I rebuilt a $3,000,000/month app with Claude Opus 5.5
Notability, rebuilt from prompts, running on my iPad. Here is every prompt, the repo, and both ways to get it onto a device.
I rebuilt Notability, a note-taking app that does an estimated three million dollars a month, by describing what I wanted to Claude Opus 5.5 and reacting to what came back. It records while you write, replays the page in sync with the audio so you can see exactly what you were writing when someone said a thing, transcribes automatically, works out who was speaking, and hands any note to an agent that does the follow-up work. The whole thing runs on my iPad, and I can open the code and change any part of it.
What I tested
Six prompts, in order, each one reacting to whatever the last one produced. Every prompt below is verbatim, including the parts where I am vague or change my mind halfway through. The code is on GitHub, so you can clone it and tell your own agent to build your version: github.com/per-simmons/inkwell
Phase 0: Work out what it actually does
Before any code, the model researches the real app and writes the spec. The hard feature gets named up front: ink that replays in sync with the audio.
But I 1st just wanted you to get a sense of how notability works, so we can build out our own version. So I want the same kind of features, all the different notes. It's a relatively simple app. I guess the hardest part is the actual recording feature, and then being able to When you're recording and taking notes, getting exactly when you're taking notes on that record. So when you play back that record, it will show you exactly the note that you were taking. At the time of the record, if that makes sense. And then once we get there, what we're gonna do is we're gonna add some AI features onto this. I want this to function. So we're gonna get live transcripts in here. And then we're gonna also add a feature where, and I still haven't really thought through this, where we hand this over to an AI agent. Don't overcomplicate this. I want this UI to be simple, straightforward. Don't add all of these like, dumb, superfluous things that sometimes you tend to add. It should really be as basic as notability, and then we'll just stack our own features on top of it.
Phase 1: Every screen, drawn before it is built
Mockups of every screen first, so the parts I disagreed with got changed on paper instead of in code.
On the actual UX, there's a couple things that I don't like about notability. So, in this 1st phase, you can just note this in the PRD for the build agent. In this 1st phase, I want all of the different app screens, and I'm going to react to those, and I want us to come up with our own variation of looking at their recordings, because I don't like how notability does it. They have some funky UX that I want us to change, especially because we're going to be live transcribing this. Tell the agent in the PRD to just use its best judgment and then come back to me with some kind of recording output that I can react to in the app screens when we put those together in phase one.
Phase 2: Build the real application
The actual iPadOS app, built and running on a device.
Go ahead and just build this out into a proper iOS, or I guess, iPadOS application. So full, all the best practices, do some research on this, just make sure that you're kind of double checking your work, you could even spawn an agent to do this, just in building all of this out. I'm assuming it's going to be react native, but let me know. I just want this to be a functioning application. If it's gonna be more complicated to build in Swift, then you can just avoid that. And yeah, I mean, QA, do everything, don't stop until this app is live or as close to live on my device as possible.
Phase 3: Hand a note to an agent
One button that packages the handwriting, the transcript and who said what, then gives an agent a link it can read.
I want the AI agent to see my notes, like in handwriting, and like read my handwriting, and also look at the transcript and see what note I was taking there at a certain time, and then just take all of that, and then understand what, you know, repo to go into. Basically, what tasks to do? And then just like run with that task based on the note. And I literally, it's probably just like one button, like hand over to an agent. Maybe the transcripts could just be stored in the cloud, and then when I hit copy, the agent will have immediate access to that. So I don't need to export the transcript and feed it into the agent, and then it can give the PDF of the actual of my handwritten notes as well. We're probably going to need speaker detection as well, and an ability to change the speaker names as well and store people's speaker names.
Phase 4: Accounts and a real database
Sign-in and Postgres, both from Neon, so notes belong to a person and follow them between devices.
Add sign-in and a real database to this app so more than one person can use it, each with their own notes. Use Neon for both. Neon now does authentication as well as Postgres, so set up Neon Auth rather than bolting on a separate auth service. Create the schema, wire the connection string in properly instead of hardcoding it, and make sure the users Neon Auth creates are readable from my own tables. Then go through everything the app currently stores on the device (notes, recordings, transcripts, subjects) and give each row an owner, so signing in on a different iPad brings my own notes down and nobody can read anyone else's. Tell me what happens to the notes already on my device when I sign in for the first time, and handle that migration rather than losing them. Keep the app working offline. It should not need a connection to open a note I already have.
Phase 5: Make it production ready
Storage, authentication, and whatever else the app needs before anyone other than me can use it.
Set up more database storage, and authentication, and anything else if needed, to get this to a fully functional, production ready application.
Getting it onto your own iPad
You install it yourself from your Mac over a cable, and it never goes near the App Store. A free Apple ID works, with the catch that the app stops opening after seven days until you plug in and build again. Ninety-nine dollars a year to Apple makes that a year instead.
Get this app running on my iPad. Walk me through it and do the parts you can do yourself. Set the bundle identifier to something unique to me. Turn on automatic signing and use my personal team. Make sure the deployment target matches my iPad's iOS version. Then tell me, step by step, exactly what to tap on the iPad itself. I know Developer Mode and trusting the certificate are involved, but tell me where those settings actually are. I'm using a free Apple ID, not a paid developer account. Tell me what that limits and what I'd have to redo when the app stops opening.
Putting it on the App Store
Only worth it if you want strangers using it. The ninety-nine dollars stops being optional, you need a hosted privacy policy, you declare every service the app sends data to, screenshots at every size Apple asks for, an in-app way to delete an account, and then review takes days and can come back no.
Get this app ready to submit to the App Store. Do the code and config side yourself, and give me a checklist for the parts only I can do in App Store Connect. On the code: set a real bundle identifier, fill in the version and build numbers, write every usage description string the app needs (microphone, speech recognition, anything else), add an in-app account deletion path if the app has accounts, and make sure the archive builds clean with no warnings that would fail validation. Then tell me: what my App Privacy answers should be based on what this app actually collects and where it sends audio, what my privacy policy has to say, every screenshot size I need, and what in this app is most likely to get rejected in review. Be specific about the rejection risks rather than reassuring me.
What this is and is not
This is not a plan to clone Notability and go make three million dollars a month. Building the app turned out to be the quick part. Everything after it is the actual work: getting in front of people, convincing them to try it, and giving them a reason to stay. Notability has years of head start and millions of users who are not looking for a replacement.
What you get instead is smaller and more useful. The app works the way you work rather than the way an average user is assumed to, and you can open it up and change anything you disagree with. And you find out how short the distance actually is between wanting a piece of software and having it running on your iPad.
Comments
Sign in to join the conversation.