Jose Antonio Licon · Pittsburgh, PA

One person.
Many very different projects.
One engine.
Shipping constantly.

I build apps, games, and platforms — powered by an AI development system I built myself. Product manager and engineer, open to consulting.

Get more from AI →See the workThe engine →

Xanadu isn't an AI assistant. It's an .

Not “Antonio uses AI to help him code” — an unattended system that plans the work, writes the code, tests it, and fixes its own mistakes, then brings back only the decisions that need a human.

Most people describing AI-assisted development mean : a smarter autocomplete with someone at the keyboard. This is categorically different. Nobody is at the keyboard.

The apps below aren't just products. They're the benchmarks.

That's Xanadu. How it works →

What could it do for your team? →

Projects

The engine

Xanadu

An that compresses two weeks of work into two days of wall-clock time. Here's how it works.

Xanadu architecture: a task backlog runs through four local model tiers, escalating to Claude only when stuck; failures and fixes feed a shared learning store; the same engine scales from a solo Mac to parallel workers to rented cloud GPUs.
Automation, learning, and scaling run as one loop. Click to enlarge.

Tasks completed autonomously

1,200+

First-pass success rate

70%

Commits in the last 30 days

581

From the task logs and git history across 21 of the last 30 days; updated 2026-09-27.

The loop

A turns a into small, testable . An executor writes each change. A validator runs and the task’s own — nothing counts as done until they . Failures are classified, fed back into the next attempt, and escalated if they keep coming. All state lives in the roadmap and , so a run survives being stopped and picks up where it left off.

The ladder

Every task starts on , on . Day to day, that’s a Mac running a coding model through Apple’s — and in practice it handles nearly everything. For big sprints it scales out to : one rented or many, each running agents , with headroom for larger models if a job ever calls for them; most of Galaxican’s 600+ tasks ran that way. Claude sits at the top, reached only when a task has beaten every open-model , so compute goes to the problems that genuinely need it. Gemini is the outside voice: I consult it for creative work and as a sanity check on what the loop produces.

Swappable by design

Every rung of the ladder is a setting, not a rewrite. Each tier names a model, and swapping one in — a newer release, a bigger dense model, a small fast one, a coding specialist — is a config change. When a better open model ships, Xanadu gets better the same day.

It learns

A immune system blocks mistakes it has already seen. A loop turns repeated fixes into permanent rules shared across every machine. And a of every task shapes what gets planned next.

In practice

ProjectsDash

From an idea to a working tool in under three days

I woke up with the idea, had a quick chat with Claude to shape a , and pointed Xanadu at it. On a single Mac, with a and no cloud bill, it worked through the roadmap largely unattended. Then I polished the rough edges with Claude.

first to finished roadmap
2.75 days
roadmap tasks done — 35 by Xanadu
49 of 49
lines of , with test suites
4,455
cloud compute: one laptop
$0
See ProjectsDash →

Galaxican

Scaling out when the roadmap is big

Galaxican is where Xanadu was proven and hardened. For its biggest push, the same loop scaled out to on a rented — capacity that costs a few dollars an hour — and the game shipped to both app stores.

tasks completed autonomously
626
passed on the first attempt
483
for the parallel
2 weeks
App Store and Google Play
2 stores
See Galaxican →

Want a loop like this for your team or your product? Get more from AI →

Why I built it

I started where everyone starts — Claude, Gemini, the usual suspects. I was amazed at what was possible. Then I ran out of .

Most people slow down at that point. I bought a maxed-out MacBook Air and started learning instead.

What began as a workaround turned into something more interesting: a complete development loop. Product ideation. analysis. generation. Code execution across . Models that fail over to more capable when a task is too hard. Error patterns that get learned and encoded so they don't burn retries twice.

Now I set it running overnight. By morning, the project is mostly done. When I need more firepower, I spin up and the backlog burns down in parallel, at a cost that doesn't require a VC.

It didn't replace the craft — my background as a full-stack developer and technical product manager is what makes the system work, not what it replaced. I still drive. I still take the wheel when the models hit a wall, or the project needs a pivot. methodology is the backbone of the whole system — not just a buzzword, but the actual structure that keeps every project on this page moving at once.

This isn't a silver bullet. It's a superpower.

Background

Product manager and engineer — I write the , and I build the thing it describes.

Before Xanadu, I spent my career on both sides of the product line: as a product owner and manager setting direction, and as the web and mobile developer shipping the code. That work spans podcasting, public media, higher education, 3D software and games — including live-audio apps and Alexa skills for Pittsburgh public radio.

Xanadu is what happens when those two jobs meet: product discipline, encoded into a system that does the building.

Product and technical leadership roles with

  • Libsyn
  • SoundStack
  • Autodesk
  • University of Pittsburgh
  • WYEP 91.3 FM
  • Wild Pockets
  • Asia City Media Group

More on LinkedIn and GitHub.

Want that on your team? Get more from AI →

Consulting

Get more from AI.

I turn product people into builders, and help dev teams ship more — and better — with AI. ProjectsDash started as an idea one morning — and was working software three days later.

I spend most of my time building and traveling, so I'm not looking for a full-time role. I take on a few focused engagements at a time.

For product leaders

Turn your roadmap into running software

For technical , product leads, and founders. I help you set up a development loop and learn the workflow I use: shape a with a , hand the bulk of the build to an , then polish with an . You stop waiting on a queue and start shipping your own ideas.

For dev teams

A measured , not a promise

For engineering leaders. We baseline one team’s , , and , set up the loop on your real — with as the for “done” — and compare after about six weeks, with a first read at two. You keep the setup and the numbers either way.

For existing codebases

Modernize without the big rewrite

Clean up, extend, port, or re-architect an existing codebase — splitting out services where it actually pays, not because it’s fashionable. We start with an assessment and a that pins down what the code does today, then the loop modernizes it in small, tested steps, and your code stays on . Proven in Dart, TypeScript, Python, and Go; older languages welcome, COBOL included. If yours is new to the system, I’ll prove it out on a small project first, on me.

A side effect: most of the work runs on on hardware you control, so your AI bill grows far more slowly as you add developers.

Book a 30-minute callor email dev@spyderboy.com