Enterprise Cloud Advisory · AI Architecture · Principal Engineering

30 years of infrastructure.
Applied to AI at enterprise scale.

Enterprise technology consulting background — cloud migration strategy, post-M&A assessments, application rationalization, and TCO modeling for Fortune 500 clients across healthcare, financial services, retail, CPG, and government. Work spans a $651K UCaaS DC consolidation and a HIPAA-compliant multi-agent Bedrock platform to a production ML weather system and a three-cloud AI ecosystem at under $100/month.

30
Years Experience
14
Advisory Engagements
$57M+
Savings Identified
25+
Documented Case Studies
Filter:
Enterprise AI Delivery

AI systems designed for regulated,
high-stakes organizations

Healthcare, financial services, and technology clients operating under compliance constraints don't have the option of deploying AI that can't be audited. These projects were scoped with governance as a design input — not a retrofit. Multi-agent architectures, HIPAA-compliant infrastructure generated from spec, dual-cloud deployment with zero forked business logic, and AI governance platforms that enforce SDLC gate reviews across 10 regulatory frameworks.

Live Demo

Enterprise Application Rationalization Platform

Healthcare · AWS Bedrock + Azure OpenAI · Multi-Agent · AI-Generated IaC · HIPAA

Multi-agent AI pipeline that scores an enterprise application portfolio against 6R cloud migration criteria and produces auditable, provenance-tagged recommendations — deployed for a healthcare imaging organization (36 clinical apps, 408 VMs, $24 total AI compute, 22 governance rules, zero black-box outputs). The full deployment stack behind it — CloudFormation on AWS, Bicep on Azure, Bedrock and GPT-4o multi-agent swarms, MCP servers, PHI-masking ETL — was generated from a written spec using Kiro with zero hand-written IaC, and runs identically cross-cloud with only a cloud-adapter layer separating the two versions.

36 apps · 408 VMs
$24 total AI cost
AWS + Azure 0 manual IaC
22 governance rules
Multi-AgentBedrock + GPT-4oProvenance GovernanceHIPAA ComplianceAI-Generated IaC (Kiro)Cross-Cloud (AWS + Azure)
Live Demo

Enterprise AI Governance Platform

GitHub · Azure AI Foundry · AWS Bedrock · ISO 42001 · NIST AI RMF · Cross-Cloud

Enterprise AI governance platform that scans codebases against 10 regulatory frameworks (including ISO 42001, NIST AI RMF, HIPAA), generates compliance artifacts, and enforces human approval gates at 5 SDLC checkpoints. The v3 release adds a Framework Explorer, a Policy-as-Code engine, and a full runbook library — DevSecOps, PM/Scrum, Workshop Guide, and Software Factory — so AI-generated commits are scanned against the same rules as human-written code. Deployed cross-cloud with zero forked business logic — AWS (CloudFormation, DynamoDB, Bedrock) and Azure (Bicep, Cosmos DB, Managed Identity) run identical application behavior behind a cloud-adapter layer — and productized as a multi-tenant SaaS (PostgreSQL + Redis, blue-green deploys, hybrid SDK) for teams that want the library without owning the infrastructure.

10 frameworks
5 SDLC gates
AWS + Azure zero-fork
SaaS-ready multi-tenant
AI GovernanceISO 42001 · NIST AI RMFHIPAA ComplianceCross-Cloud (AWS + Azure)Multi-Tenant SaaSSoftware Factory
Solution Detail

Pre-Sales Intelligence Research Agent

Azure AI Foundry · Claude Tool Use · Live Data APIs

Pre-sales research agent that turns a company name into a technology diligence brief in under 10 minutes — live news, website analysis, stock data, stakeholder mapping, tech stack profiling, and opportunity framing. Replaces 4+ hours of manual pre-call research per account. Built for enterprise technology sales cycles where showing up informed is a competitive differentiator.

13 sections per report
4 news sources
2 agent modes
<10 min vs 4 hrs
Agentic Tool UseClaude SonnetAzure AI FoundryReal-Time API IntegrationEnterprise Sales Enablement
Solution Detail

Digital Twin App Dependency Simulator

AWS Lambda · Dependency Graph · AI Simulation · TCO Analysis

Collects 30 days of live datacenter telemetry via PowerShell/Bash agents, builds an in-memory dependency graph, and runs 5 AI simulations — wave rehearsal, blast radius, co-dependency discovery, right-sizing, and TCO projection — across 1,053 servers in 4 DCs. Used in enterprise cloud migration advisory engagements to give infrastructure teams a visual model of what a migration actually disrupts before they start.

1,053 servers
5 AI simulations
174 dep. edges
8-rule 6R engine
Dependency Graph ArchitectureAI Simulation Engine6R Migration FrameworkAWS LambdaTCO ModelingCloud Migration Advisory
Live Demo

Historical-inator — AI Local History Platform

Generative AI · Location-Aware · Multi-Audience · Public Archive Data

Location-aware generative AI product that turns any GPS coordinate into a narrated historical brief, drawing on 60M+ digitized public-domain records from the Library of Congress, National Archives, Smithsonian, and DPLA. Serves 5 distinct audiences — consumers, K-12 educators, homeschoolers, tourism boards, and cultural institutions — from a single platform, and is positioned to qualify for NEH/IMLS cultural-heritage digital-access grant funding.

60M+ archive records
5 audience segments
$9.8B ed-tech market
$0 data access cost
Generative AILocation-AwarePublic Archive AggregationMulti-Audience PlatformGrant-Fundable
Architecture · Design Spec

MemoryOS — Enterprise Knowledge Ingestion Pipeline

Bedrock Guardrails · Bedrock Claude · Extensible Connector Library · Hybrid Search

New enterprise data AI pipeline that connects to just about any enterprise data source — chat, ticketing, wikis, document repositories, email, or a custom pipeline — through a library of connectors, then runs every document through a 4-stage Bronze → Silver → Gold enhancement pipeline: deterministic pruning, Bedrock Guardrails screening, tool-forced Claude classification (temp=0), and embedding into a hybrid search index. Bedrock Guardrails and Claude are already the production AI layer today, called from Azure-hosted infrastructure — this documents the full AWS-native port target.

4-stage pipeline
70%+ pruned pre-AI
0 client data stored in AWS
extensible connector library
Bedrock GuardrailsBedrock Claude (tool-forced)Hybrid Search (BM25 + Vector)Cross-Cloud PII MinimizationExtensible Connector Library
Park Whisperer Platform

A production R&D platform
for validating AI architecture patterns

Every architectural pattern I recommend to enterprise clients has already run in production here first. Park Whisperer is a fully operational AI ecosystem — real users, live data pipelines, a six-model ML stack, automated content operations, and a conversational agent — running across Azure, GCP, and AWS at under $100/month. The domain is theme park intelligence. The purpose is proving that specific architecture decisions work before scaling them into environments where failure is expensive.

Full platform architecture →
Solution Detail

Park Operations Weather Intelligence API

GCP · BigQuery · Cloud Run · Terraform · METAR · NWS

Production GCP pipeline that fuses METAR surface observations, NWS forecasts, and upper-air radiosonde soundings in BigQuery. ML scoring maps current conditions to per-attraction OPERATE / MONITOR / CLOSE recommendations and publishes a live JSON API to GCS every 15 minutes, consumed by the agent and dashboards.

5 BQ tables
5 Cloud Run jobs
15min freshness
$35 max/month
Data EngineeringBigQueryML ScoringGCP ArchitectureTerraform IaCReal-Time API
Production · pgvector

Operational Knowledge Retrieval System

PostgreSQL + pgvector · Azure OpenAI · Phi-3 Mini Classifier · HNSW

ETL pipeline and SLM-routed query engine over 1.6M+ theme park operational records. A fine-tuned Phi-3 Mini classifier routes queries to one of 3 strategies (vector, numeric, hybrid). Deterministic fast paths bypass AI inference entirely for wait-time and outage questions — no latency, no hallucination.

1.6M+ records
34+ knowledge types
3 query strategies
1536-dim embeddings
RAGpgvector + HNSWSLM / Phi-3 Mini Classifier1536-dim EmbeddingsHybrid SearchAzure OpenAI
Production · LangChain · Bedrock

Automated Social Content Factory

Azure Container Apps · LangChain · Claude (Bedrock) · 30+ Tools

Scheduled pipeline that produces and publishes theme park social content with no human involvement. The architecture: intent classification → parallel knowledge pre-fetch → LangChain agentic loop with 30+ tools → 3-pass generation → direct platform publish. Ten content types, zero hallucinated facts, grounded entirely in live operational data. The production system that validates the content generation patterns recommended in enterprise AI deployments.

10 pipeline types
30+ tools
3 gen passes
0 hallucinated data
Agentic AI (LangChain)AWS BedrockSLM Intent RoutingClaude (Haiku · Sonnet)Content Automation30+ Tool Calls
Production · 4 AI Models

Multi-Model Content Quality Architecture

Phi-3 Mini · Claude Haiku · Claude Sonnet · Per-Model Instructions

Four AI models with distinct roles collaborate on each content piece. Phi-3 Mini classifies intent. Haiku runs the agentic tool loop (fast, cheap). Sonnet writes the final output — replacing Haiku after model-specific testing revealed it lacked domain knowledge for the subject matter. Each model has a persona and guardrails.

4 AI models
3 gen passes
temp=0 format fidelity
5+ platforms
Multi-Model ArchitectureSLM (Phi-3 Mini)Claude Haiku · SonnetModel Selection StrategyPer-Model Guardrails
Production · ElevenLabs · FFmpeg

Script-to-Published Video Pipeline

ElevenLabs TTS · Pillow · FFmpeg · Instagram · TikTok · YouTube Shorts

Five systems take a Claude-written script from text to a published social post. ElevenLabs per-character timestamps drive frame-accurate word-pop captions. Pillow composes brand overlays. FFmpeg encodes. An API publisher posts to three platforms. The pipeline was built to validate automated content production patterns — the same approach applies in enterprise content operations and AI-assisted marketing workflows at scale.

5 AI systems
word-sync captions
3 caption colors
0 manual steps
AI Content GenerationElevenLabs TTSFFmpeg PipelineMulti-Platform PublishingFrame-Accurate Captions
Production · Live Q&A

Natural Language Operations Assistant

Azure Functions · Claude Sonnet · Shared Tool Library · Bedrock Prompt Cache

Conversational agent that answers questions about park operations in plain language. Uses the same Azure Function, SLM classifier, and 15+ live data tools as the content pipelines — the agent and content factory share infrastructure. Designed for responses short enough to paste directly into social DMs and comments.

1 shared function
auto pipeline routing
15+ live tools
Prompt Cache
Agentic AIRAGTool Use (15+ tools)Azure FunctionsBedrock Prompt CachingClaude Sonnet
Production · ETL · 10 min

Live Theme Park Data Pipeline

Azure Container Apps · ThemeParks.wiki API · PostgreSQL

Containerized ETL job running every 10 minutes that collects live attraction status, wait times, Lightning Lane sellout events, and schedules for 286 WDW entities and writes them to PostgreSQL. Feeds every downstream consumer: the RAG, the agent, and all content pipelines. The foundation of the platform.

286 entities
10 min cadence
4 PG tables
v6 current
Real-Time ETLData EngineeringAzure Container AppsPostgreSQL286 Entities · 10-min cadence
Architecture · Data Engineering

Database Architecture Decision: A Cost Inflection Story

Azure Cosmos DB · PostgreSQL · pgvector · Cost Analysis

How the platform's analytics store went PostgreSQL → Cosmos DB → back to PostgreSQL. A Cosmos DB monolith developed a critical hot-partition problem at 5.9M documents. The fix cost $394/month with no benefit. This documents the decision process, the migration, and the six architectural lessons — including when not to use a document store.

5.9M peak docs
$394/mo Cosmos floor
$0 today
6 lessons
Data ArchitectureCost AnalysisCosmos DB → PostgreSQLpgvector MigrationHot-Partition Diagnosis
ML · BigQuery · scikit-learn

ML-Based Weather Nowcasting System

GCP · BigQuery · scikit-learn · METAR · Radiosonde Soundings

8 years of Central Florida METAR surface obs fused with twice-daily radiosonde soundings (CAPE, Lifted Index, K-Index) trains 6 scikit-learn models that nowcast thunderstorm, precipitation, fog, and venue-impact risk every 20 minutes. A spatial boost via BigQuery ST_DISTANCE amplifies probabilities when confirmed active storms are within 15 miles.

44K+ training obs
8 yrs METAR history
6 ML models
0.99 best AUC
Data Sciencescikit-learn (6 models)BigQuery MLTime-Series ForecastingFeature EngineeringGCP
Satellite · GOES-18 · Geospatial

Satellite Lightning → Park Ride Risk Intelligence

NOAA GOES-18 GLM · BigQuery · GCP Cloud Run · Storm State Machine

Ingests GOES-18 Geostationary Lightning Mapper data every 20 seconds, applies a two-stage spatial filter to attribute flashes to specific parks, and drives a 5-state storm machine (CLEAR → SEVERE) that fuses satellite data, 17-station METAR surface obs, NWS alerts, and SPC categorical outlook to compute per-ride closure risk.

20 sec GLM cadence
4 parks attributed
5 states
20 mi park filter
Geospatial Data EngineeringSatellite Data (GOES-18 GLM)5-State Storm MachineBigQuery20-sec Cadence
Research & Architecture Explorations

Documented iteration —
what led to the production decisions

Each of these directly preceded a production component. They're documented because architecture decisions are more credible when you can show what was tried first and why it was replaced. The forecasting iterations show how compounding error and inference-time feature availability constrained the final design. The agent framework explorations show the tradeoff analysis that led away from Assistants API and n8n toward stateless Azure Functions.

These aren't abandoned experiments — they're the evidence trail behind production choices. A Principal Architect who can only show the current state of a system and not the decision path that got there hasn't fully documented the work. Each entry here documents a specific tradeoff, what it revealed, and what changed as a result.
Predecessor · LightGBM · PostgreSQL

Attraction Wait Time Forecasting — LightGBM Iteration

LightGBM · PostgreSQL · Recursive Multi-Step Forecasting · Iteration 6

Global LightGBM model across all WDW attractions using a recursive multi-step loop — predicted values fed back as lag features for subsequent horizons. Seven forecast intervals from 15 minutes to 3 hours. One of 8+ iterations in the wait-time forecasting R&D track, each informing the next architectural decision.

v6 iteration
7 horizons
3hr max forecast
global model
LightGBMML ForecastingRecursive Multi-StepFeature EngineeringData Science
Predecessor · Prophet · BigQuery

Ride Whisperer v8 — Prophet + BigQuery

Facebook Prophet · Google BigQuery · NWS Weather · GCP

Per-attraction time-series forecasting with one Prophet model per ride, 50+ external regressors, and a 24-hour horizon written back to BigQuery. Reached v8 before being shelved — rolling window features unavailable at inference time degraded accuracy significantly.

v8 final iteration
50+ regressors
24hr horizon
130+ attractions
ProphetTime-Series ForecastingBigQueryGCPData Science50+ Regressors
Prototype · AWS · Azure · GCP

Multi-Cloud Agentic Architecture Exploration

Amazon Bedrock · AWS Lambda · Azure Logic Apps · GCP Cloud Run · OpenAPI

Three-cloud exploration of Bedrock Agents and custom action group patterns. Wired three weather tools to a GCP Cloud Run backend via two integration architectures: direct Lambda action groups and Azure Logic Apps as cross-cloud backends. The tool design patterns and OpenAPI schema approach carried forward directly into the production agent.

3 tools
2 architectures
3 clouds
Agentic AIAWS BedrockMulti-Cloud ArchitectureOpenAPI Tool DesignAzure Logic Apps
Prototype · Assistants API

Park Whisperer — Azure OpenAI Assistants API

Azure OpenAI Assistants API · GPT-4o-mini · Cosmos DB Vector Search

Earlier agent architecture using the Azure OpenAI Assistants API (threads/runs model). Persistent assistant object, 16 function tools, server-managed thread state, Cosmos DB vector search over 9 knowledge types. Directly preceded the production Park Agent Chat.

16 tools
9 knowledge types
IaC config
Azure OpenAIVector Search (Cosmos DB)Assistants APITool Use (16 tools)GPT-4o-mini
Research · n8n · Multi-Agent

Park Whisperer — n8n Agentic Backbone

n8n · Google Gemini · FastAPI · Redis Stack · pgvector · Docker

"Walt" — a central host agent — coordinated seven specialized sub-agents, each named for a Disney character and owning a park knowledge domain. Two custom FastAPI microservices ran alongside n8n. Iterated through 7 Docker Compose versions before being replaced by the Azure Functions architecture.

8 agents
12+ SRE tools
v7 final compose
Multi-Agent Orchestrationn8npgvectorFastAPI · Redis StackGoogle GeminiDocker Compose
Available for New Engagements

Have an AI system that needs to ship?

I take on a limited number of freelance engagements through AI Pathfinder LLC — architecture reviews, governed AI builds, cloud migration analysis, and hands-on delivery. If something in this portfolio is close to your problem, let's talk about yours.

Email Me → More Ways to Connect →