iOS × AI
iOS AI
We track 37 iOS AI case studies from 16 engineering teams. SwiftLee, Duolingo and DoorDash write about it most. Many posts also cover Xcode and Developer Tools. The posts run from 2017 to 2026. The newest is from October 2026.
iOS AI articles 1–30 of 37
Agentic iOS Development with RocketSim and RocketTrace
Antoine van der Lee built his Video Compressor app with AI agents that can actually see and measure what they're building. His accessibility score jumped from 0/100 to 99/100 without manual testing.
Introducing RocketTrace: Using Xcode Instruments with AI Agents
Antoine van der Lee just launched RocketTrace, a Mac app that makes AI agents 6x more efficient at finding iOS performance issues. The benchmark results are striking: agents found more bugs while using a fracti...
Why Expo is a great fit for new and existing React Native apps
Keith Kurak from Expo makes a bold claim: AI coding agents don't eliminate the need for cross-platform frameworks. They actually make the case stronger.
The iOS Simulator Inside Cursor, Claude Code, and Codex
Antoine van der Lee, creator of RocketSim, is rethinking the iOS Simulator's role as AI agents take over coding. His latest move? Embedding the Simulator directly into Cursor, Claude Code, and Codex.
How AI Learned to Investigate Mobile Build Failures Like an Experienced Support Engineer
Archana Indran's team at Salesforce turned years of mobile debugging expertise into AI that investigates build failures like a senior engineer. Eight people now support 60+ repositories with less firefighting.
How We Automated iOS Unit Test Generation with AI
Kush Agrawal from Duolingo just shared how they generated 85,000 lines of iOS test code with almost zero manual effort. The bottleneck in software development has officially flipped: it's no longer writing code...
SwiftUI Best Practices, straight from Apple's Xcode 27 Agent Skill
Antoine van der Lee reverse-engineered Apple's official SwiftUI Agent Skill from Xcode 27 and found something surprising: it's laser-focused on performance, but leaves out huge chunks of everyday SwiftUI develo...
AI-Powered Xcode Simulator Automation (token-efficient)
Antoine van der Lee just shipped a CLI that makes AI agents 19% faster at controlling Xcode Simulator while using 63% fewer tokens. If you're building with AI coding assistants, this changes the game.
Record, generate, run: AI-powered UI test generation for iOS
Grab Engineering just turned a days-long iOS testing nightmare into a 10-minute workflow. Their AI-powered system records your app interactions and auto-generates complete UI tests, including mocks, feature fla...
Leveraging AI to build a faster iOS CI system
Muhieddine EL Kaissi from Thumbtack cut iOS CI time in half using runtime coverage instead of running every test. His Smart Test Selection system proves you don't need faster tests—you need fewer tests.
Xcode Instruments Time Profiler: Improve performance with AI
Antoine van der Lee just achieved a 25x performance improvement using AI agents and Xcode Instruments. His workflow shows how AI can analyze profiling data and iterate on optimizations faster than manual debugg...
Network Requests Optimization using Xcode's Simulator & Agents
Antoine van der Lee reveals how combining AI agents with continuous network monitoring caught bugs he'd been missing for years. The secret? Stop opening proxies only when you need them.
How Dart and Flutter are thinking about AI in 2026
Mariam Hasnany from Google's Flutter team just dropped their AI strategy, and the numbers reveal a massive shift: 79% of Flutter developers already use AI assistants. But there's a trust problem.
Xcode Build Optimization using 6 Agent Skills
Antoine van der Lee just open-sourced an AI agent skill that saved one iOS team 87% on incremental build times. That's 61 seconds per build, translating to 5 hours saved monthly at just 10 builds per day.
Using an MCP to perform product optimizations
Antoine van der Lee stopped guessing what to build next. By connecting his AI coding agent to Amplitude analytics via MCP, he now makes product decisions backed by real user data without leaving his IDE.
How We Claudified Our iOS App Without Wrecking Our Codebase
Dan Federman from Tolan reveals how Claude now writes 55% of their iOS commits. And their crash-free rate improved while doing it.
Vision-Based Mobile App Testing CLI for Claude Code
Revyl introduces a CLI tool that gives Claude Code vision-based mobile app testing capabilities. The tool interacts with apps like a human — no scripts, selectors, or element IDs needed — enabling a full write-...
Pro Tip: Use Xcode Instruments Time Profiler with AI for Performance Analysis
Antoine van der Lee (@twannl) found a quick way to get performance fixes from Xcode Instruments: deep copy the Time Profiler call tree and paste it into an AI agent.
Do you need an MCP to build your native app?
Sentry ran 1,350 trials to answer an uncomfortable question: does their newly acquired XcodeBuildMCP tool actually beat a simple markdown file for iOS development?
Swift Testing Agent Skill: Write high quality tests with AI
Antoine van der Lee from SwiftLee just open-sourced an Agent Skill that teaches AI to write Swift tests the right way. No more serialized tags killing your test performance.
Why Apple Is Secretly Betting Against Native iOS Development
Apple is quietly pushing developers away from the native iOS stack they've championed for over a decade. The evidence? Look at what they're building, not what they're saying.
Core Data Agent Skill: Now available open-source
Antoine van der Lee just open-sourced a Core Data Agent Skill that could save you from rookie persistence mistakes. If you're still working with Apple's older framework, this is a game-changer.
SwiftUI Agent Skill: Build better views with AI
Antoine van der Lee from SwiftLee introduces an open-source Agent Skill that teaches AI to write better SwiftUI code. No more fixing the same mistakes over and over in your AGENTS.md file.
AI App Development: What I Learned in One Month
Antoine van der Lee shipped an AI-powered app in one month and hit a wall so hard he almost killed the project. His biggest mistake? Moving too fast.
11 Things I learned after using AI Agents full-time
Antoine van der Lee went all-in on AI agents for iOS development and jokes that 'Arie and Ingrid (AI) are doing my work while we're having lunch.' After months of daily use, his workflow has changed more than i...
Agent Skills explained: Replacing AGENTS.md with reusable AI knowledge
Antoine van der Lee reveals why he ditched AGENTS.md files across all his projects. The replacement? A reusable AI knowledge system that's already supported by Cursor, Claude, and Gemini.
The State of Agentic iOS Engineering in 2026
Thomas Ricouard spent only 2% of his time in Xcode last year while shipping more iOS code than ever. His secret? Treating AI agents as tireless coworkers, not autocomplete tools.
Scaling Mobile UI Testing with AI
Trendyol scaled from 4,869 to 10,400 UI tests in under a year — while keeping execution under one hour. Here's how AI became their test generation engine.
Accelerating on-device ML on Meta’s apps with ExecuTorch
Meta just shared how they moved billions of daily users to their new on-device ML framework. The performance gains are substantial.
How we reduced manual regression tests by 70% using AI tools
Duolingo's QA team cut manual regression testing by 70% using AI. Here's how they made it work at scale.