IT Architect and AI Agent Engineer

Elu Gonzalez

I design agents that build, review and verify production software. I set the bar; nothing ships until they clear it.

Elu Gonzalez in a suit, arms crossed, outdoors

10,413 contributions in the last year.

Behind the calendar: agent branches, pull requests reviewed by CodeRabbit, and tests that decide what lands in each product.

How my agents work.

I design the system and set the bar. The agents explore, implement, review each other, and only deliver what passes the tests.

  1. They explore before asking.

    Several agents read the repository in parallel: architecture, contracts, tests and debt. Only the questions the code cannot answer reach me, and no line is written until they are closed.

  2. The test fails first.

    Every change starts with a red test that describes the behavior. Execution agents with a tight scope turn it green. If it passes on the first run, the test is useless.

  3. Review has to hold up.

    CodeRabbit reviews every pull request. My resolution agent separates real findings from false positives, puts security and correctness first, and turns failures into regression tests.

  4. QA with fresh eyes.

    The reviewer is never the implementer. For critical deliveries I run independent reviewers in parallel, each with its own angle: integrity, strategy and editorial.

  5. Gates that block.

    Validators stop a delivery on near-duplicate pages, unsourced data, API spend above the cap, or any failed check in the app's validation manifest.

  6. The system learns.

    Each skill lives in its own repository, changes through a reviewed pull request, and passes an audit. It syncs itself at session start. Whatever stops saving work is rebuilt or retired.

What they have built.

Production products I designed, and my agents built and verified with this system.

  • iOS and watchOS app

    App Store

    RazFit

    A fitness app with subscriptions, Apple Watch and offline mode. The backend runs on Supabase with RLS, and purchases, App Store notifications and push run in Edge Functions.

    150unit and UI test files

    How it is verified

    An 18-check manifest gates every release, and an AGENTS.md routes agents to 27 architecture policies.

  • Tax advisory

    taxfactory.es

    Taxfactory

    Beyond the website, an online contracting system: Stripe payments, document signing and automatic delivery on Workers, D1, R2 and five queues with retries.

    328pull requests merged after review

    How it is verified

    Staging with E2E before every production release, and an AGENTS.md hierarchy checked by a test.

  • Multilingual content

    razfit.app

    RazFit Web

    Blog and programmatic SEO for search engines and AI assistants, with llms.txt and agent-ready Markdown on every page.

    18languages

    How it is verified

    Similarity, duplicate and boilerplate detectors, plus a hook that runs the full build and E2E before every push.

  • Internal tool

    VisuApp

    My App Store screenshot studio: canvas editor, per-language variants and direct publishing to App Store Connect, on Workers, D1, R2 and queues.

    3device formats: iPhone, iPad and Apple Watch

    How it is verified

    Built with mandatory TDD. If publishing fails halfway, it resumes from the last checkpoint.

  • My own package

    astro-markdown-for-agents

    An Astro integration that turns HTML into deterministic Markdown, so an AI agent can read a site without wading through markup.

    6client sites use it

    How it is verified

    CI with coverage and package verification before every release.

Experience.

Architecture at MSI Studio and my own products, built with agents. Before that, more than ten years in IT consulting.

MSI Studio

IT Architect and AI Agent Engineer

September 2024 - PresentFull-timeBarcelona, SpainTeam of 7 developers

I design the architecture and the CI of the studio's products with a team of 7: a European data space, a project and timesheet platform, and an AI rendering product.

  • IT architecture
  • Layered CI
  • EKS and Azure

Tools: TypeScript, Python, C#, Terraform, AWS, Azure, GitHub Actions

Freelancer

Infrastructure and products

2025 - PresentFreelanceBarcelona, Spain

Separate from MSI, I design products and client platforms and run them with my agents: Cloudflare Workers sites with synced data, programmatic SEO behind validators, and my own apps such as RazFit.

  • Autonomous agents
  • Cloudflare Workers
  • Programmatic SEO
  • iOS

Tools: Cloudflare Workers, D1, R2, Supabase, Astro, TypeScript, Swift

Before MSI

  • Pryme

    Senior IT Consultant

    December 2022 - August 2024

    Barcelona, Spain

    Business software in JavaScript, TypeScript and AL for Business Central, with Azure AI and Power Automate applied to real processes.

  • Ernst & Young (EY)

    Senior IT Consultant

    April 2019 - December 2022

    Barcelona, Spain

    IT audits of business applications: finding vulnerabilities, fixing them and speeding up user administration. EY Data Strategy certification.

  • Studentfy

    IT Consultant

    September 2015 - April 2019

    Barcelona, Spain

    Technical support for clients and teams in several countries, plus internal training on JavaScript frameworks and automation tools.

  • Supercellcomp

    IT Consultant

    June 2013 - June 2015

    Venezuela

    Admin systems across seven branches, handling about 8,000 CONATEL requests a month. I helped the company become third in the country for user registrations.

Skills.

What I build with, and where I have used it.

  • Codex

    Most of my agent work lives here. Each skill describes a whole process, like resolving a CodeRabbit review or generating SEO pages, and splits the work between agents that explore and agents that execute. A modified skill has to pass its contract tests before I use it.

  • Claude

    I use it to explore large repos and plan before touching code. On sites like Pedro Ochoa I run agents with fixed roles: one for Astro architecture, one for CSS, one for SEO. My skills sync from GitHub every time I start a session.

  • Grok

    I am trying it as an orchestrator. On RazFit Web I prepared a plan package so it hands out tasks with the same loop as everything else: explore, test first, separate review.

Let's talk.

If you need someone who designs agents and puts them to work on software that holds up in production, write to me.

elugon10@gmail.com
Location
BarcelonaRemote work welcome
Reply
Within a dayMy usual response time