---
title: "How I Used AI to Build An Apple Watch App"
description: "5 source-backed AI claims from How I Used AI to Build An Apple Watch App, with key statistics, context, and the original AI Adopters Club source."
url: "https://kbanc.com/claims-library/how-i-used-ai-to-build-an-apple-watch-app"
source: "https://aiadopters.club/p/how-i-used-ai-to-build-an-apple-watch"
date: "2026-10-08"
topics: ["tools", "implementation", "strategy"]
generated: "2026-10-09"
---

# How I Used AI to Build An Apple Watch App

By Kamil Banc | October 8, 2026

## Claims

1. **Non-Developer Ships Watch App** (source summary): Kamil Banc, who is not a developer, built an app called Eggsitus running on iPhone and Apple Watch.
2. **139 Passing Rule Tests** (source summary): The project record reports 139 tests of shared, device-independent rules passing, along with simulator and signed builds.
3. **Real Walks Exposed Problems** (source summary): Real walks exposed Siri and AirPods audio problems, confusing setup, and a crowded Watch screen.
4. **AI Extends Current Skills** (Kamil's interpretation): AI can help people do work beyond their current skills when used to think, learn, decide, and finish.
5. **Four Jobs Kept Separate** (Kamil's interpretation): Four jobs must stay separate: conversational AI reasons, agents edit files, humans decide, reality validates.

## Evidence

### 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." - Kamil Banc

### Key Statistics
- **139 tests passing**: 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.
- **24-page workbook**: A premium workbook expands the same method into an AI-assisted thinking and work process with five fillable worksheets.
- **3 prompts**: The author shares three recommended prompts for moving from having no idea to producing one inspectable, testable result.

## Context
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.

## Source
- Original: [How I Used AI to Build An Apple Watch App](https://aiadopters.club/p/how-i-used-ai-to-build-an-apple-watch)
- Cite: kbanc.com/claims-library/how-i-used-ai-to-build-an-apple-watch-app

## Primary Evidence
- [eggsitus.com](https://eggsitus.com/) (eggsitus.com; supports claims 2, 3)