TriDuel
Classic Rock Paper Scissors game with animated hand gestures, score tracking, win streaks, and playful celebrations. Part of the 777-1 Experiment: 7 projects, 7 context engineer subagents, 7 case studies, one algorithm for predicting prompt failures.
Project Demo
English video coming soon
Tech Stack
Category
777-1 ExperimentAbout This Project
TriDuel is a polished Rock Paper Scissors game featuring smooth animations, satisfying sound effects, score tracking, and win streak celebrations. Players compete against an AI opponent with randomized choices and enjoy visual feedback for wins, losses, and ties. This project is part of the 777-1 Experiment, built with a "goldilocks zone" prompt that is intentionally underspecified to test how AI models handle ambiguity. After initial generation, 7 context engineer subagents (Amber, Kristy, Micaela, Lindsay, Eesha, Daniella, and Cassandra) will review the application in sequence, each focusing on their specialized domain. The findings will be documented in a case study that contributes to developing an algorithm for predicting prompt failures before they happen. As the simplest project in the experiment with no authentication requirements, TriDuel serves as the baseline control and is first in the execution sequence. Its simplicity helps establish a baseline for subagent effectiveness before tackling more complex applications.
Related Projects

AI Prompt Engineering Toolkit
Platform for predicting prompt failures before they happen, powered by 7 context engineer subagents derived from 129 code reviews. Currently running the 777-1 experiment: 7 projects, 7 case studies, one algorithm.