The Defense Innovation Unit (DIU), part of the U.S. Department of Defense (DOD), is leading an experimental project, Thunderforge, to build a custom agentic AI system with multiple digital “agents” critiquing war plans across different military domains, running parallel analyses, and flagging potential weaknesses neglected by human planners.
The U.S. Indo-Pacific Command (INDOPACOM) tested some of Thunderforge’s AI capabilities during a tabletop exercise in June. The project, first announced in March, remains in the early stages, with an initial rollout targeting commanders and planners across INDOPACOM and its sister command in Europe (EUCOM). Ultimately, the system will query internal databases, run DoD-grade simulations, and integrate with pre-existing software, such as DARPA’s SAFE-SiM modeling and simulation architecture, to create vast numbers of realistic and plausible military scenarios for study.
California-based Scale AI is steering the project, with Microsoft supplying its large language model (LLM) technology and Anduril providing modeling. Scale AI says its system is designed to coordinate multiple custom agents, each leveraging a range of models and acting as a digital staff officer to help synthesize data for mission-critical planning activities.
“These agents dynamically collaborate, fusing separate analyses into a more comprehensive view for operational planners to consider,” says Dan Tadross, the head of public sector at Scale AI. “This approach is designed to shift the role of the operator from being ‘in the loop’—micromanaging a single process—to being ‘on the loop,’ where they can apply their strategic judgment to the options generated.”
Enhancing AI in Military Planning
The DIU has split Thunderforge’s development into two tracks, starting with augmenting the cognitive plan-writing process through red-teaming. The system will submit a human-authored plan to a team of AI agents to offer perspectives across multiple domains—including logistics, intelligence, and cyber and information operations. “You can really customize it however you want,” says Bryce Goodman, the DIU’s chief strategist for AI.
The second track will link with DOD’s most advanced modeling software to conduct modeling simulations, generate and analyze outputs, and interpret the results. Even for humans, building simulations and understanding the raw results requires extensive training in a specialized skillset. Goodman says, “Where that becomes really powerful is that now, the LLMs are calling on tools the DOD has built and validated, and suddenly you’re combining the brute pattern recognition that AI does with physics-based simulations or other logical reasoning tools that perform similar tasks. It’s scaffolding in all those capabilities.”
With track one underway, the DIU has already developed a minimum viable product, though it requires deeper integration with classified data systems and separate government…
Read full article: Thunderforge Aims to Transform AI Wargames

The post “Thunderforge Aims to Transform AI Wargames” by Shannon Cuthrell was published on 07/23/2025 by spectrum.ieee.org
Leave a Reply