Working Systems · Live in Production

Not slides.
Working software.

These are live, operational systems — built, deployed, and operated by one engineer. Each demo opens in a dedicated environment. Interact with real data, real APIs, real results.

AI Governance Code Scanner

Point it at any public GitHub repository, select compliance frameworks — NIST AI RMF, ISO 42001, EU AI Act, HIPAA, GDPR, SOC 2, ModelOps, AIOps, XDR, FinOps — and receive a scored governance compliance analysis in under 30 seconds. Deterministic pattern analysis against real source code. No mock data. No AI-generated guesses.

Live
Frameworks
NIST AI RMF · ISO 42001 · EU AI Act · HIPAA · GDPR · SOC 2 · ModelOps · AIOps · XDR · FinOps
Coverage
Up to 60 source files per scan · GitHub Trees API · subfolder targeting supported
Scoring
Per-pillar compliance scores · severity-weighted findings · Critical / High / Medium / Info
Engine
Azure Function (Flex Consumption) · 8-worker parallel fetch · sub-30s end-to-end
AI Pipeline Token Economics

A full token audit of a 7-agent enterprise AI rationalization pipeline — real token counts from AWS Bedrock Converse API usage fields, not estimates. Per-agent cost breakdown, retry economics, prompt anatomy, and a prioritized optimization roadmap across a 36-application healthcare portfolio run. Shows $23.97 baseline path to $7.63 with three targeted changes.

Live
Run Stats
3.05M tokens · $23.97 total · $0.67/app · 250 API calls · 4.9 hrs wall-clock
Agents
7 specialized agents · Telemetry · Dependency · Procurement · Provisioning · Synthesizer · Confidence Advisor · Portfolio Narrative
Analysis
Per-agent cost bars · token anatomy · retry rate by agent · prompt size vs. necessity · benchmark table
Optimization
7 prioritized optimizations · P1 code changes only · P1+P2 near-term: 68% cost reduction · 6 tokenomics principles
Enterprise App Design

How I approach enterprise application architecture — a full-stack AWS solution design for a HIPAA-compliant rationalization platform. Every component is a managed service chosen for compliance, zero operational overhead, and pay-per-use economics. Seven feature flows traced end-to-end from browser to data store, with explicit cost and data-path rationale.

Live
Architecture
6-layer AWS stack · CloudFront → API Gateway → Bedrock Multi-Agent → DynamoDB / S3 · HIPAA-eligible services throughout
Design Method
Feature-first tracing — select any user flow and watch active services highlight with rationale, cost model, and data path
Service Selection
Pay-per-use only · zero standing compute · managed auth (Cognito) · immutable audit trail (WORM S3) · no self-managed infra
Why Grid
Every architectural decision documented — compliance posture, operational model, cost rationale, and data governance constraints
Application Rationalization Digital Twin

Enterprise cloud migrations fail when dependency risk and cost assumptions aren't visible until cutover. This demo shows how I surface both — a live simulation built on masked data from a real healthcare engagement: AI-generated 6R dispositions across 1,053 servers, an interactive dependency graph that reveals hidden cross-stack risk, and a scenario simulator that lets stakeholders test migration waves before committing. The result: decisions made in steering committee instead of discovered in production.

Live
Scale
1,053 servers · 198 applications · 4 global data centers · real engagement data, masked for confidentiality
AI Dispositions
Automated 6R recommendations with complexity scoring — what to rehost, replatform, refactor, or retire, and why
Dependency Risk
Force-directed graph exposes cross-stack dependencies that are invisible in spreadsheets — clickable blast-radius simulation
Migration Simulator
5-wave scenario planner with TCO modeling and infrastructure winddown — test assumptions before committing to a wave
AI Governance SDLC Workflow

Governance frameworks mean nothing without a process to enforce them. This demo visualizes the full AI development lifecycle as a gated pipeline — five control gates from requirements through production, with HITL approval checkpoints, CI/CD integration, scrum ceremony alignment, and a live RACI matrix. Built to show clients what responsible AI delivery actually looks like operationally, not just on a slide.

Live
Pipeline Gates
5 control gates · Requirements → Design → Build → Validation → Production · click any gate for artifacts and approvers
HITL Controls
Human-in-the-loop approval flows mapped to gate thresholds — who reviews, what triggers escalation, what blocks release
CI/CD Integration
Governance checks embedded in the build pipeline — scan thresholds, automated gates, and rollback triggers at each stage
Accountability
RACI matrix covering every role across the lifecycle · ceremonies mapped to sprint cadence · no ambiguity on who owns what
App Rationalization Agent Swarm

The prompt design, agent instruction contracts, and data flow behind the 6R Application Rationalization Framework — the same Bedrock multi-agent swarm that powered the Digital Twin Simulator and the 36-app healthcare engagement. Five specialized agents, parallel execution, structured JSON output contracts, and explicit uncertainty reporting via missing_intelligence_list.

Live
Agent Swarm
Orchestrator · Telemetry · Dependency · Procurement · Provisioning · Synthesizer — native Bedrock multi-agent framework
System Prompts
Per-agent instruction contracts · structured JSON output schemas · single-responsibility design · explicit failure modes
Data Flow
DynamoDB context in → MCP tool calls → parallel agent outputs → Synthesizer → 6R recommendation + confidence + missing intel
Guardrails
Bedrock HIPAA guardrails · MCP read-only enforcement · confidence degradation on missing fields · PHI gate
Park Whisperer

A full-stack AI platform for theme park intelligence. Real-time crowd prediction, sellout event forecasting, satellite weather analysis, ML ride-wait models, and daily AI-generated social content — all running 24/7 on a multi-cloud stack across Azure, GCP, and AWS. Built and operated solo under $100/month.

Live
Infrastructure
Azure Functions · GCP Vertex AI · AWS S3 · Cosmos DB · Container Apps
AI Stack
Multi-agent RAG · GPT-4o · Bedrock Claude · GOES-16 satellite ingest · custom ML models
Output
Daily AI content to 3 social platforms · ride wait forecasts · live sellout alerts
Operating Cost
< $100 / month · 13 platform components · 25+ deployed pipelines