Rodney Degracia

Senior iOS Engineer | Swift • SwiftUI • AI-Augmented Development

Building reliable mobile applications with modern Swift and SwiftUI. I use AI coding tools (Cursor, Claude, Codex) as force multipliers while maintaining strong architectural ownership and code quality.

I’ve delivered production iOS applications across product companies, agencies, and startups.

About

I’m a Senior iOS Engineer focused on building reliable, high-quality mobile applications using modern Swift and SwiftUI.

Over the years I’ve developed a strong foundation in architecture, concurrency, performance, and systems thinking. In recent years I’ve also become highly effective at AI-augmented development — using tools like Cursor, Claude, and Codex as force multipliers while still maintaining full ownership of design decisions, code quality, and platform correctness.

I enjoy solving complex technical problems, mentoring other engineers, and helping teams ship software that is both maintainable and robust.

Projects

LoreBuilder CLI

A persistent world you can talk to — Python CLI with RAG, Chroma, and SQLite sessions. Read the case study →

Bugmiester

A localhost trainer for Swift bug-spotting — Python, FastAPI, and free-text scoring. Read the case study →

Monitor

A personal AI coding agent CLI — Python REPL with tools and task planning. Read the case study →

ultra-trace

Deterministic Swift static analysis with an assist/gate split — Python, Swift Core, optional Advanced SIL. Read the case study →

World-Sim

A local narrative simulation with split storage, grounded play modes, and a companion World Builder. Read the case study →

Desktopper

Ordinary language to a local schema-driven app — Python, SQLite, Safari. Read the case study →

Maximus

An LLM harness for contest ML — with a human on the train gate. Read the case study →

Greenfield

A spec-first harness for building a new app one verified unit at a time. Read the case study →

super-duper

A planning and execution CLI that turns a goal into a hierarchical plan and validated workspace artifacts. Read the case study →

llm-platform

A capability-agnostic LLM tool-calling runtime with a plugin host. Read the case study →