How I built a supersonic AI riddling duel in under 20 Minutes (with zero manual coding)

Can an AI developer agent build complex full-stack logic without constant hand-holding? To test this, I set up the **#NapkinChallenge**: take a rough architectural sketch on a paper napkin and turn it into a fully functional web application in under 20 minutes. The goal: Build **"Blaine the Mono's Riddling Competition"** — a game where you duel a psychotic, sentient supersonic monorail from Stephen King's *The Dark Tower* series. If you trip him up with three logic-defying riddles, you save the passengers. If his neural net solves them, you crash at Mach 4. The result? The AI built the entire application with **zero manual lines of code written by me**. Here is how the architecture works, how the backend uses the new `@google/genai` SDK, and how you can run the challenge yourself. ## The Architecture (from sketch to code) The napkin sketch outlined a straightforward but highly interactive setup: 1. **Frontend**: A UI built in Next.js (App Router). 2. **Backend**: A Next.js API route that forwards user riddles to the Gemini API. 3. **The Engine**: The `gemini-3-flash-preview` model, prompted to act as Blaine the Mono. It must analyze the riddle and return structured JSON containing its solution, status, and theatrical psychotic commentary.  ## Key Takeaways 1. **Zero-Code Feasibility**: Developer agents like Antigravity can now understand visual layouts, bootstrap templates, design customized styling systems, and integrate real-world API clients with robust error boundaries. 2. **Styling is a First-Class Citizen**: The agent did not just generate functional code; it constructed a bespoke styling sheet (`src/app/globals.css`) incorporating Orbitron typography, custom CSS scrollbars, CRT overlays, and reactive screen shakes using CSS keyframes. 3. **Time to Gameplay**: The entire application was built in under 20 minutes, including the time it took to generate the code, test it, and get it running. ## Video See the full video of the process: {% embed https://youtu.be/PvtdEbc2xPM %} ## Join the #NapkinChallenge 📝 Now it is your turn. Can you match the speed of autonomous generation? 1. **Sketch** your app concept, system architecture, or database model on a physical paper napkin. 2. **Upload** the photo to Antigravity, Gemini, or Google AI Studio. 3. **Prompt** your agent to build the code from the image alone. 4. **Share** a video or screenshot of your live app using `#NapkinChallenge`! Let's see what you can build!