Claims Library Entry
How I Used AI to Build An Apple Watch App
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.
Published October 8, 2026 by Kamil Banc
Lead claim
A non-developer used AI to think, decide, and build a working Apple Watch app tested in real conditions.
Atomic Claims
What this article supports
Copy individual claims as needed.
Claim 1 · Source summary
Non-Developer Ships Watch App
Kamil Banc, who is not a developer, built an app called Eggsitus running on iPhone and Apple Watch.
Claim 2 · Source summary
139 Passing Rule Tests
The project record reports 139 tests of shared, device-independent rules passing, along with simulator and signed builds.
Claim 3 · Source summary
Real Walks Exposed Problems
Real walks exposed Siri and AirPods audio problems, confusing setup, and a crowded Watch screen.
Claim 4 · Kamil's interpretation
AI Extends Current Skills
AI can help people do work beyond their current skills when used to think, learn, decide, and finish.
Claim 5 · Kamil's interpretation
Four Jobs Kept Separate
Four jobs must stay separate: conversational AI reasons, agents edit files, humans decide, reality validates.
Evidence
Context behind the claims
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."
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.
Supporting 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.
How to Cite
Use the claim-level citation when you need a precise statement. Use the article or claims-collection citation when you want the wider argument and source context.
Individual Claim
Best when you need to cite one atomic claim directly inside a memo, deck, research note, or AI output.
"[claim text]" (Banc, Kamil, 2026, https://kbanc.com/claims-library/how-i-used-ai-to-build-an-apple-watch-app)Original Article
Use this when you want to cite the full newsletter article at AI Adopters Club rather than the structured claims page.
Banc, Kamil (2026, October 8, 2026). How I Used AI to Build An Apple Watch App. AI Adopters Club. https://aiadopters.club/p/how-i-used-ai-to-build-an-apple-watchClaims Collection
Use this when you want to reference the full structured claims collection on this page.
Banc, Kamil (2026). How I Used AI to Build An Apple Watch App [Structured Claims]. Retrieved from https://kbanc.com/claims-library/how-i-used-ai-to-build-an-apple-watch-appAttribution Requirements
- Include the author name: Kamil Banc.
- Include the source: AI Adopters Club or the structured claims page.
- Link to the original article or the claims page you used.
- Indicate any edits or transformations if you changed the wording.
Related Reading
More from the library
A structured prompt approach transforms performance reviews into actionable development plans by interviewing managers through six categories. The method prevents common AI pitfalls by collecting complete information before generating recommendations, producing budget-aligned plans in a single session.
5 claims
A detailed analysis of 30 days of ChatGPT and Claude conversations reveals 10 repeating prompt patterns that demonstrate systematic AI use. The author shares specific prompt structures for tasks like email triage, presentation assembly, and workflow documentation, showing how to treat AI as infrastructure rather than a casual tool.
5 claims
AI adoption fails because of habit problems, not training gaps. This practical guide shows how to build an AI reflex muscle in 20 minutes by automating one annoying task. The goal is developing automatic pattern recognition for AI opportunities.
5 claims