development.

Case 02

Alpha Stability Test — LLM Reliability Evaluation

AI Model Evaluation // Reliability Testing

A structured LLM reliability evaluation method for testing how model behavior changes across multi-turn interactions, constraint shifts, evidence updates, and ambiguous instructions.

Focus areas: multi-turn stability · hallucination risk · constraint adherence · boundary drift · confidence calibration · output consistency · self-correction behavior · failure-mode detection.

Demonstrates LLM reliability analysis, AI evaluation design, structural stability testing, failure-mode classification, and repeatable evaluation methodology.

View full protocol

Case 03

Recommendation System Gap Analysis

AI / System Behavior Analysis

A compact portfolio sample analyzing a product recommendation system that produced plausible but poorly coordinated outputs.

The analysis moves from: visible system behavior → hidden decision-logic mismatch → missing structure → practical improvement recommendation.

Demonstrates AI/system behavior analysis, gap and affordance detection, decision-logic diagnosis, practical system improvement design, and clear communication of complex analysis.

View step-through analysis

Case 04

The Odyssey Companion Map

Information Design // Structural Mapping

Interactive structural map designed to help modern readers re-orient to a complex narrative through identity handles, power relationships, episode structure, and guided explanation.

Demonstrates information design, structural mapping, explanatory systems, audience-centered complexity reduction, and interactive portfolio design.

Open interactive map

Let's look at
your problem.

A paragraph is enough to start. Tell me what you're working on and I'll tell you whether I can help — and what that looks like.