This as-told-to essay is based on a conversation with Julia Starr, the founder of Julia Starr Coaching. It has been edited for length and clarity.
I’ve been a career coach for nearly a decade, and for most of that time, my business has been capped by one factor: me. As a solopreneur, my calendar only has so much space, 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 impact. 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 transformational step yet: I vibe coded an app that replicates my core methodology. It’s providing passive income and expanding access to my work.
I tried vibe coding with no preparation
In December, I signed up for a hackathon with Lovable, an AI tool that lets non-technical people build apps using natural language prompts. I decided to really dedicate myself to it, clearing my calendar and waking up at 5 am to be on the kickoff calls.
Robert Warren for BI
I was walking in with literally zero coding or product knowledge. What I did have was my trademark coaching framework: the VSA Method, where clients dig into their core values and strengths before taking small action steps to prototype different pathways forward. I wondered if I could put that into an app.
I started by telling ChatGPT I wanted to vibe code a product and asked how to begin. Then I workshopped my prompts in ChatGPT before taking them into Lovable.
After two days of that type of back-and-forth work, I had a starter version of the app. I tested it in the Lovable community, and pretty immediately, people came back saying it had given them useful ideas they never would have thought of on their own. I was amazed.
The initial output was impressive, but needed refining
The app was promising, but it wasn’t perfect yet. I spent the next month turning it into a product that consistently worked.
Robert Warren for BI
For example, it regularly hallucinated job titles that didn’t exist. I thought I could just tell Lovable that the information needs to be legitimate and it would be fixed, but that didn’t work. I had to get creative and specific about setting the quality bar, so I required that Lovable find 100 instances of a particular job title on LinkedIn before surfacing it as a result.
I also did real user testing. I’d have people share their screens and walk through my app while narrating their inner dialogue out loud — what felt confusing, what surprised them, what they wanted next. I recorded all of it, then dropped those transcripts into Claude to identify the top changes to make and how to write the next prompt for Lovable. I did that after every single conversation.
After about 50 to 60 additional hours of work beyond the hackathon, I publicly launched my app, Threshold, in January.
My AI app provides passive income
Originally, I wanted to charge $150+ for the product because my intellectual property is valuable. However, during user testing, people told me they wouldn’t pay that much unless they already knew me and my work.
Robert Warren for BI
With that feedback, I decided the app would be more valuable if it served as a marketing funnel that could lead new customers to my higher-ticket offerings, rather than charging a premium for each individual app sale.
And I never worried the app would replace me entirely; I’ve coached long enough to know that having information doesn’t automatically lead to change. There’s a real gap between knowing what you could do and actually doing it, and crossing that gap usually takes a trusted human relationship.
Still, I wanted to put up a paywall to ensure customers were serious about their career pivots, so I landed on a one-time, $29 charge. At that price point, I’ve found that people share my app organically, and 75% of those who reach the paywall convert, so I’m making some meaningful passive income. I make small tweaks based on feedback here and there, but it’s mostly hands-off now.
What excites me most is what my app makes possible in terms of access. There are so many people who will never be able to work with me directly because of time or money limitations. This app can get them started — and for someone who’s been stuck, that first unlock changes everything.
