Source URL: https://simonwillison.net/2025/Jul/6/macos-app-built-entirely-by-claude-code/#atom-everything
Source: Simon Willison’s Weblog
Title: I Shipped a macOS App Built Entirely by Claude Code
Feedly Summary: I Shipped a macOS App Built Entirely by Claude Code
Indragie Karunaratne has “been building software for the Mac since 2008", but recently decided to try Claude Code to build a side project: Context, a native Mac app for debugging MCP servers:
There is still skill and iteration involved in helping Claude build software, but of the 20,000 lines of code in this project, I estimate that I wrote less than 1,000 lines by hand.
It’s a good looking native app:
This is a useful, detailed write-up. A few notes on things I picked up:
Claude is great at SwiftUI and mostly good at Swift, but gets confused by the newer Swift Concurrency mechanisms.
Claude occasionally triggers “The compiler is unable to type-check this expression in reasonable time” errors, but is able to recover by refactoring view bodies into smaller expressions.
Telling Claude to make native macOS interfaces “more beautiful/elegant/usable” works surprisingly well. I’ve seen the same with web frontend code.
Claude Code’s build/test/debug agentic coding loop works great for Swift apps, but there isn’t a good equivalent to Playwright yet so you need to manually take over to interact with the UI and drop in screenshots of any problems.
Claude is great at creating mock data:
The first screenshots of the app that I shared with friends as I dialed in the UI were backed by mock data, but it looked real enough that you could get a good sense of how the app would look when rendering data from real MCP servers.
Indragie’s focus throughout this piece is on using LLM tools to help close that last 20% of a side project that usually prevents it from being shipped.
The most exciting thing about this entire journey for me is not the app I built, but that I am now able to scratch my coding itch and ship polished side projects again. It’s like I found an extra 5 hours every day, and all it cost me was $200 a month.
Via Hacker News
Tags: macos, ai, generative-ai, llms, ai-assisted-programming, anthropic, claude, model-context-protocol, coding-agents, swift, claude-code
AI Summary and Description: Yes
**Summary:** This text discusses the experience of a developer, Indragie Karunaratne, who utilized Claude Code—an AI-powered coding assistant—to create a macOS application with minimal manual coding. The insights provided reveal both the strengths and limitations of leveraging AI tools in software development, particularly for enhancing productivity and usability in coding projects.
**Detailed Description:** The author shares their experience of building a macOS application named Context, emphasizing the significant role that an AI language model, Claude Code, played in this development process. Key observations include:
– **Automation with AI:** The developer notes they wrote less than 5% of the total lines of code by hand, illustrating how AI can dramatically accelerate software development by automating significant portions of the coding process.
– **Strengths of Claude Code:**
– Proficient in SwiftUI and reasonably competent in basic Swift.
– Effective at suggesting improvements for aesthetic aspects of the app’s user interface.
– Produces realistic mock data that aids in visualizing the application during the early stages.
– **Limitations Encountered:**
– Issues with Swift’s newer concurrency features, which the AI struggles to comprehend.
– Challenges with complex expressions that lead to time-consuming compiler errors.
– The need to manually intervene for certain tasks, particularly in UI testing, as the existing tools lack adequate support compared to alternatives like Playwright.
– **Personal Impact:** The author expresses excitement and newfound motivation in coding, feeling as though leveraging AI tools has provided them with extra time and resources to focus on side projects.
Overall, this narrative shows the integration of AI in modern software development, presenting both its potential for enhancing productivity and the challenges that still exist in fully replacing human developers with AI solutions. The insights can be valuable for professionals in the fields of AI, software security, and compliance, as they highlight considerations for AI tool implementation and dependency in agile software development environments.