June 2, 2026 5 min read
How I Shipped an AI Product in 48 Hours
A weekend, one LLM call, and zero features nobody asked for. That was the entire spec.
AIProductShipping
SoulCompass started with a two-sentence question. Could the Bhagavad Gita answer any modern human problem, and could an AI find the exact verse in real time. I gave myself a weekend to find out.
The trap with AI side projects is spending 80 percent of the time on the wrapper and 20 percent on the AI. I inverted that. The product had to do exactly one thing well: take a problem in plain language, return the shloka that speaks to it, plus a modern interpretation.
What I cut on day one
- Signup and auth. If the product needs an account to be useful, the product is not useful yet.
- A database. Every response is stateless, so I did not need one.
- A backend I control. Gemini API + Vercel serverless functions covered everything.
- A design system. Tailwind + one accent color, no component library.
- Analytics. First launch, first hundred users. I wanted feedback, not funnels.
The stack, top to bottom
Next.js frontend. Gemini API for verse retrieval and interpretation. Web Audio API for ambient frequency sounds during reading. Vercel for deployment. That is it. No queue, no cache, no CDN gymnastics. Cold start latency was fine because the LLM call dominates the round trip anyway.
The part I over-invested in
Prompt engineering. The whole product is worthless if Gemini returns a generic verse. I spent about six hours iterating on one system prompt with 30 problem inputs, checking that responses were contextually correct rather than surface-level pattern matches. This is where 80 percent of the perceived quality lives.
If you ship an AI product, the prompt is the product. Everything else is packaging.
What I would do differently
One thing. I would have added a way for the response to be shareable as an image from day one. Every user who found something meaningful wanted to share it. I shipped the sharing on day four and lost a whole growth loop in between.
The lesson holds beyond this project. Ship the smallest version that reveals whether people care. Then ship the sharing before you ship anything else.
Keep reading
Why I Am Building AI Consumer Products Solo in 2026
For the first time in software history, one engineer can ship a real consumer AI product in a weekend. Here is why I left founding engineer roles to focus on it.
Designing React Native for Users Who Do Not Speak Your Language
What building an earned wage access app at Unipe taught me about React Native for users who do not have latest phones, fast internet, or English as a first language.