AI Development
AI Development covers practical ways Swift developers can use artificial intelligence to build better software. From agentic coding and AI-assisted workflows to LLM-powered tooling and automation, these articles focus on real-world techniques you can apply in Swift, Xcode, and modern app development.
Xcode Build Optimization using 6 Agent Skills
Xcode build optimization ensures both your clean and incremental builds remain performant. New Xcode versions or WWDC announcements introduce new best practices that you need to apply to ensure having the best build performance. While you might expect Xcode to apply new build settings automatically, the truth is you often ...
The “One More Prompt” risk of agentic coding
Agentic coding has the risk of doing "One More Prompt" before finalizing. I've been using agents for a while now and found myself running into this trap a few times before I realized how to solve it. Agents make it so easy to fix things, that it's tempting to increase ...
Agentic Development: Multi-Project Challenges
Running multiple projects with Agentic Development is very common. I found myself creating GitHub issues for all the ideas I've had in the past, while I'm not running a prompt straight away. It's fantastic for progression, but not always for success. It becomes mentally challenging, and it's easy to find ...
Give your AI agent eyes and hands on iOSFlowDeck lets Claude and Codex tap, scroll, find bugs, and fix them — on the real simulator. No Xcode. No manual steps. No human intervention. 7-day free trial. SwiftLee readers get 25% off.
A 9-Step Framework for Choosing the Right Agent Skill
Developers are increasingly faced with multiple options for the same task, which makes it harder to choose the right agent skill. More and more Agent Skills pop up, and they all have a great story on why you should use them. And honestly, most of the ones that I used ...
Using an MCP to perform product optimizations
A Model Context Protocol (MCP) can be invaluable when used properly, especially when talking about product optimizations. I've personally been playing around with it for a while now, and feel like I need to share my learnings due to the impact it has. In this case, I've been using it ...
Swift Testing Agent Skill: Write high quality tests with AI
Swift Testing is the standard for writing tests in Swift, but it's not always applied correctly in agentic development. I've felt the pain myself while working more and more with agents, and decided to convert all my Swift Testing articles into a new agent skill. I also looked up latest ...
Core Data Agent Skill: Now available open-source
A Core Data Agent Skill for those who still write a lot of old-fashioned Core Data. While we can use SwiftData, my experience is that many projects still rely on the older framework. I'm one of those and have extensive knowledge on this framework, and even gave a talk on ...
SwiftUI Agent Skill: Build better views with AI
A SwiftUI Agent Skill that helps you build better views or refactor existing ones. It's the reality we're in today, and I honestly can't live without it anymore myself. Several skills helped me improve the code quality produced by agents, and I'm happy to introduce you to a new open-source ...
AI App Development: What I Learned in One Month
It was December 2025 when I started focusing on AI App Development. I started a new YouTube series, From App Idea to 10K MRR, found an app idea, and started building. While I used AI tools for a while, this was the first time I started using it for a ...
11 Things I learned after using AI Agents full-time
AI agents are my biggest friends these days. I'm even making jokes to my wife, saying that Arie and Ingrid (AI) are doing my work while we're having lunch. I've been developing apps since 2009, but I can't remember changing my workflow so much as in the past months after ...
Agent Skills explained: Replacing AGENTS.md with reusable AI knowledge
Agent Skills solves a common problem I have with AGENTS.md files across my projects. Every project that I'm working on has its own AGENTS file. Whenever I encounter an invalid AI output, I try to update my AGENTS file to prevent it from happening again. This mostly meant documenting coding ...