SpellForger: Prompting Custom Spell Properties In-Game using BERT supervised-trained model

TL;DR

SpellForger tackles enabling player-driven spell creation through natural-language prompts by integrating a BERT-based interpreter as a core gameplay mechanic. The approach couples a Unity frontend with a Python backend, using a supervised model trained on spell descriptions and attributes to map prompts to spell prefabs and balancing factors, augmented by a modular Trigger/Effect system. Key contributions include a defined representation of Spell Type, Status, and Effects, a Status Effects Matrix, and a real-time generation latency around 200 ms, alongside a data-creation workflow that leverages GPT-3 few-shot synthetic data. The work demonstrates the feasibility of AI-assisted co-creation in games and outlines a practical path toward automated AI data pipelines to ease adoption by developers.

Abstract

Introduction: The application of Artificial Intelligence in games has evolved significantly, allowing for dynamic content generation. However, its use as a core gameplay co-creation tool remains underexplored. Objective: This paper proposes SpellForger, a game where players create custom spells by writing natural language prompts, aiming to provide a unique experience of personalization and creativity. Methodology: The system uses a supervisedtrained BERT model to interpret player prompts. This model maps textual descriptions to one of many spell prefabs and balances their parameters (damage, cost, effects) to ensure competitive integrity. The game is developed in the Unity Game Engine, and the AI backend is in Python. Expected Results: We expect to deliver a functional prototype that demonstrates the generation of spells in real time, applied to an engaging gameplay loop, where player creativity is central to the experience, validating the use of AI as a direct gameplay mechanic.

Figures (1)

• Figure 1: Distribution of the spell database, grouped by type