Services How It Works Testimonials Websites Portfolio Let's Chat
Engineering Portfolio

Production AI systems.
All of it.

I design and build AI automation platforms end-to-end: voice agents, LLM orchestration pipelines, enterprise web apps, and real-time event-driven infrastructure. This is the work.

100+
n8n workflows in production
90+
Python execution scripts
50K+
monthly AI conversations
600+
locations served

Systems built in production

Not demos. Not side projects. Systems handling real traffic, real users, and real consequences every day.

Enterprise AI

AI Tools Platform

FastAPI web application with embedded Claude AI agent giving 200+ non-technical staff one-click access to 64 automation tools. Full role-based access control, audit logging, and Docker deployment. Replaced manual CLI workflows company-wide and enabled the business to scale operations without adding headcount.

64 tools 200+ users 94% provisioning time saved
Stack: FastAPI, Claude API, SQLite, Docker, Python, RBAC
Voice AI

Sallie Voice Control System

Real-time AI voice state machine controlling behavior for 600+ shop locations via n8n and Genesys Cloud APIs. Handles 50,000+ monthly conversations across inbound, outbound, and overflow flows. Replaced static per-location IVR configuration that previously required manual updates for every change.

600+ locations 50K+ monthly calls Real-time state machine
Stack: n8n, Genesys Cloud CX, Python, REST APIs, webhook architecture
Voice AI

Vonimate Voice Receptionist

Fully productized AI voice agent handling appointment booking, availability checks, call memory, and human escalation. Built on a 6-webhook event pipeline connecting Vapi.ai, n8n, Cal.com, and Google Sheets. Deployed for client businesses as a turnkey AI front desk.

Live in production 6 webhook handlers Full call memory
Stack: Vapi.ai, n8n, Cal.com, Google Sheets, Python
Analytics

Call Forensics Engine

SIP/PCAP packet analysis combined with Genesys CDR API data to reconstruct complete call paths, identify failure points, and surface audio quality issues. Reduced call investigation time by 87%. Built a 2,071-line IVR parser that enumerates every distinct caller path through any flow definition.

87% faster investigation 2 hrs to 15 min 2,071 LOC IVR parser
Stack: Python, SIP/PCAP, Genesys CDR API, scapy
AI Evaluation

IVR Testing Suite

Automated LLM evaluation infrastructure using parallel LiveKit call agents orchestrated by Claude. Auto-generates test cases directly from IVR flow definitions and runs 20 concurrent synthetic calls to validate behavior before any change reaches production. Previously, IVR changes were tested manually in live environments.

20 concurrent synthetic calls Auto-generated test cases Pre-production validation
Stack: LiveKit, Claude API, Python, asyncio
Framework

3-Layer AI Reliability Architecture

Directive/Orchestration/Execution pattern that separates LLM decision-making from deterministic execution. The core insight: 90% accuracy per step compounds to 59% success over 5 steps. This pattern keeps AI in the decision layer only. Self-annealing loop: every runtime failure fixes the script and updates the directive. The system gets stronger on each failure.

90+ scripts built on this pattern 100 workflows Self-annealing
Stack: Python, Claude API, n8n, Markdown directives
AI Research

Rainman Signal Fusion System

Multi-model orchestration system ingesting FRED macroeconomic data, Finnhub financials, GDELT news sentiment, and ACLED conflict data. Claude Opus orchestrates deep signal analysis; Claude Haiku handles batch preprocessing at scale. Built to demonstrate multi-source fusion and intelligent model routing based on task complexity.

4 data sources Multi-model routing Opus + Haiku orchestration
Stack: Python, Claude Opus, Claude Haiku, pandas, FRED API, Finnhub, GDELT, ACLED

100+ n8n workflows in production

Spanning contact center operations, voice AI, enterprise provisioning, analytics, and sales automation. A representative sample below.

Voice AI 7
  • Vonimate Virtual Agent Core
  • Vapi: Book Appointment Handler
  • Vapi: Check Availability Handler
  • Vapi: Memory Read/Write Handler
  • Vapi: Call Ended Handler
  • Vapi: Schedule Meeting Handler
  • Vapi: Escalate to Human Handler
Contact Center Operations 8
  • Sallie Control Hub
  • Sallie Bulk Update Engine
  • Sallie Gmail Forwarder
  • Shop Phone Alert (outage detection)
  • PRD Daily Outage Report
  • PRD Outage Routing Workflow
  • Extension Allocator
  • Update nextAvailable Extension
Enterprise Provisioning 5
  • Create Genesys Site (idempotent)
  • Create Genesys Location (idempotent)
  • Bulk Import Shop Form
  • Bulk Import Corporate Form
  • SCIM Update (Azure AD sync)
Analytics & Reporting 3
  • IT Service Desk Weekly Report
  • PRD Daily Outage Report
  • Shop Performance Dashboard Feed
Outreach & Sales 2
  • Apollo, Apify & Perplexity Deep Personalization System
  • Instagram DM Auto-Reply
Data & Lookups 2
  • LookupVerse (real-time data endpoint)
  • DEV_Lookup Endpoint (dev/prod pair)

Apps people actually use

From internal enterprise tools to client-facing business websites. All designed, built, and deployed end-to-end.

AI Tools Platform

Multi-user FastAPI web app with Claude AI agent. 64 tools available to 200+ non-technical staff. Role-based access, audit logging, Docker deployment on VPS.

Stack: FastAPI, Claude API, SQLite, Docker, Jinja2

Vonimate.com

Business automation services site with Cal.com booking integration, mobile-responsive design, and live testimonials. Built and deployed from scratch.

Stack: HTML, CSS, JavaScript, Cal.com

JB's Smokehouse Catering

Client business website for a catering company. Custom design, mobile-first, inquiry form integration.

Stack: HTML, CSS, JavaScript

CleanRight Professional Services

Client website for a cleaning services business. Service area pages, booking flow, brand-matched design.

Stack: HTML, CSS, JavaScript

Ridgeline Contracting

Client website for a contracting business. Project gallery, service descriptions, and lead capture form.

Stack: HTML, CSS, JavaScript

n8n Webhook Orchestrator

Custom webhook router deployed on Modal. Maps inbound requests to directives and executes Claude-orchestrated workflows. Powers the automation layer across multiple production systems.

Stack: Modal, Python, FastAPI, n8n, Claude API

Want to work together?

I take on a small number of consulting engagements alongside my full-time work. If you're building something that needs serious AI infrastructure, let's talk.