GAI4RDE

The Challenge

Rigorous Digital Engineering (RDE) is arguably the most powerfully transformative methodology in engineering today. So why isn’t everyone using it?

Think of RDE as virtual cartography for complex systems. By meticulously defining the function and relationships of each component, as well as requirements, digital engineers create detailed models of a system at different levels of abstraction. These models aren’t just diagrams; they’re reusable, analyzable artifacts that enable rapid design exploration, cybersecurity optimization, and even automated code generation. What’s more, RDE uses formal methods to mathematically prove that a system behaves as specified.

The result? An extremely high level of assurance, a high degree of traceability between components and different levels of abstraction, and significantly faster, safer, cheaper critical system development. This is a methodology that can literally shave months or years (and millions of dollars) off system development timelines, while simultaneously dramatically increasing system reliability.

The catch? RDE often has an prohibitively high cost in terms of the level of expertise required. Scaling RDE to its full potential across the DOD and industry would require an army of specialized computer science PhDs that simply doesn’t exist.

The Solution

With the Generative Artificial Intelligence for Rigorous Digital Engineering (GAI4RDE) Project, Galois developed RDE Wingman: an LLM-based, multi-agent framework that automates RDE workflows.

Trained on information from dozens of RDE papers, case studies, and even a 2000 page RDE training manual, RDE Wingman not only understands the big picture goals of Rigorous Digital Engineering, but how to do RDE: how to break down a problem into solvable steps and a system into coherent components with traceable connections, how to generate specifications and code, and how to maintain and evolve those specifications, models, code, and assurance artifacts. 

Users interact with RDE Wingman either via a command line tool for more advanced users, or a prompt-like interface for more general users. The prompt-based front end, integrated with a local LLM, is set up with a personality and script to seamlessly walk users through the RDE process. Through LLM-based conversation, RDE Wingman can gauge a user’s RDE knowledge and goals, recommend a plan of action, and then – based on the user’s specific requests (e.g., “Use Taphos to analyze this C++ code and give me a SysMLv1 model” or “I like agile programming and Python, but have types”) – put that plan into action on the backend.

Multi-Agent Framework

Because each stage of RDE demands specialized expertise, Galois built RDE Wingman as a multi-agent framework. At the center is an LLM-powered RDE agent that understands and oversees the overall process, autonomously delegating tasks to a network of sub-agents, each focused on a specific domain. For example, one sub-agent specializes in writing and understanding system requirements, while another handles system design. Some sub-agents are further supported by their own helpers, such as a shell agent that understands and writes command-line operations. This hierarchical structure prevents the core agent from being overloaded, while enabling the entire system to collaboratively execute the complex, multi-stage tasks involved in RDE.

The team has already successfully used RDE Wingman on a number of experimental applications, including to automatically draw a system architecture diagram, translate English language system requirements into a test bench, and more. If you give RDE Wingman a system specification, you can ask it to generate code, create a more or less detailed version of that same specification, or translate a specification from one language to another. You can also go the other way: give RDE Wingman a codebase, and ask it to generate a specification. 

Adaptive Assurance

Traceability and high assurance are built-in. Because RDE is the backbone of this framework, RDE Wingman has an understanding of abstraction layers and how they must relate to each other. And because formal methods are integral to RDE, it understands how to check that a specification and implementation are in alignment, either because they should be equivalent, or because one should refine the other. It will independently problem-solve to accomplish the goal you set for it, for example - searching online for a needed tool, and downloading it to your computer so that it can do the job.

The tool’s inherent malleability also makes it uniquely adapted to a rapidly changing technological environment. As AI agents continue to improve over time, RDE Wingman can integrate the latest developments. And as new tools or DSLs are introduced to the RDE ecosystem, RDE Wingman can simply learn them, adding to its toolbelt. This reactive dynamism also makes RDE Wingman well-suited for integration into CI/CD/CV pipelines: once a system model has been built, the tool can be used to ensure that both system and model stay up-to-date as changes are made – e.g., automatically updating code in response to changes in the model or system requirements. 

Value Add

Even as a prototype, RDE Wingman is making RDE workflows 10-100X faster. Extrapolated to large-scale projects, it could feasibly save months or years of person hours and millions of dollars in costs for complex system development and sustainment projects. 

The RDE Wingman also acts as a co-pilot for engineers who want to use and learn formal methods and RDE, but avoid taking weeks of professional development time to take the RDE course and conduct RDE “skunkworks” or self-educational projects. While using the RDE Wingman, engineers learn how to do applied formal methods and model-based engineering by example, working hand in hand with an AI agent.

Even more significantly,  engineers aren’t limited to working with just a single RDE Wingman. As many RDE Wingmen can be run simultaneously as desired, so long as the LLM resources are available. The RDE Wingmen can work as a kind of RDE Squadron or Swarm, what we call the H.O.A.R.D.E.—the Hierarchical Orchestration of Autonomous Rigorous Digital Entities. Imagine if each engineer on your team had ten AI collaborators who knew formal methods and could work 24/7, helping them achieve their engineering goals. That’s where the RDE Wingman is going next.

Fully realized, RDE Wingman could streamline the development and modification of virtually every imaginable cyber-physical, software, or hardware system, both new and legacy, from aircraft to computer chips to hospital IOT systems and beyond.