Personal execution notes from a non-tech builder who started with AI FOMO and is now navigating the messy reality of production beyond the initial 'one-click' hype.
Everyone says “AI makes anyone a developer” and that “the era of solo unicorns is here.” Honestly, I got hit by FOMO. As someone from a non-tech background, I started this journey with a mix of skepticism and hope: can I really build and run a service with just a few clicks?
As soon as I jumped in, I realized it’s way more than just clicking a button. Claude and Cursor write the code, sure. But understanding how that code actually behaves in a Production environment, how to hook up payments, or why security is blowing up… I was hit with a mountain of messy problems that no tutorial ever mentions.
Minbook is my personal execution log from that messy process.
Core Values: Build, Document, Share
- Build: I’m not just here to look at code; I’m here to build products that actually work. I’m currently building “real” stuff through WICHI (a GEO SaaS) and Make Me Unicorn (an open-source CLI).
- Document: I record the “trial and error” hidden behind the AI-generated code. This is where I log the raw data of Ops—auth, billing, infrastructure—the stuff you only see when you leave the lab and go live.
- Share: I hope my struggles as a non-tech builder serve as a roadmap for others. If the time I spent getting lost can become a shortcut for someone else, that’s enough for me.
From Experiment to Production
Most tutorials end at “Deployment Successful.” I’ve learned that real development actually starts after that. Minbook dives deep into this “Post-Deployment” territory.
- SaaS Ops: Billing, Security, and Infra issues that solo builders face.
- GEO (Generative Engine Optimization): How AI search engines work and how to optimize for them in the real world.
- Build Log: The architectural decisions and technical trade-offs made while scaling projects.
These are just my trial and error notes. If you’re struggling with similar problems, I hope you find a useful hint or two here.
Related Posts

What Happens When You Launch Without Monitoring
A guide to zero-cost minimum monitoring using Sentry and Betterstack, showing how an 80-minute pre-launch investment reduced error response time from 13 hours to 1 hour.

Build Your Own Self-Tuning Loop — Reference Implementation Guide
Self-Tuning Loop 4 steps (Generate → Capture → Analyze → Evolve) extracted as a universal module. Supabase DDL, diff capture utilities, analysis/evolution prompts, email/blog examples, GitHub reference implementation.

Cron + Telegram + Claude: Anatomy of a Self-Improving System at $0
The actual production system implementing Self-Tuning Loop from Part 1. Data collection (35 sources), AI curation, Telegram input pipeline, weekly auto-review, and Syncthing-based zero-deploy prompt evolution.