I built an AI tool to mimic my work. It has helped me create passive income from my solo business.

• Career coach Julia Starr used AI to vibe an app that mimics her signature framework.

• The app is a passive income stream and a marketing funnel, introducing his work to new clients.

• Starr said she’s not worried about her human coaching experience being replaced by AI.

This essay is based on a conversation with founder Julia Starr Julia Starr Coaching. It has been edited for length and clarity.

I’ve been a career coach for almost a decade, and for most of that time, my business has been capped by one factor: me. As a solopreneur, there’s only so much room in my calendar, and I’ve never been interested in growing a team.

About a year and a half ago, I started experimenting with how AI could help me expand my influence. I built prompts that clients could use to dig deeper between our sessions, and created an AI “co-coach” to support participants through each week of my group coaching program.

Last year, I took my most transformative step yet: I coded an app that replicated my original methodology. It is providing passive income and expanding the reach of my work.

The AI-Powered Solopreneur series explores how solo business owners use AI to thrive.

I tried Vibe coding without any preparation

In December, I signed up for a hackathon with Loveball, an AI tool that lets non-technical people build apps using natural language prompts. I decided to dedicate myself to it, clearing my calendar and getting up at 5 a.m. to be on kickoff calls.

I was walking in with literally zero coding or product knowledge. I had my trademark coaching format: the VSA method, where clients discover their core values ​​and strengths before taking small steps to prototype different paths. I think I can put it in the app.

I wanted ChatGPT to generate Vibe code and asked how to get started. I then workshopped my prompts on ChatGPT before taking them to Loveball.

After two days of that kind of back and forth work, I had a starter version of the app. I tested it in the loving community, and immediately, people came back with useful ideas they never thought they would have. I was shocked.

The initial output was impressive, but refinement was needed

The app was promising, but it still wasn’t great. I spent the next month turning it into a consistently working product.

For example, it routinely confused job titles that did not exist. I thought I needed the information to be valid to Lovable and it would be fixed, but that didn’t work. I had to get creative and specific about setting the quality bar, so Loveable needed to find 100 examples of a particular job title on LinkedIn before I surfaced it as a result.

I also did real user testing. I want people to share their screens and walk through my app while describing their inner dialogue out loud — what confused them, what surprised them, what they wanted. I recorded them all, then dropped those transcripts into the cloud to identify the top changes to make and how to write another prompt for Loveable. I did that after every conversation.

After working about 50 to 60 extra hours besides the hackathon, I publicly launched my app, Threshold, in January.

My AI app provides passive income

Basically, I want to charge $150+ for a product because my intellectual property is valuable. However, during user testing, people told me that they wouldn’t pay that much unless they already knew me and my work.

With that feedback, I decided the app would be more valuable if it served as a marketing funnel that could drive new customers to my high-ticket offerings, rather than charging a premium for each individual app sale.

And I never worried that the app would completely replace me; I have trained long enough to know that information cannot automatically change. There is a real gap between knowing what you can do and actually doing it, and bridging that gap usually takes a trusted human relationship.

Still, I wanted to put a paywall in place to make sure clients were serious about their career pivots, so I introduced a one-time, $29 charge. At that price point, I found that people shared my app organically, and 75% of those who reached the paywall converted, so I was making some meaningful passive income. I make small tweaks here and there based on feedback, but it’s mostly hands-off right now.

What excites me most is what my app makes possible in terms of accessibility. There are many people who cannot work with me directly due to time or money constraints. This app can get them started — and for anyone stuck, that first unlock changes everything.

Read the original article on Business Insider