"Beginning My Journey in AI" was the title of the first note I ever wrote about artificial intelligence. At the time, I admitted something simple: "I'm not an expert in artificial intelligence." I was just curious — and curiosity has a way of pulling you into unexpected rabbit holes.
This post is the story of the first one.
While I had already experimented casually with AI tools, my journey truly shifted when I stopped just chatting with AI and tried to build something real. As a lifelong tinkerer, I wanted to see if I could construct a functional, customized application from scratch without going back to school for a computer science degree.
If you're standing on the sidelines wondering how a non-developer actually navigates these tools, here's exactly what happened when I tried to build my first app.
The Vision vs. The "No-Code" Wall
I started where most beginners do: a low-barrier-to-entry platform that promised to turn simple text prompts into working software.
My goal was straightforward — a vacation trip board organizer to plan and visualize travels.
At first, it felt like magic. I typed in what I wanted and a clean, basic interface appeared. It felt like wizardry.
But the honeymoon phase ended fast. As soon as I began testing the app, I slammed into invisible walls:
- The Sluggish Search: The database search was painfully slow, making it useless for filtering destinations or itineraries.
- The Credit Crunch: The AI-powered features ran on background credits… which evaporated almost instantly.
- The "Free" Tier Wall: Before I could finish a prototype, the platform cut me off entirely.
I wasn't ready to abandon the project, but the tool had run out of resources long before I ran out of ideas.
The "AI-to-AI" Troubleshooting Loop
This is where the rabbit hole truly opened.
Determined to keep going, I bypassed the no-code interface and started researching workarounds. YouTube, Google, forums — anything that could help me understand why the app was struggling.
That led me to a bizarre multi-AI workflow that felt like orchestrating a digital team of rivals:
- Copy the sluggish search code or system logs from the app builder.
- Paste them into Copilot and ask: "Why is this tool processing searches so slowly, and how can we optimize the query?"
- Take Copilot's fix and drop it into another AI model: "Can you rewrite this to use fewer computing credits?"
Sometimes it felt brilliant — one AI acting as translator, another as debugger. Other times it was a comedy of errors. One AI would confidently propose a fix that relied on a feature the other AI didn't support, creating a loop of digital finger-pointing.
But even when it failed, I was hooked. I wasn't just consuming technology anymore; I was negotiating with it.
What I Learned on the Ground
If you're thinking about using AI to build your first app, skip the marketing hype and keep these practical realities in mind.
1. No-Code Doesn't Mean No-Logic
AI can write syntax, but you still have to design the logic. If you don't know how your data should flow, the AI will happily build a beautiful interface that leads nowhere.
2. The Resource Trap Is Real
"Free" tiers and credit systems are great for mockups, but they collapse the moment you start testing real logic or search capabilities.
Don't rely on a single AI. Different models catch different mistakes. When you hit a wall, ask another AI to look at the problem from a fresh angle.
What's Next?
My first vacation trip board was a messy, mismatched puzzle of tools — but it proved something important: the barrier to entry has officially collapsed. You don't need to be an expert to start building; you just need patience and curiosity.
After wrestling with the limitations of basic app builders, I realized I needed a tool that could handle more complex, end-to-end coding without forcing me into a template. That search eventually led me to Claude — and down an entirely different, incredibly visual rabbit hole of game development.
But that is a story for the next post.