Matt Torcasso

I design, build, and operate production software end-to-end.

A builder who ships. I take an idea to a working, deployed product, and I stay close enough to the architecture to debug it, extend it, and keep it running in production.

How this was built

Everything on this page was built in collaboration with Claude Code, Anthropic's AI coding agent. That is not a footnote; it is the method.

I set the direction, design the systems, direct the implementation, review and test what the AI writes, and operate the results in production on my own infrastructure. The AI multiplies the output. The judgment, the taste, and the accountability are mine.

Selected work

Trainer App

In production
Trainer App client analytics hub: lifetime weight moved, weekly session metrics, and an automated coach's read
Mesocycle template library: 24 reusable training blocks filterable by resistance, cardio, and hybrid Week calendar with planned and scheduled client sessions (names anonymized)

A SaaS platform for personal trainers, built to sell. The wedge is speed: program a client's next training block by voice or through an AI agent instead of clicking through forms.

  • 25+ MCP tools expose the whole app to an AI agent: scheduling, programming, client management, and analytics
  • Client analytics hub with a custom metric engine and a reusable chart kit, deployed to production
  • Phone-first PWA; a feature is not done until it works on a real device in the field
Next.jsPWA MCP / AI agentsB2B SaaS

April

Live · daily use
April's live dashboard in demo mode: a morning briefing over a scenic backdrop, with schedule, training, money, and messages at a glance April's money panel in demo mode: portfolio value, gains, holdings, and a chat with the money-desk agent

A personal AI operations platform that runs my day. It lives on a Linux home server as a fleet of always-on services, and it is how I found out this whole approach actually holds up over months of real use.

  • Runs my calendar, reminders, and daily briefings, with hands-free voice through Siri
  • Live operations dashboard with real-time status and one-tap approve/reject controls for the trading system
  • Runs as systemd services designed to survive reboots and fail loudly rather than silently
AI agentsPython Linux / systemdAutomation

Governor

Live · real account

An observer over three deterministic trading strategies, each testing one of my market theses with real money, not a backtest.

  • Watches the three strategies run and studies what each one's rules actually produce
  • Surfaces only the trades the theories rate best; I make the final call on every one before execution
  • Live on a real, funded brokerage account since July 2026, benchmarked against simple buy-and-hold
Trading systemsRisk controls Human-in-the-loop

Entangled

Live · early access
Entangled landing page: Everyone needs a place to just let it out. No name, no account, no one watching, free forever

An anonymous peer-support platform: a safe first place to be heard, with matching between real people as the destination. A mission project, live in early access.

  • Live at entangled.chat, served from my own hardware behind a Cloudflare tunnel
  • AI spend runs under a hard daily cost cap; free for the people using it today, built to grow into a self-sustaining business
  • Privacy and anonymity designed in from the first commit, not patched on later
Node.jsPrivacy / safety Cloudflare

Also running

Ledger

A personal finance PWA that pulls accounts, spending, and investing into one calm view, on a considered green design system.

Jerry

An autonomous job-search agent. It sweeps 40+ boards nightly, scores roles against feedback I have given it, and drafts the slate I wake up to. If a well-matched application led you here, that was Jerry.

Usage dashboard

Tracks exactly what my AI tooling costs, per project and per model. Tokens are real money, and I run this operation like it.

How I work

I'm not the coder, and I'm upfront about that. What I bring is translation: I can take a technical topic, understand the infrastructure and the logic underneath it, use the tools hands-on, and see clearly where AI genuinely helps and where a simpler solution wins.

I'm an AI realist and a believer, and above all a connector, the bridge between the technical minds who build the tech and the people who actually need it. Closing that gap is the work I'm best at.