changyouΒ·Oct 13How to Build an iOS App with AI: A 7-Step WorkflowUse Claude Code or Codex to define an MVP, build in modules, and prepare for an App Store launch.
changyouΒ·Sep 21I Turned App Store Connect Releases Into an Auditable PipelineWhat a real bilingual iOS release taught me about asc CLI, agent skills, stale metadata, screenshot automation, and API boundaries
changyouΒ·Sep 8iOS Visual Regression Testing with simctl and Pixel DiffsA practical UIKit screenshot pipeline, a paywall layout bug, and the failure modes to fix before trusting CI.
changyouΒ·Sep 4AI Image and Video Agents Need an Evaluation Loop, Not Just a Better PromptA practical architecture for planning, judging, failure routing, targeted retries, cost controls, and human reviewA response icon1A response icon1
changyouΒ·Aug 30Context-Aware AI Code Review: Beyond the DiffMost AI code review systems start with a pull request diff. That is useful, but it is not enough.
changyouΒ·Aug 24Apple Foundation Models PCC: From Entitlement to RuntimeIf you are building an iOS or macOS app with summarization, rewriting, translation, or document Q&A, Apple Foundation Models deserves aβ¦
changyouΒ·Aug 11The 5 Assets Developers Should Build in the AI EconomyAI will not make you rich automatically. It can lower the cost of turning expertise into products, workflows, customers, distribution, andβ¦
changyouΒ·Jul 25I Built a Durable AI Knowledge Base with Markdown and GitWhy search alone does not create memory β and how source layers, agent rules, and deterministic checks keep a knowledge base useful overβ¦
changyouΒ·Jul 17What 178 Claude Code Sessions Taught Me About Working With Coding AgentsHow /insights turned repeated mistakes into CLAUDE.md rules, reusable Skills, and evidence-driven agent workflows
changyouΒ·Jul 16DESIGN.md: Stop Letting AI Guess What Your UI Should Look LikeA practical workflow for turning visual intent into a versioned, lintable contract for coding agents.