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

• Emanuel C. Silva FURG
• Emily S. M. Salum FURG
• Gabriel M. Arantes FURG
• Matheus P. Pereira FURG
• Vinicius F. Oliveira FURG
• Alessandro L. Bicho FURG

DOI: https://doi.org/10.5753/sbgames_estendido.2025.14890

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 supervised-trained 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.

Keywords: Artificial Intelligence, Procedural Content Generation, Game Design, Natural Language Processing, BERT

References

Amaral, G., Baffa, A., Briot, J.-P., Feijó, B., e Furtado, A. (2022). An adaptive music generation architecture for games based on the deep learning transformer model. In Anais do XXI Simpósio Brasileiro de Jogos e Entretenimento Digital, pages 13–18, Porto Alegre, RS, Brasil. SBC.

Awiszus, M., Schubert, F., e Rosenhahn, B. (2023). Wor(l)d-gan: Toward natural-language-based pcg in minecraft. IEEE Transactions on Games, 15(2):182–192.

Hastings, E. e Stanley, K. (2010). Automatic content generation in the galactic arms race video game. Computational Intelligence and AI in Games, IEEE Transactions on, 1:245 – 263.

Hello Games (2016). No man’s sky (video game). Released June 2016 for PS4, PC, Xbox One.

Jagdale, D. (2021). Finite state machine in game development. International Journal of Advanced Research in Science, Communication and Technology, 10(1).

Lima, E., Feijó, B., Cassanova, M., e Furtado, A. (2023). Chatgeppetto - an ai-powered storyteller. In Anais do XXII Simpósio Brasileiro de Jogos e Entretenimento Digital, page 28–37, Porto Alegre, RS, Brasil. SBC.

Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., e Chintala, S. (2019). Pytorch: An imperative style, high-performance deep learning library. In Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché Buc, F., Fox, E., e Garnett, R., editors, Advances in Neural Information Processing Systems 32, pages 8026–8037. Curran Associates, Inc.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., e Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.

Persson, M. (2010). Minecraft (pc game). PC Game.

Senanayake, C. (2025). Dynamic npc ai using reinforcement learning for an enhanced gaming experience.

Song, Y., Wang, T., Cai, P., Mondal, S. K., e Sahoo, J. P. (2023). A comprehensive survey of few-shot learning: Evolution, applications, challenges, and opportunities. ACM Comput. Surv., 55(13s).

Usherwood, P. e Smit, S. (2019). Low-shot classification: A comparison of classical and deep transfer machine learning approaches.