Bouncing bomb card game Design workflow
I mapped out a high-level workflow to track how ideas moved from sketch → AI generation → digital prototype → physical cards → playtesting.
As a board game enthusiast, I’ve long wanted to create a simple card game. This summer project explored whether AI-only platforms (ChatGPT, Lovable, Replit, etc.) could take an idea from scratch all the way to a playable prototype - without me writing any code.
Also I'd like to learn about the current limits or things that these AI platform ace and gaps.
🧢 Role
Designer
🙌 Collaborator
Board Game Friends
🗓️ Date
2025
I mapped out a high-level workflow to track how ideas moved from sketch → AI generation → digital prototype → physical cards → playtesting.
To kick things off, I sketched the core mechanics of how the game might play. These rough ideas became the starting point for AI-powered iteration.
Using ChatGPT, I ran through multiple iterations to refine the game loop, number of cards for 3–8 players, and mechanics balance. This resulted in Version 1 of the rules.
I translated the rules into digital prototypes using AI-driven platforms like Replit and Lovable. Replit came closest to what I envisioned, enabling me to playtest online.
I designed simple card layouts in Figma, printed them, and created a physical deck for in-person playtesting.
Early feedback from my board game group:
💣 Too many “fluffy bomb” cards made rounds drag
💣 Reverse cards confused new players
💣 Overall potential felt strong, but tweaks were needed before the next round of testing
The first playtest surfaced key issues around pacing, clarity, and card balance.
My aim is to reduce confusion and streamline gameplay, then create a Version 2 for the next round of playtesting to gather more feedback.
This project showed me how AI platforms can accelerate prototyping, but also that human playtesting and feedback are irreplaceable for balancing fun and clarity in game design.
