stphndxn.com

Over the past year, a lot of developers have experimented with adding AI to their apps.

Over the last year, I’ve started noticing something subtle but important.

There was a moment — not long ago — when prompt engineering felt like the future.

In late 2025, I found myself caught in a loop.

OpenAI just wrapped their biggest event of the year — and it wasn’t just about AI.

If you’ve read any of my recent posts, you know I’ve been deep in the weeds with Model Context Protocol (MCP), foundation models, and AI-native app design.

For the past few months, I’ve been diving deep into MCP (Model Context Protocol) — shaping inputs, modularising prompts, and designing smarter ways to talk to models like GPT-4.

Prompting doesn’t scale.

Last year, building with AI meant prompt engineering.

When I first heard about “MCP” in the context of AI, I shrugged it off.

Back in May 2025, I found myself between roles.

Since its introduction, SwiftUI has redefined how developers build fluid, Apple-like interfaces.

Swift 6 marks a major evolution in the language’s concurrency model, bringing powerful new tools and refinements that make asynchronous programming safer, faster, and easier to reason about.

A Complete Guide for Swift Concurrency and Clean Architecture Synchronizing local and remote data sources is one of the trickiest parts of app development — especially when you want the result to be clean, reliable, and concurrency-safe.

Going indie is a choice that demands clarity, commitment, and a bit of courage.

So, I started writing a guide on how to implement an authorization layer in our apps using Firebase Authentication — and before I knew it, I had written well over a thousand words on just the basics of Swift Concurrency.

Updated October 2025 to reflect my current focus on Swift, web, and AI engineering.