Building an iPhone app with zero technical skills | Bryce Rattner Keithley
Episode
46 min
Read time
2 min
Topics
Health & Wellness, Artificial Intelligence, Software Development
AI-Generated Summary
Key Takeaways
- ✓Beginner's Mindset as Advantage: Not knowing technical boundaries prevents self-limiting behavior. Bryce acquired Railway infrastructure, used Claude Code, and navigated App Store submission without understanding what these tools fundamentally do. Stating ignorance explicitly to AI models — "I am not technical" — prompts more accessible, step-by-step guidance and surfaces solutions that informed users might never explore.
- ✓Two-Claude Workflow for App Store Submission: Use standard Claude as a technical architect to generate a structured plan, then pass those specific steps to Claude Code for execution. When Claude Code produces output, return it to standard Claude for verification before applying changes in the terminal. This division of roles — planner versus executor — makes complex mobile deployment manageable without engineering knowledge.
- ✓AI Video Production Pipeline: Anthropomorphized animal exercise videos are produced in three stages: generate a precise still image in Gemini with exact body positioning described literally, film yourself performing the exercise on an iPhone, then combine both in Higgs Field using the Cling 3.0 motion control model. Starting position accuracy in the Gemini image is the single biggest determinant of final video quality.
- ✓Prompting Precision Over Iteration: When AI image generation fails, rewriting the prompt from scratch outperforms copying and pasting the previous version. Adding hyper-literal spatial descriptors — "both feet off the ground," "head to the left," "knees above hips" — reduces misinterpretation. Screenshots of physical reference positions can substitute for text descriptions when repeated verbal prompting stalls on the same error.
- ✓App Store Rejection Recovery: Apple's first rejection of Daily Hundreds flagged three fixable issues: an incorrect parental advisory checkbox, a Sign In with Apple feature that was implemented but never tested on iPad, and a missing account deletion button. Pasting Apple's rejection feedback directly into Claude generated a prioritized remediation list, and the app passed review on the second submission.
What It Covers
Bryce Rattner Keithley, a non-technical talent professional, built and shipped a fitness app called Daily Hundreds to the Apple App Store using Replit, Claude, Claude Code, Gemini, and Higgs Field — with no software engineering background — demonstrating that AI tools now enable complete beginners to build production-ready consumer applications.
Key Questions Answered
- •Beginner's Mindset as Advantage: Not knowing technical boundaries prevents self-limiting behavior. Bryce acquired Railway infrastructure, used Claude Code, and navigated App Store submission without understanding what these tools fundamentally do. Stating ignorance explicitly to AI models — "I am not technical" — prompts more accessible, step-by-step guidance and surfaces solutions that informed users might never explore.
- •Two-Claude Workflow for App Store Submission: Use standard Claude as a technical architect to generate a structured plan, then pass those specific steps to Claude Code for execution. When Claude Code produces output, return it to standard Claude for verification before applying changes in the terminal. This division of roles — planner versus executor — makes complex mobile deployment manageable without engineering knowledge.
- •AI Video Production Pipeline: Anthropomorphized animal exercise videos are produced in three stages: generate a precise still image in Gemini with exact body positioning described literally, film yourself performing the exercise on an iPhone, then combine both in Higgs Field using the Cling 3.0 motion control model. Starting position accuracy in the Gemini image is the single biggest determinant of final video quality.
- •Prompting Precision Over Iteration: When AI image generation fails, rewriting the prompt from scratch outperforms copying and pasting the previous version. Adding hyper-literal spatial descriptors — "both feet off the ground," "head to the left," "knees above hips" — reduces misinterpretation. Screenshots of physical reference positions can substitute for text descriptions when repeated verbal prompting stalls on the same error.
- •App Store Rejection Recovery: Apple's first rejection of Daily Hundreds flagged three fixable issues: an incorrect parental advisory checkbox, a Sign In with Apple feature that was implemented but never tested on iPad, and a missing account deletion button. Pasting Apple's rejection feedback directly into Claude generated a prioritized remediation list, and the app passed review on the second submission.
Notable Moment
During a live demo, Bryce generated a leopard doing crunches in under ten minutes — first attempt failed on hand and leg positioning, second attempt succeeded after a full prompt rewrite. The finished video showed the leopard's gym reflection in a mirror, a detail no one explicitly requested.
Episode Transcript
I built an app called Daily Hundreds. I opened Lovable and Replit actually on the same day and left the simplest prompt. It was incredible to me that I could tell these AI tools, I want this, and it spit out a very basic minimum viable product of it. I asked you the other day. I was like, are you in TestFlight? And you're like, yeah. I was in TestFlight. And so now it's in the App Store. You got it approved. It's ready to go. We have anthropomorphic animal demos. This is my favorite part, and we're gonna see some pretty amazing ones. But can you walk us through how you generated this? I make the animal in Gemini. I film myself doing the exercise, and then I mash up the anthropomorphic animal with Bryce exercising to create the videos. Were there any hard skills you felt like you developed as you went through this process? I got really good at copying and pasting, but I think I knew how to do that beforehand. I I don't actually really know what Railway does, and yet it's there now. The fact that you, a very nontechnical person, are buying or acquiring Railway as your infrastructure without really knowing what it is is kind of amazing from a go to market perspective for these AI tools. And I'm sure saying what you don't know and then trusting the beep boop robot gods also helps you discover and push further than you would if you knew the boundaries of things. Welcome back to How I AI. I'm Claire Vaux, product leader and AI obsessive, here on a mission to help you build better with these new tools. Today, I have my friend, Bryce Ratner Keithley, who is decidedly not technical. She's actually spent her entire career in talent and people, but she has somehow beat me to the App Store with a Vibe Coded fitness app, including customized animal videos for any workout you wanna do. She's gonna walk us through her step by step and show you how a beginner's mindset can mean you can build anything you want with AI. Let's get to it. This episode is brought to you by WorkOS. AI has already changed how we work. Tools are helping teams write better code, analyze customer data, and even handle support tickets automatically. But there's a catch. These tools only work well when they have deep access to company systems. Your copilot needs to see your entire code base. Your chatbot needs to search across internal docs. And for enterprise buyers, that raises serious security concerns. That's why these apps face intense IT scrutiny from day one. To pass, they need secure authentication, access controls, audit logs, the whole suite of enterprise features. Building all that from scratch, it's a massive lift. That's where Work OS comes in. Work OS gives you drop in APIs for enterprise features so your app can become enterprise ready and scale up …
Get the full transcript (7,955 words) + summary by email — free
One-time email with the complete transcript and AI summary of this episode. No account needed.
One email, no spam. We’ll also show you what SignalCast does.
You just read a 3-minute summary of a 43-minute episode.
Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
More from How I AI
How I turned Claude into a self-improving PM assistant | Daniel Blum (PM, Melio)
Aug 31 · 46 min
Beyond Biotech
BIOSPAIN 2026: partnering, policy, and the rise of Spanish biotech
Aug 28
More from How I AI
I spent $20,000 on Devin in a month. Here’s what I learned | Ryan Carson (solo founder)
Aug 24 · 44 min
The Tim Ferriss Show
#872: Graham Duncan — Talent Is the Best Asset Class (Repost)
Jul 1
Books, tools, and gear mentioned in this episode
SignalCast may earn commission on purchases via these links. As an Amazon Associate, SignalCast earns from qualifying purchases.
Tools
“built and shipped a fitness app called Daily Hundreds to the Apple App Store using Replit, Claude, Claude Code, Gemini, and Higgs Field”
by Google
“built and shipped a fitness app called Daily Hundreds to the Apple App Store using Replit, Claude, Claude Code, Gemini, and Higgs Field”
“Bryce acquired Railway infrastructure, used Claude Code, and navigated App Store submission”
“built and shipped a fitness app called Daily Hundreds to the Apple App Store using Replit, Claude, Claude Code, Gemini, and Higgs Field”
“combine both in Higgs Field using the Cling 3.0 motion control model”
by Anthropic
“built and shipped a fitness app called Daily Hundreds to the Apple App Store using Replit, Claude, Claude Code, Gemini, and Higgs Field”
by Anthropic
“built and shipped a fitness app called Daily Hundreds to the Apple App Store using Replit, Claude, Claude Code, Gemini, and Higgs Field”
Products
- Daily HundredsBy guest
by Bryce Rattner Keithley
“Bryce Rattner Keithley, a non-technical talent professional, built and shipped a fitness app called Daily Hundreds to the Apple App Store using Replit, Claude, Claude Code, Gemini, and Higgs Field”
More from How I AI
We summarize every new episode. Want them in your inbox?
How I turned Claude into a self-improving PM assistant | Daniel Blum (PM, Melio)
I spent $20,000 on Devin in a month. Here’s what I learned | Ryan Carson (solo founder)
I tested Grok Bot, Grok 4.6, and Cursor Origin - here’s my honest take
How a solo founder used Codex and ChatGPT to launch a fashion brand without engineers | Yana Welinder
Claude Code for normal people: skills, voice mode, and how to collaborate with AI
Similar Episodes
Related episodes from other podcasts
Beyond Biotech
Aug 28
BIOSPAIN 2026: partnering, policy, and the rise of Spanish biotech
The Tim Ferriss Show
Jul 1
#872: Graham Duncan — Talent Is the Best Asset Class (Repost)
Software Engineering Daily
Jun 11
Developing Multiplayer Games in Godot
Masters of Scale
Apr 16
Why CEOs need to think more like athletes, with investor Byron Deeter
Software Engineering Daily
Apr 7
FastMCP with Adam Azzam and Jeremiah Lowin
Explore Related Topics
This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.
Read this week's Health & Longevity Podcast Insights — cross-podcast analysis updated weekly.
You're clearly into How I AI.
Every Monday, we deliver AI summaries of the latest episodes from How I AI and 192+ other podcasts. Free for one show.
Start My Monday DigestNo credit card · Unsubscribe anytime