Featured Work
Projects that define
what I do
Each project starts with a real problem. Click a featured project to explore its interactive visualization, or hover to preview the case study.
Flukebase
AI-first agent platform
A Go monorepo for building, deploying, and orchestrating autonomous ARIA agents with effect-based architecture. The backbone that manages infrastructure, CI/CD, DNS, email, and deployments for all my projects.
Problem
Managing multiple projects across different servers, domains, and deployment pipelines was a fragmented, manual process. No single platform could orchestrate AI agents alongside traditional infrastructure.
Solution
Built a unified Go platform with MCP server integration, agent orchestration, and full infrastructure management — from DNS to SSL to deployments. Every project in this portfolio is managed through Flukebase.
Impact
Manages 8+ domains, 5+ deployed apps, and orchestrates AI agents across all projects. Single control plane for the entire portfolio.
FeelTrack
Emotional wellness tracking
A wellness tracking app that helps users understand their emotional patterns through daily check-ins, mood visualization, and trend analysis.
Problem
People struggle to understand their emotional patterns. Traditional journaling is inconsistent, and existing mood apps lack depth or actionable insights.
Solution
Built a Rails 8.1 app with Hotwire for real-time interactions, rich mood visualizations, and pattern recognition that surfaces emotional trends over time.
Impact
Live at feeltrack.tech with SSL. Full production deployment managed through Flukebase infrastructure.
Pilate
AI-native Pilates studio management
An AI-native studio management platform purpose-built for Pilates studios, with a Go backend and Next.js 16 frontend. Unlike generalist fitness tools, Pilate is architected around autonomous AI agents that manage scheduling, revenue optimization, client relationships, and equipment-aware operations.
Problem
Pilates studio owners juggle scheduling, client management, payments, and marketing across disconnected generalist tools. No platform is Pilates-native — every competitor is a generalist fitness tool with AI bolted on, not foundational.
Solution
Built a Go API backend with a Next.js 16 frontend using shadcn/ui, Zustand state management, and React Query. AI agents handle scheduling optimization, equipment-aware capacity planning (reformer spots, apparatus), and progressive autonomy with human-in-the-loop approvals.
Impact
Targeting the $500M studio software market growing to $1.8B by 2033. First Pilates-native platform with foundational multi-agent architecture instead of bolted-on AI.
Vamos
AI-powered travel itinerary builder
AI-powered travel itinerary builder for Sao Paulo using LLM reasoning (GPT-4o/Claude Sonnet) to generate personalized, constraint-validated walking tour itineraries with guide matching and Bitcoin Lightning payments.
Problem
Planning multi-destination trips involves juggling spreadsheets, maps, bookings, and notes across disconnected tools.
Solution
Built a Next.js 16 travel planner with Prisma 7, NextAuth v5, OpenAI/Claude for AI itinerary generation, Stripe + BTCPay for payments, and Zod v4 validation.
Impact
AI-generated itineraries personalized to user constraints, with guide matching and dual payment options (Stripe + Bitcoin Lightning).
