Wargames are a powerful tool for understanding and rehearsing real-world decision making. Automated play of wargames using artificial intelligence (AI) enables possibilities beyond those of human-conducted games, such as playing the game many times over to see a range of possible outcomes. There are two categories of wargames: quantitative games, with discrete types of moves, and qualitative games, which revolve around open-ended responses. Historically, automation efforts have focused on quantitative games, but large language models (LLMs) make it possible to automate qualitative wargames. We introduce "Snow Globe," an LLM-powered multi-agent system for playing qualitative wargames. With Snow Globe, every stage of a text-based qualitative wargame from scenario preparation to post-game analysis can be optionally carried out by AI, humans, or a combination thereof. We describe its software architecture conceptually and release an open-source implementation alongside this publication. As case studies, we simulate a tabletop exercise about an AI incident response and a political wargame about a geopolitical crisis. We discuss potential applications of the approach and how it fits into the broader wargaming ecosystem.

Tallinn, Estonia - Things are bad on the small island nation of Berylia after a diplomatic row with Crimsonia, its bigger neighbour and rival. There are street protests by the Crimsonian minority in Berylia, which then suffers a wave of cyber-attacks that make it lose control of its drones and its only international airbase. Crimsonia is blamed for the cyberoffensive even though there's no hard proof. Crippled by the attacks, Berylia, a new member of the North Atlantic Treaty Organisation (NATO), weighs its options. One of them is to invoke Article 5 and take the military alliance to war against Crimsonia.