From Prompt to Simulation: Coding Agents on Matlantis – Natural Language Workflows for Atomistic Simulations

Coding agents that write and run code from instructions in natural language are beginning to change how atomistic simulations are set up and run. This webinar shows how to use them with Skills for Matlantis, and what they can and cannot do today.

Who should attend

• Researchers considering atomistic simulation for their work, including those without a background in computational chemistry
• Computational scientists who want to spend less time on setup and post-processing
• R&D teams interested in using coding agents for simulation workflows

Outline

Atomistic simulation involves a good deal of work around the analysis itself: building structure files, choosing calculation settings, and then collecting and plotting the results. These steps can take up much of a project’s time. How to set up and run the calculations has also depended largely on the experience of specialists, which has made it hard for researchers from other fields to get started.

As generative AI tools such as ChatGPT and Claude have advanced, coding agents, which write and run code from instructions given in natural language, are now being used in R&D as well. Matlantis has released Skills tailored to its simulation workflows, and this webinar shows how to put coding agents to work on atomistic simulations.

When simulations can be driven through conversation in natural language, experienced users can leave routine work to the agent and spend their time on the questions they actually want to investigate. Researchers who have relied on specialists are also starting to be able to try those calculations themselves. Drawing on examples of projects carried out with coding agents, the session looks at what coding agents can already handle, how to get good results from them, and where their limits currently lie.

These calculations run on Matlantis PFP, a universal machine learning interatomic potential covering 96 elements, so no system-specific model needs to be trained.

Speaker

Joshua Young

Senior Application Scientist,
Matlantis Inc.

Joshua received his Ph.D. in Materials Science and Engineering from Drexel University, followed by appointments at the Naval Research Laboratory, Binghamton University, and the New Jersey Institute of Technology. Over the course of his career, he has used a wide variety of computational techniques, including density functional theory, molecular dynamics, and materials informatics/machine learning, to study and design materials for electronics, batteries, catalysis, and more.

Webinar Details

Apply here