My research connects two things usually done by different people: a decade of hands-on quantum-materials experiments and AI systems that assist the expert judgment those experiments require. Every claim below is grounded in instruments I have operated and analysis loops I have run by hand — before teaching an agent to help.
The expert loop in scattering analysis — freeing parameters, judging residuals, grading a reduction — never got automated. I study how much of it LLM agents can help with when given real domain tools instead of chat, with one design across my tools: the agent sits on a tested scientific core, and numbers and rules live in code. It is live in MATERIA, NEBULA3D, RMCProfile Workbench (AI Copilot, beta) and NEXPLAN (MCP tools); Athanor tests agent-driven screening against non-LLM baselines. All of it is independent, personal open-source work.
Grounding principles: physics-based tools the agent must call, numbers and guardrails in code, actions a person can review, local-first models, and evals from real failures — not demos.
Kagome magnets host Weyl nodes and anomalous transport that the lattice can in principle switch — if you find a material where the switch operates. My first-author Nature Communications (2026) study of Mn3Ga found exactly that: an intrinsic topological Weyl phase transition driven by a magnetostructural transformation near room temperature. A new preprint on Mn3Sn (arXiv 2026) adds the disorder side: correlated local distortions enable an anomalous Hall response that the average symmetry forbids.
Why it matters: a lattice-coupled route between distinct Weyl states near room temperature — a potential pathway toward antiferromagnetic spintronics.
Average structures hide the physics. Using PDF, diffuse scattering, large-box RMC modeling, and symmetry-mode analysis, I resolve the distortions behind emergent order: local symmetry breaking emerging with antiferromagnetic order in kagome (Co,Fe)Sn (JACS 2024), quadrupolar ordering and spin-orbital dimers in GaNb4Se8 (PRB 2024), and bond ordering in the cluster Mott insulator GaTa4Se8 (PRR 2022).
The thread: disorder is not noise — quantifying it is what turns a structure into a mechanism.
RMC ensembles encode experimentally constrained disorder — but only as static snapshots. I extract dynamics from them: harmonic phonon bands, DOS, and simulated INS inferred from the ensembles and GPU-accelerated with WebGPU, plus 3D-ΔPDF pipelines where every cleanup decision is inspectable. Everything ships as browser tools — your own data, nothing to install.
Outcome: phonon spectra from RMC models of measured total scattering, with no separate simulation backend — released as working, open-source software.
I have worked hands-on at every step of the pipeline. Synthesis: flux and vapor-transport crystals, inert-atmosphere chemistry, MBE thin films. Measurement: neutron and synchrotron experiments designed and run at ORNL's Spallation Neutron Source and other national facilities, plus STM/SP-STM down to single molecules — under cryogenic, high-pressure, and UHV conditions.
Why it matters for AI: knowing where data comes from — and how it breaks — separates physics-grounded models from black boxes.