{
  "slug": "how-i-used-ai-to-build-an-apple-watch-app",
  "title": "How I Used AI to Build An Apple Watch App",
  "date": "2026-10-08",
  "featuredClaim": "A non-developer used AI to think, decide, and build a working Apple Watch app tested in real conditions.",
  "description": "Kamil Banc, a non-developer, describes how he used AI tools including Grok, Codex, and Xcode to build Eggsitus, an interval walking app for iPhone and Apple Watch. He frames the project as evidence that AI can help people complete work beyond their current skills when roles are kept separate. The article outlines four distinct jobs: conversational reasoning, file-changing agents, human decision-making, and real-world testing.",
  "keyPoints": [
    "AI can help you do work beyond your current skills when used to think, learn, decide, and produce one testable result",
    "Four jobs must be kept separate: conversational AI for reasoning, agents for file changes, humans for decisions, and the real world for final validation",
    "Project evidence like passing tests is not the same as independent reliability audit—real-world use exposes issues simulators miss",
    "The method applies beyond apps to processes, analyses, customer workflows, or internal tools"
  ],
  "topics": [
    {
      "id": "tools",
      "slug": "ai-tools",
      "label": "AI Tools",
      "description": "Practical tools and platforms for AI implementation"
    },
    {
      "id": "implementation",
      "slug": "ai-implementation",
      "label": "Implementation",
      "description": "Hands-on implementation techniques and frameworks"
    },
    {
      "id": "strategy",
      "slug": "ai-strategy",
      "label": "AI Strategy",
      "description": "Strategic planning and implementation approaches for AI adoption"
    }
  ],
  "claims": [
    "Kamil Banc, who is not a developer, built an app called Eggsitus running on iPhone and Apple Watch.",
    "The project record reports 139 tests of shared, device-independent rules passing, along with simulator and signed builds.",
    "Real walks exposed Siri and AirPods audio problems, confusing setup, and a crowded Watch screen.",
    "AI can help people do work beyond their current skills when used to think, learn, decide, and finish.",
    "Four jobs must stay separate: conversational AI reasons, agents edit files, humans decide, reality validates."
  ],
  "claimTitles": [
    "Non-Developer Ships Watch App",
    "139 Passing Rule Tests",
    "Real Walks Exposed Problems",
    "AI Extends Current Skills",
    "Four Jobs Kept Separate"
  ],
  "originalUrl": "https://aiadopters.club/p/how-i-used-ai-to-build-an-apple-watch",
  "claimProvenance": [
    "source-summary",
    "source-summary",
    "source-summary",
    "author-interpretation",
    "author-interpretation"
  ],
  "primarySources": [
    {
      "title": "eggsitus.com",
      "url": "https://eggsitus.com/",
      "publisher": "eggsitus.com",
      "claimIndices": [
        2,
        3
      ]
    }
  ],
  "quote": "AI can help you do work beyond your current skills when you use it to think, learn, make decisions and produce one testable result.",
  "keyStatistics": [
    {
      "stat": "139 tests passing",
      "context": "The project record reports 139 tests of shared, device-independent rules passing, along with simulator and signed builds; the author notes this is project evidence, not an independent reliability audit."
    },
    {
      "stat": "24-page workbook",
      "context": "A premium workbook expands the same method into an AI-assisted thinking and work process with five fillable worksheets."
    },
    {
      "stat": "3 prompts",
      "context": "The author shares three recommended prompts for moving from having no idea to producing one inspectable, testable result."
    }
  ],
  "supportingContext": "Kamil Banc, a self-described non-developer, documented building Eggsitus, an interval-walking app for iPhone and Apple Watch, by using Grok for conversational reasoning and Codex with Xcode for file-changing agent work. His methodology separates four roles: conversational AI for thinking and learning, agents for code changes, the human for decisions, and real-world use for final validation. The approach is deliberately generalizable, with the author noting it applies equally to processes, analyses, customer workflows, or internal tools. Practitioners should note the author's own caveat that passing project tests do not prove reliability under real conditions like Siri interruptions or small-screen interaction, and that revenue, release status, and medical benefit remain unestablished.",
  "canonicalUrl": "https://kbanc.com/claims-library/how-i-used-ai-to-build-an-apple-watch-app",
  "markdownUrl": "https://kbanc.com/md/claims-library/how-i-used-ai-to-build-an-apple-watch-app.md",
  "jsonUrl": "https://kbanc.com/api/claims/how-i-used-ai-to-build-an-apple-watch-app.json",
  "source": {
    "publisher": "AI Adopters Club",
    "title": "How I Used AI to Build An Apple Watch App",
    "url": "https://aiadopters.club/p/how-i-used-ai-to-build-an-apple-watch"
  }
}