Teaching AI to Speak LAMMPS: A Practical Guide to Prompting and Script Checking

Large language models (LLMs) are opening new possibilities for assisting with scientific simulations, but using them effectively requires careful prompting and validation, especially in domain-specific languages like LAMMPS. In this hands-on tutorial, participants will learn how to prompt large language models to generate LAMMPS input scripts and how to use a structure-aware static parser to catch common syntax and logic errors before running a simulation. We will explore typical failure modes, discuss prompt design strategies, and demonstrate a practical workflow for integrating AI tools into molecular dynamics projects. The tutorial will also introduce the LARK parsing library used to build the validator, giving interested participants a chance to understand and contribute to its ongoing development. This session is designed for both new and experienced LAMMPS users interested in improving usability, reproducibility, and automation in their workflows.

Additional Info: For attendees to follow along with the Jupyter notebooks we will be using, make a nanoHUB account here: https://nanohub.org/register/.