Alejandro Morales

I'm an AI engineer who designs and ships production AI systems: agents that do real work, retrieval that returns the right thing, evals that tell you whether it actually works, and LLM features that live inside real SaaS. I'm self-taught: no CS degree, no bootcamp, no corporate ladder. Everything I know, I learned by shipping, and I haven't stopped since.

Before software, I spent six years in operations management, leading a 12-person team in cannabis, one of the most heavily regulated industries there is. Seed-to-sale tracking, state compliance, and audit trails were the daily job. That operations background is why I can read what a business actually needs versus what it says it needs, and it is the core of how I approach forward-deployed work: embed, learn the constraints, and remove the manual process.

Today, I run an indie software studio where I architect, design, build, and deploy complete web applications as a solo developer. My stack is Next.js, React, TypeScript, Prisma, and Neon PostgreSQL, deployed on Vercel. I've shipped 8 production applications across 5 different industries: rental management, fintech, cannabis compliance, legal tech, and gaming.

What sets me apart is how I build. I don't just write code. I engineer with AI. Claude Code is my daily pair programmer. I've developed structured methodologies for AI-augmented development: master prompts that serve as 10,000-word product specifications, multi-agent workflows that handle everything from architecture design to deployment, and verification gates that keep AI-generated code honest. AI handles the repetitive work so I can spend my time on the architecture, the evals, and the judgment calls an AI can't make. The discipline is the point, and knowing where the AI breaks down is half of using it well.

My goal is simple: build software that solves real problems for real people, and ship at a pace that lets one developer do the work of a team, with the judgment a team gives you. Every product I build is designed to generate revenue and serve actual users, not sit in a portfolio collecting dust.

I usually ship solo, but I work the way a team needs: clear specs, reviewable PRs, and code someone else can pick up. I review my own work adversarially, I'm comfortable working inside other people's codebases and async handoffs, and I document the decisions the AI couldn't make, so the next person inherits the reasoning, not just the diff.