01 / Portfolio — 2026 Remote · Available for new work

Ruzzel Maestro AI Systems Developer. AI integration, automation, and custom tooling for teams that ship.

02 / Selected work

Seven shipped systems. No placeholders.

Each project below is a full-stack build — product, AI architecture, infrastructure, and copy. Live links where applicable. Everything else is in production or in active use.

  1. Macross — Multi-agent platform
    01 / Case study 01 / 06

    Macross

    A multi-agent platform, running in production.

    Macross is the multi-agent platform I use daily — rooms where specialized AI agents collaborate on actual work. It runs on Protoculture, an agentic harness with multi-provider LLM routing (Claude, Gemini, OpenAI), real-time orchestration, Docker-native deployment, and personality-driven agents.

    • Node.js
    • Docker
    • Claude / Gemini / OpenAI
    • WebSockets
  2. Numera — Full-stack accounting platform
    02 / Case study 02 / 06

    Numera

    An accounting firm, fully instrumented.

    A three-surface platform for a Philippine accounting firm: marketing site, CRM for pipeline management, and Workdesk where client work happens. AI ingests Gmail, runs OCR on receipts, categorizes transactions, and drafts BIR filings — end to end.

    • Turborepo
    • Next.js
    • Supabase
    • Claude
  3. GoNoGo — Automated QA agent
    04 / Case study 03 / 06

    GoNoGo

    An autonomous agent that audits your app.

    An autonomous agent that crawls a running web app and runs audits across seven lenses — functionality, design, UX, performance, accessibility, code quality, and content. Delivers two reports: one for humans, one machine-readable for coding AIs.

    • Python
    • Playwright
    • GPT-4o
    • Next.js UI
  4. noDeadfish — Job-offer negotiation tool
    05 / Case study 04 / 06

    noDeadfish

    Compose, send, and negotiate offers in real time.

    An AI-powered tool for composing, sending, and negotiating job offer letters in real time. Multi-step wizard, role-based access (Owner / Candidate), provision-level negotiation, and Gemini-backed conflict detection. Outputs signed .docx.

    • Next.js
    • Firebase
    • Gemini
    • docx generation
  5. VaiTAL — Personal health intelligence
    06 / Case study 05 / 06

    VaiTAL

    Your labs, decoded.

    Upload a lab report PDF. VaiTAL parses it, normalizes results, and produces actionable insights: what's out of range, what's trending, what to ask your doctor. Powered by Google Gemini for reasoning over parsed values.

    • Next.js 16
    • Supabase
    • Gemini
    • PDF parsing
  6. asBuilt — AI codebase documentation generator
    07 / Case study 06 / 06

    asBuilt

    Two documentations from one codebase.

    Feed asBuilt a zip, a local folder, or a GitHub repo. It analyzes the codebase and emits two documents: a technical reference tuned for AI coding assistants, and a human-readable overview for stakeholders. Multi-provider LLM support.

    • Next.js
    • Firebase
    • Multi-LLM routing
03 / Services

Three things, done well. Everything else is a referral.

  1. 01

    Business process automation

    Mapping the boring parts of your company onto systems that don’t need Monday mornings off.

    • n8n
    • Temporal
    • Zapier
    • Airtable
    • Retool
  2. 02

    AI integration

    Retrieval, agents, and evals wired into the tools your team already uses — not a separate tab no one opens.

    • OpenAI
    • Anthropic
    • Gemini
    • pgvector
    • Evals
  3. 03

    App & internal tools

    From the first Figma to the last TestFlight build. Opinionated stacks, shipped fast, documented properly.

    • Next.js
    • Astro
    • Supabase
    • Firebase
    • TypeScript
04 / Next step

Bring a problem. Leave with a plan.

30 minutes. No slides, no salesy monologue. You describe the system you need, I ask sharp questions, we leave with an honest read on what it takes to build it.

Prefer to write first?

Drop a note. I reply within 48 hours — always from me, never a template.