/

/

The Dyad Dispatch: November 2025

/

/

The Dyad Dispatch: November 2025

The Dyad Dispatch: November 2025

The Dyad Dispatch: November 2025

Date Published

Nov 6, 2025

Nov 6, 2025

Contributors

Share

Share

Date Published

Nov 6, 2025

Contributors

Share

Welcome to the first edition of The Dyad Dispatch! A monthly roundup of Dyad news for the Modeling & Simulation community 

Upcoming Webinars and Workshops

Mitsubishi Electric – Building High-Fidelity HVAC Models with Dyad and Scientific Machine Learning — 13 November 2025

Join Christopher Laughman (Mitsubishi Electric Research Laboratories) and Avinash Subramanian (JuliaHub) for a webinar exploring how advanced simulation tools can transform HVAC system modeling. Register here.

Sign up for Webinars With Dyad Experts

Workshop at MIT — November 18

Dr. Chris Rackauckas, and Anshul Singhvi will be leading a workshop on Dyad: Agentic AI for Modeling and Simulation, on November 18, at MIT, where they will demonstrate building of real world models using AI agents.

Product News

Dyad Studio 1.2.0: Stable, Smarter, and AI-Ready

We’ve officially launched Dyad Studio v1.2.0. This release introduces:

  • Graphical model editor within VSCode

  • Submodule Support for clean, modular model libraries

Check out this short video showing how to create an RC circuit in the new diagram view:

Read more: Announcing Dyad Studio v1.2.0

Agentic AI for Model-Based Engineering

The real barrier to AI in Model-Based Engineering isn’t speed—it’s correctness. Fast code means nothing if it doesn't fulfil the fundamentals of physics.

Dyad solves this by embedding AI agents inside a constrained, unit-tested framework, ensuring models are correct by design and errors are caught early.

Watch the short demo to see how Dyad’s Agentic AI handles tasks like automated calibration with full physics validation:

View the full guide: Agentic AI for Model-Based Engineering

What’s New With ModelingToolkit

ModelingToolkit.jl continues to advance as a unified framework for modeling and simulation across ODEs, DAEs, and optimization problems.

At JuliaCon 2025, Aayush Sabharwal highlighted new features including type-stable parameters with MTKParameters, automatic Initialization for consistent start conditions, and HomotopyContinuation for polynomial systems.

Read the full article: What's New With ModelingToolkit

Dyad: Agentic AI for Modeling and Simulation

Dr. Chris Rackuackas recently facilitated a workshop on Dyad: Agentic AI for Modeling and Simulation at Norwegian University of Science and Technology(NTNU). Around 30 participants gained hands-on experience in building real-world models using over 30 million Agentic AI tokens, exploring acausal modeling, working with validated reusable components, and leveraging Dyad’s pre-built models across domains such as electrical, mechanical, HVAC, and more.

Dyad at Simulation World, Detroit

At Simulation World, JuliaHub CEO and Co-Founder Dr. Viral Shah joined industry leaders from Boeing, Cummins, Lockheed Martin, Synopsys, and Booz Allen Hamilton for a panel on Digital Engineering in the Age of AI, moderated by Dr. Prith Banerjee.

The discussion explored the future of MBSE, digital twins, simulation-driven design, AI/ML, and agentic AI, along with how the next generation of engineers will be trained for a digitally integrated future.

Read more: Simulation World

Learn by Building: The Hands-On Dyad Tutorial Series

If you’re new to Dyad, our new video series walks you from the first model to advanced control systems. Start with:

  1. Getting Started with Dyad: build your first component library

  2. Creating Components with Acausal Modeling: model physical laws directly

  3. DC Motor + PID Control: design and tune controllers end-to-end

Find out more: Hands-On with Dyad

More Resources

Want to get enterprise support, schedule a demo, or learn about how we can help build a custom solution? We are here to help. Contact Us

Authors

JuliaHub, formerly Julia Computing, was founded in 2015 by the four co-creators of Julia (Dr. Viral Shah, Prof. Alan Edelman, Dr. Jeff Bezanson and Stefan Karpinski) together with Deepak Vinchhi and Keno Fischer. Julia is the fastest and easiest high productivity language for scientific computing. Julia is used by over 10,000 companies and over 1,500 universities. Julia’s creators won the prestigious James H. Wilkinson Prize for Numerical Software and the Sidney Fernbach Award.

Authors

JuliaHub, formerly Julia Computing, was founded in 2015 by the four co-creators of Julia (Dr. Viral Shah, Prof. Alan Edelman, Dr. Jeff Bezanson and Stefan Karpinski) together with Deepak Vinchhi and Keno Fischer. Julia is the fastest and easiest high productivity language for scientific computing. Julia is used by over 10,000 companies and over 1,500 universities. Julia’s creators won the prestigious James H. Wilkinson Prize for Numerical Software and the Sidney Fernbach Award.

Authors

JuliaHub, formerly Julia Computing, was founded in 2015 by the four co-creators of Julia (Dr. Viral Shah, Prof. Alan Edelman, Dr. Jeff Bezanson and Stefan Karpinski) together with Deepak Vinchhi and Keno Fischer. Julia is the fastest and easiest high productivity language for scientific computing. Julia is used by over 10,000 companies and over 1,500 universities. Julia’s creators won the prestigious James H. Wilkinson Prize for Numerical Software and the Sidney Fernbach Award.

Learn about Dyad

Get Dyad Studio – Download and install the IDE to start building hardware like software.

Read the Dyad Documentation – Dive into the language, tools, and workflow.

Join the Dyad Community – Connect with fellow engineers, ask questions, and share ideas.

Learn about Dyad

Get Dyad Studio – Download and install the IDE to start building hardware like software.

Read the Dyad Documentation – Dive into the language, tools, and workflow.

Join the Dyad Community – Connect with fellow engineers, ask questions, and share ideas.

Contact Us

Want to get enterprise support, schedule a demo, or learn about how we can help build a custom solution? We are here to help.

Contact Us

Want to get enterprise support, schedule a demo, or learn about how we can help build a custom solution? We are here to help.